Last modified on: November 10th, 2015
Last updated on November 10th, 2015

The Computer Vision and Pattern Recognition Group in Bahria University is interested in the following areas of   research:

  • Advanced medical image analysis
  • Object class recognition
  • Tracking of objects in video
  • Hand-writing recognition
  • Biometrics (Fingerprints, retina veins etc.)
  • Content-based image and video retrieval
  • Pattern Recognition
  • Clustering in Euclidean and General feature spaces.
  • Modeling, classification and anomaly detection in Euclidean and General feature spaces
  • Automated scanning and recognition of hand written document and converting it to computer understandable text
  • Automatic extraction of text from TV channels. One can search the video clips based on the text contained in it. Typically applicable for news channel

Dr. Shehzad Khalid

Head of Bahria University CVPR Research Group
Associate Professor
Department of Computer Engineering
Bahria University, Islamabad CampusEmail: shehzad@bahria.edu.pk
Tel(off): +92-51-9260002, Ext(315)

Prof. Dr. Shehzad Khalid
 
Email  shehzad@bahria.edu.pk
Phone 0092-51-9261281
Education PHD (University of Manchester, UK)
Specialization Image Processing, Computer Vision, Biometrics, Medical Imaging, Machine learning,  Signal Processing, Urdu OCRs, Natural Language Processing, Dimensionality Reduction, Time Series Analysis, English and Urdu OCRs,Natural Language Processing
Associate Prof. Dr. Imran Siddiqui
 
Email imran.siddqi@gmail.com
Education PHD (Paris Descartes University, France)
Specialization  Digital Image processing
Assistant Prof. Dr. Amina Jameel
 
Email  amina@bahria.edu.pk
Phone 051-926002 ext 359
Education PHD (NUST Pakistan)
Specialization

Image Processing

Signal Processing

Image Fusion

Image Registration

Medical Imaging
Dr Usman Akbar
 
Email  usmakram@googlemail.com
Phone 00923336913921
Education MS (NUST Pakistan)
Specialization Image Processing, Signal Processing, Machine learning, Pattern Recognition, Computer Vision, Artificial Intelligence and Medical Imaging
Lecturer. Engr. Abubaker Yamin
 
Email  Abubakar.yamin@gmail.com
Phone +92-321-4065499
Education MS (Computer Engineering) (NUST-Pakistan)
Specialization

Image Processing, Pattern Recognition, Computer Vision, Artificial Intelligence
Dr. Muhammad Muzammal
 
Email  muhammadmuzammal@gmail.com
Phone +92 51 9260002 Ext. 426
Education PHD (University of Leicester, UK.)
Specialization Data Mining, Algorithms, Image Processing
Lecturer. Engr. Bushra Sabir
 
Email  bushra.sabir@bahria.edu.pk
Phone 051-926002 ext 439
Education MS (NUST Pakistan)
Specialization

Image Processing

Pattern Recognition

Machine Learning

Spatial and temporal surveillance systems

Medical Imaging
Assistant Prof. Imran Fareed Nizami
 
Email  imran.fareed@bui.edu.pk
Phone 051-92-51-9260002 Ext: 358
Education MS .(yonsei University, South Korea)
Specialization Signal Processing , Image Processing , Pattern Recognition
RA. Engr. Muhammad Usman Akbar
 
Email  muhamadusman@outlook.com
Phone 051-926002
Education MS
Specialization

Image Processing, Medical Imaging

Dr Shehzad Khalid

 

Book Chapter:

 

  1. Shehzad Khalid, “Behavior recognition using any feature space representation of motion trajectories”, In book “Video Surveillance”, Intech, 2011, ISBN 978-953-307-958-5.
  2. Usman Akram, Shehzad Khalid, “A software system for grading diabetic retinopathy by analyzing retinal images”, In book “Knowledge based processes in software development”, IGI Global, 2012.
  3. Anwar Shaukat, Imran Farid, Shehzad Khalid, Amina Jamil, Detection of Lung Nodules in CT Scan Data- A Review, in book “Ensuring Patient Safety and Confidentiality through Secure Health Information Management”, 2015.
  4. Uzma Jamil, Shehzad Khalid, Analysis of Valuable Techniques & Algorithms Used in Automated Skin Lesion Recognition Systems, in book “Ensuring Patient Safety and Confidentiality through Secure Health Information Management”, 2015.

 

Publications:

                                Journal

  1. Shehzad Khalid and Andrew Naftel, “Classifying spatiotemporal object trajectories using unsupervised learning in the coefficient feature space”, ACM Multimedia Systems Special Issue: Multimedia video surveillance, Vol. 12, No. 3, pp. 227-238, December 2006. [IF-0.44]
  2. Shehzad Khalid and Andrew Naftel, “Automatic motion learning in the presence of anomalies using coefficient feature space representation of trajectories”, Acta Automatica Sinica, Vol. 36, No 5, January, 2010. [International Journal]
  3. Shehzad Khalid and Andrew Naftel, “Self-Tuned Unsupervised Learning of Motion Trajectories”, Vol. 2, No. 1, pp. 27-36, August 2009. [HEC Recognized Journal]
  4. Shehzad Khalid, “Motion based behaviour learning, profiling and classification in the presence on anomalies”, Pattern Recognition, 43, No. 1, pp. 173-186, 2010. [IF- 2.584]
  5. Shehzad Khalid, “Activity classification and anomaly detection using m-Mediods based modeling of motion patterns”, Pattern Recognition, 43, No. 10, pp. 3636-3647, 2010. [IF- 2.584]
  6. Khalid, S.Razzaq, “Frameworks for multivariate m-mediods based modeling and classification in Euclidean and general feature spaces, Pattern Recognition, Vol. 45, No. 3, pp. 1092-1103, March 2012. [IF- 2.584]
  7. Shehzad Khalid,“Incremental indexing and retrieval mechanism for scalable and robust contour-based shape matching”, Multimedia Systems, Vol. 18, Issue 4, pp. 319-336, July 2012. [IF-0.60]
  8. Usman Akram, Shehzad Khalid, “Identification and Classification of Microaneurysms for Early Detection of Diabetic Retinopathy”, Pattern Recognition, Vol. 46, Issue 1, pp. 107-116, Jan 2013. [IF- 2.584]
  9. Sohail Jabbar, Abid Ali Minhas, Imran Shafi, Shehzad Khalid and Rabia Iram, “Intelligent Optimization of Wireless Sensor Network through Bio-Inspired Computing: Survey and Future Directions”, International Journal of Distributed Sensor Network, http://dx.doi.org/10.1155/2013/421084, 2013. [IF- 0.923]
  10. Usman Akram, Shehzad Khalid, Anam Tariq, M. Younus Javed, Detection of neovascularization in retinal images using multivariate m-Mediods based classifier, Computerized Medical Imaging and Graphics, vol. 37, no. 5-6, pp. 346-357, 2013. [IF-1.664]
  11. Usman Akram, Shehzad Khalid, Anam tariq, Shoab Khan, “Detection and classification of retinal lesions for grading of diabetic retinopathy”, Journal of Computers in Biology and Medicine, vol 45, pp. 161-171, 2014. [IF- 1.162]
  12. Mehr Yahya, Taimoor Khan, Armughan Ali, Ali Mustafa, Shehzad Khalid, “Machine learning, a solution for intrusion detection”, Journal of Basic and Applied Scientific Research, vol. 4, 2014. [ISI indexed].
  13. Shehzad Khalid, Sadaf Mukhtar, Sohail Jabbar, Seungmin Rho, “Accurate and efficient shape matching approach using vocabularies of multi-feature space representations”, Journal of Applied Mathematics, 2014, [IF- 0.720]
  14. Shehzad Khalid, Sannia Arshad, Sohail Jabbar, Seungmin Rho, “Robust Framework to Combine Diverse Classifiers Assigning Distributed Confidence to Individual Classifiers at Class Level”, Scientific World Journal, 2014. [IF- 1.219]
  15. Mubashir Ali, Shehzad Khalid, M. Haneef Saleemi,A novel stemming approach for Urdu language,Journal of Applied Environmental and Biological Sciences, vol. 1(7), 2014 [ISI Indexed]
  16. Muhammad Nazakat, Shehzad Khalid, Imran Siddiqi, A Review of offline signature verification techniques, Journal of Applied Environmental and Biological Sciences, vol. 1(9), pp. 342-347, 2014 [ISI Indexed]
  17. Jawad-ur-Rehman Chughtai, Shehzad Khalid, Imran Siddiqi, Online signature verification : A review, Journal of Applied Environmental and Biological Sciences, vol. 1(9), pp. 303-308, 2014 [ISI Indexed]
  18. Sannia Arshad, Shehzad Khalid, “A hybrid approach to combine heterogeneous classifiers using weight learning robust to the presence of class label noise and imbalanced classes”, Bahria University Journal of Information & Communication Technology, 2014. [HEC Recognized]
  19. Shahid Razzaq, Shehzad Khalid, “Determination of System Dimensionality from Observing Near-Normal Distributions”, Journal of Abstract and Applied Analysis, 2015. [IF- 1.274]
  20. Sohail Jabbar, Abid Ali Minhas, Muhammad Imran, Shehzad Khalid, Energy Efficient Strategy for throughput Improvement in Wireless Ad
    Hoc Sensor Networks, Journal of Sensors, vol. 15(2), pp. 2473-2495, 2015. [IF- 2.048]
  21. Shehzad Khalid, Usman Akram, Shahid Razzaq, “Behaviour recognition using multivariate m-mediod based modelling of motion trajectories”, Multimedia Systems, vol. 21(5), pp. 485-505, [IF-0.44]
  22. Shahid Razzaq, Shehzad Khalid, “TOBAE: A density-based agglomerative clustering algorithm”, Journal of Classification, 10.1007/s00357-015-9166-2, 2015. [IF-0.571]
  23. Sohail Jabbar, Rabia Iram, Abid Ali Minhas, Chaudhary Muhammad Imran, Shehzad Khalid “EASARA: Energy Aware Simple Ant Routing Algorithm in Wireless Sensor Network”, Recent Advancements in Soft Computing and its Application, The Scientific World Journal, [IF- 1.219]
  24. Saima Shaheen, M. Younus Javed, Muid Mufti, Shehzad Khalid, Aasia Khannum, Shoab Khan and M. Usman Akram, A Novel Compression Technique For Multi-Camera Nodes Through Directional Correlation, International Journal of Dsitributed Sensor Network, vol. 2015, Article ID 539838, 2015. doi:10.1155/2015/539838. [IF- 0.923]
  25. Amna Waheed, M. Usman Akram, Shehzad Khalid, Zahra Waheed, Muazzam A. Khan, Arsalan Shaukat, Hybrid Features and Mediods Classification based Robust Segmentation of Blood Vessels, Journal of Medical Systems, 2015. [IF- 2.213]
  26. R. Malik, T. Ahmad, M. Farhan, M. Aslam, S. Jabbar, S. Khalid, M. Kim, Big-Data: transformation from heterogeneous data to semantically enriched simplified data, Multimedia Tools and Applications, pp 1-21, 2015. [IF- 1.346]
  27. Usman Akram, Anam Tariq, Shehzad Khalid, Ubaid ullah Yasin, M. Younis Javed, Glaucoma detection using novel optic disk localization, hybrid feature set and classification techniques, Australasian physical and engineering sciences in Medicine, 2015. [IF- 0.882]
  28. Shehzad Khalid, Sadaf Mukhtar, “A hybrid shape matching framework for efficient and effective shape matching”, submitted to Journal of Image and Video Processing, 2014.
  29. Taimoor Khan, Shehzad Khalid, Mehr Durrani, Armughan Ali, Irum Inayat, “Survey of sentiment analysis techniques and the related NLP challenges”, submitted to Journal of Computing, Springer, 2014. [IF- 1.055]
  30. Taimoor Khan, Mehr Yahya, Usman Nazir, Shehzad Khalid, Kamran Habib Khan, “Survey of topic modeling techniques for aspect-based sentiment analysis”, submitted to BUJICT, 2014. [HEC Recognized]

 

 

                                Conference

  1. Andrew Naftel and Shehzad Khalid, “Video Sequence Indexing Through Recovery of Object Based Motion Trajectories”, Irish Machine Vision and Image Processing Conference, 232-239, Trinity College, Dublin, Sep 1-3, 2004.
  2. Naftel and S. Khalid, “Indexing and Retrieval of Video Clips via Object Motion Trajectory Descriptors”, Visualization, Imaging and Image Processing, 452-141, Sep 6-8, 2004, Marbella, Spain.
  3. Khalid and A. Naftel, “Evaluation of Matching Metrics for Trajectories-based Indexing and Retrieval of Video Clips”, IEEE workshop on Applications of Computer Vision, Jan 5-7 2005, Colorado, U.S.A.
  4. Shehzad Khalid and Andrew Naftel, “Motion Trajectory Clustering for Video Retrieval Using Spatiotemporal Approximation”, 8th International Conference on Visual Surveillance Systems, July 4, 2005, Amsterdam, Holland.
  5. Shehzad Khalid and Andrew Naftel, “Motion Clustering Using Spatiotemporal Approximation” IASTED international conference on Internet and Multimedia Systems and Applications, August 15-17,2005, Honololu, Hawaii,S.A.
  6. Andrew Naftel and Shehzad Khalid, “Classification and Prediction of Motion Trajectories Using Spatiotemporal Approximation”, BMVC workshop on Human Activity Recognition and Modelling, 9th Sep, 2005, Oxford, U.K.
  7. Shehzad Khalid and Andrew Naftel, “Classifying Spatiotemporal Object Trajectories using Unsupervised Learning of Basis Function Coefficients”, 3rd ACM International Workshop on Video Surveillance and Sensor Networks, Nov. 11-12, 2005, Singapore.
  8. Shehzad Khalid and Andrew Naftel, “Detecting Anomalous Motion Trajectories in the Coefficient Space”, IEEE International Conference on Computer Vision Systems, Jan 5-7, 2006, New York, S.A.
  9. Shahid Razzaq, Shehzad Khalid, “Image Matching using Feature Set Transformations”, in IEEE ICET, pp. 218-223, September 2011.
  10. Shehzad Khalid, “Robust shape matching using global feature space representation of contours”, in ICNC’12-MCC, pp. 724 – 728, Maui, Hawaii, USA, Feb.,
  11. Shehzad Khalid, Sadaf Mukhtar, “An approach to improve efficiency and accuracy of sophisticated and intelligent shape matching techniques”, IEEE 4th International Conference on Simulation, Modeling and Simulation, Bangkok, Thailand, 29-31 January, 2013.
  12. Shehzad Khalid, Sannia Arshad, “Framework for constructing hybrid classifier using weight learning to combine heterogeneous classifiers.” IEEE 5th International Conference on Computational Intelligence, Communication System and Networks. Seoul, South Korea, 24-26 September, 2013.
  13. Shehzad Khalid, Sannia Arshad, “A Robust Ensemble based Approach to Combine Heterogeneous Classifiers in the Presence of Class Label Noise”, IEEE 5th International Conference on Computational Intelligence, Communication System and Networks. Seoul, South Korea, 24-26 September, 2013.
  14. Anwar Shaukat, Shehzad Khalid, “A survey of e-learning techniques and the role of agent based assistance”, IEEE 5th International Conference on Computational Intelligence, Communication System and Networks. Seoul, South Korea, 24-26 September, 2013.
  15. Sadaf Sajjad, Shehzad Khalid, “Preprocessing Approach Identifying and Removing Noise”, 16th IEEE International Conference of Modelling and Simulation, Cambridge University, 26-28 March, 2014.
  16. Mubashir Ali, Shehzad Khalid, Muhammad Haneef Saleemi, in 2nd international conference on Computational and Social Sciences, Turkey, August 26-28, 2014.
  17. Mazhar Iqbal, Shehzad Khalid, Usman Akbar, News Classification Based On Their Headlines: A Review, 17th IEEE INMIC 2014 Conference, Bahria University, Karachi, Pakistan.
  18. Uzma Jamil, Shehzad Khalid, Comparative Study of Classification Techniques Used in Skin Lesion Detection Systems, 17th IEEE INMIC 2014 Conference, Bahria University, Karachi, Pakistan.
  19. Khurram Mustafa Abbassi, Irfan ul Haq, Ahmed Kamran Malik, Shehzad Khalid, Saba Fazil, Hanif Durad, On Access Control for Cloud Service Chains, 17th IEEE INMIC 2014 Conference, Bahria University, Karachi, Pakistan.
  20. M. Usman Hashmi, Ammar Ajmal, Arsalan Akhter, Shehzad Khalid, Waleed Manzoor, Application layer time synchronization utilizing symbol time recovery in wireless sensor networks, 17th IEEE USKIM-AMSS, Cambridge, U.K, 25-27 March, 2015.
  21. Uzma Jamil, Shehzad Khalid, Valuable pre-processing and segmentation techniques used in automated skin lesion detection systems, 17th IEEE USKIM-AMSS, Cambridge, U.K, 25-27 March, 2015.
  22. Shehzad Khalid, Uzma Naqvi, Imran Siddiqi, Framework for human identification through offline handwritten documents, 2nd IEEE International conference on computer, communication, and control technology, Kuching, Malaysia, 21-23 April, 2015.
  23. Israr Uddin Khattak, Imran Siddiqi, Shehzad Khalid and Chawki Djeddi, Recognition of Urdu ligatures: A Holistic Approach, 13th International Conference on Document Analysis and Recognition, Gammarth, Tunisia, 23-26 August, 2015.
  24. Jawad chughtai, Mehr Yahya, Shehzad Khalid, ONLINE SIGNATURE VERIFICATION USING CHEBYSHEV POLYNOMIALS, In 3rd International Conference on Computational and Social Siences, August 25-27, Johor Bahru, Malaysia.
  25. Israr-ud-din, Imran Siddiqi, Shehzad Khalid, LINE AND LIGATURE SEGMENTATION IN PRINTED URDU DOCUMENT IMAGES, In 3rd International Conference on Computational and Social Siences, August 25-27, Johor Bahru, Malaysia.
  26. Uzma Naqvi, Shehzad Khalid, Imran Siddiqi, Review of Offline Text Independent Writer Identification Techniques, In 3rd International Conference on Computational and Social Siences, August 25-27, Johor Bahru, Malaysia.
  27. Mazhar, Shehzad, Fizza, Armughan, Mehr, Farhan, NEWS HEADLINES CLASSIFICATION USING PROBABILISTIC APPROACH, In 3rd International Conference on Computational and Social Siences, August 25-27, Johor Bahru, Malaysia.

Dr Usman Akram

Research Publications Book Chapters:

1.      Samra Irshad, M. Usman Akram, Sara Ayub, Anaum Ayaz, “Retinal Blood Vessels Differentiation for calculation of Arterio-Venous Ratio”, Image analysis and Recognition, Lecture Notes in Computer Science, LNCS, Canada, 2015

2.      Ammama Furrukh Gill, Syeda Alishbah Fatima, M. Usman Akram, Sajid Gul Khawaja, Saqib Ejaz Awan , “Analysis of EEG Signals for Detection of Epileptic Seizure using Hybrid Feature Set”,  Theory and Applications of Applied Electromagnetics, Lecture Notes in Electrical Engineering, Volume 344, pp 49-57, 2015

3.      M. Usman Akram, Anam Tariq, Shafaat A Bazaz, Furqan Masood, Ubaid ullah Yasin, ” Self Diagnostic and Telemedicine System for Detection and Grading of Diabetic Retinopathy”, In book “Ensuring Patient Safety and Confidentiality through Secure Health Information Management,  IGI Global, 2015. Accepted

4.      S. Ayaz, S. Sahar, M. Zafar, M. U. Akram, Y. Nadeem “Analysis of OCT Images for Detection of Choroidal Neovascularization in Retinal Pigment Epithelial Layer”, 21st International Conference on Neural Information Processing, LNCS, pp. 226-233, Malaysia, Nov 2014.

5.      M. U. Azhar, M. D. Ashraf, A. Haider, S. O. Maruf, M. Naqvi, S. G. Khawaja, M. U. Akram, “Separation and Classification of Crackles and Bronchial Breath Sounds from Normal Breath Sounds Using Gaussian Mixture Model”, 21st International Conference on Neural Information Processing, LNCS, pp. 495-502, Malaysia, Nov 2014.

6.      M. Usman Akram, Sarmad Abbas, Anam Usman, Ubaid ullah Yasin, “Detection of Hemorrhages in Colored Fundus Images using Non Uniform Illumination Estimation”,  Image analysis and Recognition, Lecture Notes in Computer Science, (Berlin, Heidelberg: Springer), LNCS, pp.329-336, Portugal, 2014.

7.      Anam Usman, Sarmad Abbas, M. Usman Akram, Yasser Nadeem, ” A Robust Algorithm for Optic Disc Segmentation from Colored Fundus Images”, Image analysis and Recognition, Lecture Notes in Computer Science, (Berlin, Heidelberg: Springer), LNCS, pp. 303-310, Portugal, 2014.

8.      M. Usman Akram, Shehzad Khalid, “A software system for grading diabetic retinopathy by analyzing retinal images”, In book “Knowledge based processes in software development”, IGI Global, 2012.

9.      M. Usman Akram, Mahmood Akhtar, M. Younus Javed, “An Automated System for the Grading of Diabetic Maculopathy in Fundus Images”, 19th International Conference on Neural Information Processing, LNCS 6666, pp. 36-43, Nov 2012, Qatar

10.  M. Usman Akram, Anam Tariq, Shoab A Khan, “Detection of Neovascularization for Screening of Proliferative Diabetic Retinopathy”, Image analysis and Recognition, Lecture Notes in Computer Science, (Berlin, Heidelberg: Springer), LNCS, Portugal, pp. 372-379, Portugal, June12.

11.  M. Usman Akram, Aftab Khan, Khalid Iqbal and Wasi Haider Butt, “Retinal Image: Optic Disk Localization and Detection”, Image analysis and Recognition, Lecture Notes in Computer Science, (Berlin, Heidelberg: Springer), LNCS 6112, pp.40-49, Portugal, June10.

12.  Anam Tariq, M. Usman Akram, Sarwat Nasir, Rabia Arshad, “Fingerprint Image Postprocessing Using Windowing Technique”, Image analysis and Recognition, Lecture Notes in Computer Science, (Berlin, Heidelberg: Springer), LNCS 5112, pp. 915–924, Portugal, June08.

13.  Rabia Anwar, M. Usman Akram, Rabia Arshad, “A Modified Singular Point Detection Algorithm”, Image analysis and Recognition, Lecture Notes in Computer Science, (Berlin, Heidelberg: Springer), LNCS 5112, pp. 905–914, Portugal, June 2008.

ISI Indexed Journal Papers:

14.  M. Usman Akram, Anam Tariq, Shehzad Khalid, Sarmad Abbas, M. Younus Javed, Ubaid ullah Yasin, “Glaucoma Detection using Novel Optic Disc Localization, Hybrid Feature Set and Classification Techniques”, Australasian Physical and Engineering Sciences in Medicine, OCT 2015. [impact factor: 0.888]

15.  Amna Waheed, M. Usman Akram, Shehzad Khalid, Zahra Waheed, Muazzam A Khan, Arslan Shaukat, “Hybrid Features and Mediods Classification based Robust Segmentation of Blood Vessels”, Journal of Medical Systems, Vol 39, No. 10, OCT 2015. [impact factor: 2.213]

16.  Sheeraz Akram, Muhammad Younus Javed, M. Usman Akram, Usman Qamar and Ali Hassan, “Pulmonary Nodules Detection and Classification Using Hybrid Features from Computerized Tomographic Images”, J. Med. Imaging Health Info. Vol. 6, No. 1, 1-8, 2016. [impact factor: 0.503]

17.  Amna Waheed, Zahra Waheed, M. Usman Akram, Arslan Shaukat, “Removal of False Blood Vessels Using Shape Based Features and Image Inpainting,” Journal of Sensors, vol. 2015, Article ID 839894, 13 pages, 2015. doi:10.1155/2015/839894. [impact factor: 1.182]

18.  Saima Shaheen, Aasia Khannum, M. Usman Akram, Shoab A.Khan, SangHyun Seo, M.Younas Javed, “Evaluating the Significance of Error Checksums for Wireless Video Streaming”, Multimedia Tools and Applications, Accepted [impact factor: 1.346]

19.  Saima Shaheen, M. Younus Javed, Muid Mufti, Shehzad Khalid, Aasia Khanum, Shoab A. Khan and M. Usman Akram, “A Novel Compression Technique for Multi-Camera Nodes through Directional Correlation”, International Journal of Distributed Sensor Networks, Article ID 539838, Feb 2015. [impact factor: 0.923]

20.  Sajid Gul Khawaja, Mian Hamza Mushtaq, Shoab A. Khan, M. Usman Akram, Habib ullah Jamal, ” Designing Area Optimized Application-Specific Network-On-Chip Architectures while Providing Hard QoS Guarantees”, Plos One, April 21, 2015, DOI: 10.1371/journal.pone.0125230 [impact factor: 3.534]

21.  S. Akram, M. Y. Javed, A. Hussain, F. Riaz, M. U. Akram, “Intensity Based Statistical Features for Classification of Lungs CT Scan Nodules Using Artificial Intelligence”, Taylor and Francis Journal of Experimental and Theoretical Artificial Intelligence, Vol. 27, No. 6, 2015. [impact factor: 1.0]

22.  Shehzad Khalid, M. Usman Akram, Shahid Razzaq, “Behaviour recognition using multivariate m-Mediods based modelling of motion trajectories”,  Multimedia Systems, 2014 (accepted). [impact factor: 0.619]

23.  Wasi Haider Butt,  M. Usman Akram, Shoab A Khan, M. Yonus Javed,  “Covert Network Analysis for Key Player Detection and Event Prediction Using a Hybrid Classifier,” The Scientific World Journal, vol. 2014, Article ID 615431, 13 pages, 2014. doi:10.1155/2014/615431. [impact factor: 1.730]

24.  M. Usman Akram, Anam Tariq, Shoab A Khan, M. Younus Javed, “Automated Detection of Exudates and Macula for Grading of Diabetic Macular Edema”, Computer Methods and Programs in Biomedicines, Volume 114, Issue 2,  pp. 141–152,  April 2014. [impact factor: 1.555]

25.  M. Usman Akram, Shehzad Khalid, Anam Tariq, Shoab A Khan, Farooque Azam, “Detection and Classification of Retinal Lesions for Grading of Diabetic Retinopathy”, Computers in Biology and Medicines, Volume 45, Issue 1, pp. 161–171, ,  February 2014. [impact factor: 1.162]

26.  M. Usman Akram, Shehzad Khalid, Anam Tariq, M. Younus Javed, “Detection of Neovascularization in Retinal Images using Multivariate m-Mediods based Classifier”, Computerized Medical Imaging and Graphics, Vol 37, pp. 346-357, 2013 [impact factor: 1.664]

27.  Anam Tariq, M. Usman Akram, Arslan Shaukat, Shoab A Khan, Automated Detection and Grading of Diabetic Maculopathy in Digital Retinal Images Springer Journal of Digital Imaging, Vol. 26, No. 4, pp. 803-812, 2013. [Impact factor: 1.255]

28.  M. Usman Akram, Shehzad Khalid, Shoab A Khan, “Identification and Classification of Microaneurysms for Early Detection of Diabetic Retinopathy”, Pattern Recognition (Elsevier), Vol 46, No.1, 107-116, 2013 [Impact Factor: 2.63]

29.  M. Usman Akram and Shoab A. Khan, “Multilayered Thresholding Based Blood Vessel Segmentation for Screening of Diabetic Retinopathy”, Springer journal of Engineering with Computers (EWCO), Vol. 29, No. 2, pp. 165-173, 2013.  [Impact factor:0.739]

30.  M. Usman Akram, Anam Tariq, M. Almas Anjum, M. Younus Javed, “Automated Detection of Exudates in Colored Retinal Images for Diagnosis of Diabetic Retinopathy”, OSA Journal of Applied Optics, Vol. 51 No. 20, 4858-4866, 2012. [Impact factor: 1.748]

31.  M. Usman Akram and Shoab A. Khan, “Automated detection of dark and bright lesions in retinal images for early detection of diabetic retinopathy”, Springer Journal of Medical Systems (JOMS), Vol. 36, No. 5, 3151-3162, 2012. [Impact factor:1.783]

Non ISI Indexed Journals:

32.  Faraz Tahir, M. Usman Akram, Mujahid Abbas, Albab Ahmad Khan, Detection of Laser Marks from Retinal Images for Improved Diagnosis of Diabetic Retinopathy, International Journal of Computer Information Systems and Industrial Management Application, Vol 7, pp. 131 – 138, 2015

33.  Daniyal Usmani, M. Usman Akram, Sarmad Abbas, Tanveer Ahmed and Imran Basit, “Generation of Retinal Image Mosaic using Weber Local Descriptor”, Journal of Information Assurance and Security , pp. 111 – 119, Vol 10, No. 3, 2015

34.  Israr Ul Haq, Usman Akram, Yoshifumi Saijoz, “Detection of Abnormal Blood Vessels on Optic Disc for Diagnosis of Proliferative Diabetic Retinopathy”, Journal of the Institute of Industrial Applications Engineers Vol.3, No.1, pp.1–5, 2015

35.  Israr ul haq, Usman Akram, Yoshifumi Saijo, “Automated detection of optic disc using vessels tracking”, Transactions of Japanese Society for Medical and Biological Engineering, Vol. 52, pp 283-284 (2014)

36.  Safia Shabbir, Anam Tariq and M. Usman Akram, “A Comparison and Evaluation of Computerized Methods for Blood Vessel Enhancement and Segmentation in Retinal Images”, International Journal of Future Computer and Communication, Vol. 2, No. 6, 600-603, 2013.

37.  Kiran Yaseen, Anam Tariq and M. Usman Akram, “A Comparison and Evaluation of Computerized Methods for OD Localization and Detection in Retinal Images”, International Journal of Future Computer and Communication, Vol. 2, No. 6, 613-616, 2013.

38.  Ibaa Jamal, M Usman Akram, Retinal Image Preprocessing:
Background and Noise Segmentation , TELKOMNIKA Indonesian Journal on Electrical Engineering, Vol. 10, No. 3, pp. 537-544, 2012

39.  M. Usman Akram, Ibaa Jamal, Anam Tariq, “Blood Vessel Enhancement and Segmentation for Screening of Diabetic Retinopathy”, TELKOMNIKA Indonesian Journal on Electrical Engineering, Vol. 10, No. 2, pp. 327-334, 2012

40.  Anam Tariq, M, Usman Akram, Personal Identification using Ear Recognition, TELKOMNIKA Indonesian Journal on Electrical Engineering, Vol. 10, No. 2, pp. 321-326, 2012

41.  M. Usman Akram, Assia Khanum, Khalid Iqbal, “An automated System for Liver CT Enhancement and Segmentation”, ICGST-GVIP Journal, Vol. 10, No. 4, pp. 17-22, October 2010 [ISSN # 1687-4005]

42.  M. Usman Akram, Anam Tariq, Sarwat Nasir, Shoab A. Khan, “Fingerprint Image: Pre and Post-Processing”, International Journal of Biometrics, Inderscience, Vol.1, No.1, pp. 63-80, May2008  [ISSN # 1755-8301]

Conference Proceedings:

43.  Zahra Waheed, M. Usman Akram, Amna Waheed, Arslan Shaukat, Robust Extraction of Blood Vessels for Retinal Recognition, International Conference on Information Security and Cyber Forensics (InfoSec2015), South Africa, Nov 2015.

44.  Najam Dar, M. Usman Akram, Anam Usman, Shoab A Khan, ECG Biometric Identification for General Population Using Multiresolution Analysis of DWT Based Features, International Conference on Information Security and Cyber Forensics (InfoSec2015), South Africa, Nov 2015.

45.  Asra Ashraf, M. Usman Akram, Shehzad Amin Sheikh, Detection of Retinal Whitening, Cotton Wool Spots and Retinal Hemorrhages for Diagnosis of Malarial Retinopathy, IEEE TENCON 2015, Macau, Nov 2015.

46.  Taimur Hassan, M. Usman Akram, Shafaat A Bazaz, “Review of OCT and Fundus Images for Detection of Macular Edema, 12th annual International Conference on Imaging Systems and Techniques, China, Sept, 2015

47.  Amna Waheed, Zahra Waheed, M. Usman Akram, A Robust Algorithm For Segmentation of Blood Vessels in the Presence of Lesions in Retinal Fundus Images, 12th annual International Conference on Imaging Systems and Techniques, China, Sept, 2015

48.  Asra Ashraf, M. Usman Akram, Shehzad Amin Sheikh, Sarmad Abbas, Detection of Macular Whitening and Retinal Hemorrhages for Diagnosis of Malarial Retinopathy, 12th annual International Conference on Imaging Systems and Techniques, China, Sept, 2015

49.  Anum Abdus Salam, M. Usman Akram, Kamran Wazir, S. M. Anwar, A Review Analysis on Early Glaucoma Detection Using Structural Features, 12th annual International Conference on Imaging Systems and Techniques, China, Sept, 2015

50.  Khush Naseeb Fatima, M. Usman Akram, Shafaat A Bazaz, Papilledema Detection in Fundus Images Using Hybrid Feature Set, 5th International Conference on IT Convergence and Security August 24th-27th, 2015, Kuala Lumpur, Malaysia

51.  Najam Dar, M. Usman Akram, Muazzam A Khan, Arslan Shaukat, ECG Based Biometric Identification For Population With Normal And Cardiac Anomalies Using Hybrid HRV And DWT Features, 5th International Conference on IT Convergence and Security August 24th-27th, 2015, Kuala Lumpur, Malaysia

52.  Shanza Abbas, M. Usman Akram, Arslan Shaukat, Muazzam A Khan, Analyzing Yelp Reviews of Restaurants for Categorizing Health Related Cues to Action, 2015 International Conference on Advanced Informatics: Concepts, Theory and Applications, Thailand, Aug 2015.

53.  Anum Abdus Salam, M. Usman Akram, S. M. Anwar, Autonomous Glaucoma Detection from Fundus Image using Cup to Disc Ratio and Hybrid Features, 2015 International Conference on Advanced Informatics: Concepts, Theory and Applications, Thailand, Aug 2015.

54.  Sadaf Ayaz, Sadaf Saher, M. Usman Akram, Imran Basit, “A Case Study Approach: Iterative Prototyping Model Based Detection of Macular Edema in Retinal OCT Images”, International Conference on Software
Engineering and Knowledge Engineering (SEKE 2015), USA

55.   M. Usman Akram, Daniyal Usmani, Tanveer Ahmad, Sarmad Abbas, Syeda Fouzia Noor, “Seamless fundus image stitching using WLD to improve field of view”, IEEE 5th International Conference on Digital Information and Communication Technology and Its Applications (DICTAP 2015), Lebanon, Apr 2015

56.  Faisal, M. Usman Akram, Faraz, Adnan, “Human identification using dental biometric analysis”, IEEE 5th International Conference on Digital Information and Communication Technology and Its Applications (DICTAP 2015), Lebanon, Apr 2015

57.  Mavera Mazhar Butt, M. Usman Akram, Shoab A Khan, “Denoising practices for electrocardiographic (ECG) signals: A survey,” in Computer, Communications, and Control Technology (I4CT), 2015 International Conference on , pp.264-268,  April 2015

58.  Saima Shaheen, Aasia Khannum, Shoab A Khan, M. Usman Akram, M. Younus Javed, “Using MAC frame header for efficient multimedia streaming over IEEE 802.11 wireless LAN,” in Computer, Communications, and Control Technology (I4CT), 2015 International Conference on,  pp.570-574, April 2015

59.  Uzma Abbasi, Muhammed Usman Akram, “Classification of Blood Vessels as Arteries and Veins for Diagnosis of Hypertensive Retinopathy”, 10th IEEE International Computer Engineering Conference, Egypt, December 2014.

60.  Aniqa Azam, M. Usman Akram and Usman Qammar, “Optic Disc Segmentation from Colored Retinal Images using Vessel Density”, 12th International Conference on Frontiers of Information Technology (FIT) , pp. 313-318, Pakistan, Dec 2014.

61.  Adeel Muzaffar Syed, Muhammad Usman Akbar, M. Usman Akram and Joddat Fatima, ”Automated Laser Mark Segmentation from Colored Retinal Images”, EEE 17th International Multi Topic Conference (INMIC 2014), Pakistan, Dec 2014.

62.  Saima Waseem, Usman Akram, Bilal Ashfaq, “Drusen Detection From Colored Fundus Images for Diagnosis of Age Related Macular Degeneration“, 7th International Conference on Information and Automation for Sustainability, Sri Lanka, Dec 2014.

63.  Saima Waseem, Usman Akram, Bilal Ashfaq, “Drusen Exudate Lesion Discrimination in Colour Fundus Images”, 14th International Conference on Hybrid Intelligent        Systems (HIS      2014), pp. 176-180, Kuwait, Dec 2014

64.  Daniyal Usmani, Tanveer Ahmed, M. Usman Akram, Danyal Saeed, “Fundus Image Mosaic Generation for Large Field of View”, 14th International Conference on Hybrid Intelligent   Systems (HIS      2014), pp. 30-34, Kuwait, Dec 2014

65.  Faraz Tahir,Usman Akram, Mujahid Abbass, Albab Ahmad khan, “Laser Marks Detection from Fundus Images”, 14th International Conference on Hybrid Intelligent  Systems (HIS                2014), pp. 147-151, Kuwait, Dec 2014

66.  Samra Irshad, M. Usman Akram, “Automated detection of cotton wool spots for the diagnosis of hypertensive retinopathy”, 7th Cairo International Biomedical Engineering Conference, Egypt, December 2014.

67.  Muniba Saleem, M. Usman Akram, “Detection of haemorrhages for diagnosis of malarial retinopathy”, 7th Cairo International Biomedical Engineering Conference, Egypt, December 2014.

68.  Samra Irshad, M. Usman Akram, Salman Ahmed, “System for automatic differentiation of retinal vessels into arteries and veins”, 7th Cairo International Biomedical Engineering Conference, Egypt, December 2014.

69.  Israr ul haq, Usman Akram, Yoshifumi Saijo, “Automated Detection of New Vessels for Classification of Proliferative Diabetic Retinopathy”, Proceedings of the 2nd International Conference on Intelligent Systems and Image Processing, pp.304-308,  2014

70.  A. F. Gill, S. A. Fatima, A. Nawaz, A. Nasir, M. U. Akram, S. G. Khawaja, S. Ejaz, “Time Domain Analysis of EEG Signals for Detection of Epileptic Seizure”, 2014 IEEE Symposium on Industrial Electronics & Applications (ISIEA2014), Malaysia, Sept 2014.

71.  Sabeen Basit, Shoab A Khan, M. Usman Akram, “Segmentation of Coronary Arteries”, 2014 IEEE Symposium on Industrial Electronics & Applications (ISIEA2014), Malaysia, Sept 2014.

72.  M. Usman Akram, Hassan Moatasam Awan, Abdullah Amaan Khan, “Dorsal Hand Veins Based Person Identification”, 4th International Conference on Image Processing Theory, tools and applications, France, Oct 2014.

73.  Sarmad Khitran, M. Usman Akram, Anam Usman, Ubaidullah Yasin, “Automated System for the Detection of Hypertensive Retinopathy”, 4th International Conference on Image Processing Theory, tools and applications, France, Oct 2014.

74.  Hassan Wahab, Syed Rizwan Haider, Sarmad Khitran, Noor ul Huda, M. Usman Akram, “Bright Region and Vessel Density based Robust Optic Disc Segmentation”, 4th International Conference on Image Processing Theory, tools and applications, France, Oct 2014.

75.  S. Rashid, M. Usman Akram, S. Khan, “Wireless Sensor Network for Distributed Event Detection based on Machine learning”, 2014 IEEE International Conference on Green Computing and Communications (GreenCom 2014),  Taiwan, 2014.

76.  Y. Zaidi, M. Usman Akram, Anam Tariq, “Retinal Image Analysis for Diagnosis of Macular Edema using Digital Fundus Images”, 2013 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT), Jorden, Dec 2013.

77.  Ghazanfer Raza, Majid Rafique, Anam Tariq, M. Usman Akram, “Hybrid Classifier Based Drusen Detection in Colored Fundus Images”, 2013 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT), Jorden, Dec 2013.

78.  Khawar Ali, Shoab A Khan, M. Usman Akram, “Aircraft Tracking Based on KLT Feature Tracker and Image Modeling”, 2013 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies (AEECT), Jorden, Dec 2013.

79.  M. Usman Akram, Sundus Mujtaba and Anam Tariq, “Automated Drusen Segmentation in Fundus Images for Diagnosing Age Related Macular Degeneration”, 10th IEEE International Conference on Electronics, Computer and Computation, pp. 21-24, Turkey, Nov, 2013.

80.  M. Usman Akram, Anam Tariq, Shoab Khan and Shafaat Bazaz, “Microaneurysm Detection for Early Diagnosis of Diabetic Retinopathy”, 10th IEEE International Conference on Electronics, Computer and Computation, pp.25-28, Turkey, Nov, 2013.

81.  Joddat Fatima, Adeel M Syed, M. Usman Akram, “Feature Point Validation for Improved Retina Recognition”, 2013 IEEE Workshop on Biometrics Measurements and Systems for Security and Medical Applications, pp. 13-16, Italy, Sept 2013.

82.  Joddat Fatima, Adeel M Syed, M. Usman Akram, “A Secure Personal Identification System Based on Human Retina”, 2013 IEEE Symposium on Industrial Electronics and Applications (ISIEA 2013), pp. 90-95, Malaysia, Sept 2013.

83.  M. Usman Akram, Anam Tariq, Zabeel Bashir, Shoab A Khan, “Gaussian Mixture Model Based Handwritten Numeral Character Recognition”, 2013 IEEE Symposium on Industrial Electronics and Applications (ISIEA 2013), pp. 81-85, Malaysia, Sept 2013.

84.  M. Usman Akram, Zabeel Bashir, Anam Tariq, Shoab A Khan “Geometric Feature Points Based Optical Character Recognition”, 2013 IEEE Symposium on Industrial Electronics and Applications (ISIEA 2013), pp. 86-89, Malaysia, Sept 2013.

85.  Anam Tariq, M. Usman Akram, and M. Younus Javed, “Lung Nodule Detection in CT Images using Neuro Fuzzy Classifier”, IEEE Symposium Series on Computational Intelligence (SSCI), pp. 49-53, Singapore, 2013.

86.  Anam Tariq, M. Usman Akram, and M. Younus Javed, “Computer Aided Diagnostic System for Grading of Diabetic Retinopathy”, IEEE Symposium Series on Computational Intelligence (SSCI), pp. 30-35, Singapore, 2013.

87.  Anam Tariq, M. Usman Akram, Arslan Shaukat, Shoab A Khan, “A Computer Aided System for Grading of Maculopathy”, 6th Cairo International Conference on Biomedical Engineering, pp. 31-34, Egypt, 2012.

88.  Umer Aftab, M. Usman Akram, “Automated Identification of Exudates for Detection of Macular Edema”, 6th Cairo International Conference on Biomedical Engineering, pp. 27-30, Egypt, 2012.

89.  Sana Qamber, Zahra Waheed, M. Usman Akram, “Personal Identification System Based on Vascular Pattern of Human Retina”, 6th Cairo International Conference on Biomedical Engineering, pp.64-67, Egypt, 2012.

90.  M. Usman Akram, Ibaa jamal, Anam Tariq and Junaid Imtiaz, “Automated Segmentation of Blood Vessels for Detection of Proliferative Diabetic Retinopathy”, IEEE-EMBS International Conference on Biomedical and Health Informatics, pp. 232-235, Hong Kong, Jan 2012.

91.  Anam Tariq, M. A. Anjum, M. Usman Akram, “Personal Identification using Computerized Human Ear Recognition System”, IEEE International Conference on Computer Science and Network Technology (ICCSNT 2011), pp. 50-54, Dec 2011, China.

92.  M. Usman Akram, Anam Tariq and Shoab A Khan, “Retinal Recognition: Personal Identification using Blood Vessels”, 6th International Conference on Internet Technology and Secured Transactions (ICITST 2011), pp. 180-184, 11-14 Dec, UAE

93.  Anam Tariq, M. Usman Akram and Shoab A Khan, “An Automated System for Fingerprint Classification using Singular Points for Biometric Security”, 6th International Conference on Internet Technology and Secured Transactions (ICITST 2011), pp. 170-175, 11-14 Dec, UAE

94.  M. Usman Akram and Anam Usman, “Computer Aided System for Brain Tumor Detection and Segmentation”, IEEE International Conference on Computer Networks and Information Technology (ICCNIT), pp. 299-302, July 2011, Abbottabad, Pakistan

95.  M. Usman Akram, Anuam Ayaz and Junaid Imtiaz, “Morphological and Gradient Based Fingerprint Image Segmentation”, IEEE ICICT, July 2011, Karachi, Pakistan

96.  Maryam Mubbashar, Anam Usman and M. Usman Akram, “Automated System for Macula Detection in Digital Retinal Images”, IEEE ICICT, July 2011, Karachi, Pakistan

97.  M. Usman Akram and Assia Khanum, “Retinal Images: Blood Vessel Segmentation by Threshold Probing”, IEEE Symposium on Industrial Electronics and Applications (ISIEA 2010), pp.475-479, 3rd – 6th October 2010, Penang, Malaysia.

98.  Anam Tariq, M. Usman Akram, “An Automated System for Colored Retinal Image Background and Noise Segmentation”, IEEE Symposium on Industrial Electronics and Applications (ISIEA 2010), pp. 405-409, 3rd – 6th October 2010, Penang, Malaysia.

99.  M. Usman Akram and Anam Tariq, “Automated Optic Disk Localization and Detection in Colored Retinal Images”, ACM FIT, Pakistan, Dec 2009.

100.          M. Usman Akram, Sarwat Nasir, Shoab A. Khan, “Comparison of Matched Filter and Wavelet Based Blood Vessel Enhancement”, 11th IASTED Conference on Signal and Image Processing (SIP), pp. 260-264, USA, 17-19 August, 2009.

101.          M. Usman Akram, Anam Tariq, Shoab A. Khan, “Retinal Images Blood Vessel Segmentation”, 3rd IEEE International conference on Information and Communication Technologies, pp. 181-186, Pakistan, 15-16 August, 2009.

102.          M. Usman Akram, Anam Tariq, “Cooperative Friendship Networks through SLAC and Newscast”, 3rd IEEE International conference on Information and Communication Technologies, pp. 31-34, Pakistan, 15-16 August, 2009.

103.          M. Usman Akram, Ali Atzaz, M. Younus Javed, Umair Ali khan Niazi, “Preprocessing and Blood Vessel Segmentation of Retinal Images”, IASTED conference on Visualization, Imaging and Image Processing (VIIP), pp. 13-18, UK, 13-15 July 2009.

104.          M. Usman Akram, Anam Tariq, Sarwat Nasir, Shoab A. Khan, “Gabor Wavelet Based Vessel Segmentation in Retinal Images”, IEEE CIIP, Tennessee, pp. 116-119, USA, 29, April, 09.

105.          M. Usman Akram, Sarwat Nasir, M. Almas Anjum, M Younus Javed, “Background and Noise Extraction from Colored Retinal Images”, IEEE CSIE, IEEE Computer Society, LosAngeles, pp. 573-577, USA, April, 09.

106.          M. Usman Akram, Ali Atzaz, Syed Farrukh Aneeque, Shoab A. Khan, “Blood Vessel Enhancement and Segmentation Using Wavelet Transform”, IEEE ICDIP, pp. 30-34, Thailand, March 2009.

107.          M. Usman Akram, Anam Tariq, Sarwat Nasir, “Retinal Image: noise Segmentation”, IEEE INMIC, pp. 116-119, Pakistan, Dec08.

108.          Sarwat Nasir, Imtiaz khokhar, M. Usman Akram, “Optimum Filter Overlapping Scheme For Deriving Speaker Dependent Mel Frequency Cepstral Coefficients”, 10th IASTED Conference on Signal and Image Processing (SIP), USA, August08.

109.          M. Usman Akram, Sarwat Nasir, Anam Tariq, Irfan Zafar, “Improved Fingerprint Image Segmentation using New Modified Gradient Based Technique”, 21st IEEE Canadian conference on Electrical and Computer Engineering, pp. 1967-1971, Canada, May08.

110.          Aasia Khanum, M. Usman Akram, “Fuzzy Based Facial Expression Recognition”, IEEE Congress on Image and Signal Processing(CISP 2008), IEEE Computer Society,  pp. 598-602, China, May 2008.

111.          M. Usman Akram, Anam Tariq, Sarwat Nasir, Aasia Khanum, “Core Point Detection Using Improved Segmentation and orientation”, The 6th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA08), pp.637-644, Qatar, April 2008.

112.          M. Usman Akram, Anam Tariq, Shahida Jabeen, Shoab A. Khan, “Fingerprint Image Segmentation Based on Boundary Values”, 3rd International Conference on Computer Vision Theory and Applications (VISAPP08), Vol.1, pp. 134-138, Portugal,  Jan 2008.

113.          M. Usman Akram, Sarwat Nasir, Rabia Anwer, Rabia Arshad, Shoab A. Khan, “Core Point Detection Using Fine Orientation Field Estimation”, 3rd International Conference on Computer Vision Theory and Applications (VISAPP08), Portugal,  Vol.1, pp. 351-356, Jan 2008.

114.          M. Usman Akram, Irfan Zafar, Wasim Siddique, Zohaib Mushtaq, “Facial Expression Recognition Based on Fuzzy Logic”, 3rd International Conference on Computer Vision Theory and Applications (VISAPP08), Vol.1, pp. 383-388, Portugal, Jan 2008.

115.          M. Usman Akram, Assia Khanam, “Optimal Core Point Detection”, 3rd all Pakistan Electrical Engineering Conference (APE2C), Pakistan, Nov. 2007 (Runner-ups Paper Award)

Dr. Imran Sidiqi

Journal Publications

  1. Naz, A. I. Umar, S. H. Shirazi, S. B. Ahmed, M. I. Razzak, and I. Siddiqi, Segmentation techniques for recognition of Arabic-like scripts: A comprehensive survey,Education and Information Technologies, 2015.
  2. R. Chugtai, S. Khalid and I. Siddiqi, Online Signature Verification: A Review, J. Appl. Environ. Biol. Sci., 4(9S), 303-308, 2014.
  3. Nazakat, S. Khalid and I. Siddiqi, A Review of Offline Signature Verification Techniques, J. Appl. Environ. Biol. Sci., 4(9S), 342-347, 2014
  4. Siddiqi, C. Djeddi, A. Raza and L. Souici-Meslati, Automatic Analysis of Handwriting for Gender Classification, Pattern Analysis and Applications, 2014. {IF:0.8}.
  5. Jehanzeb, G.B. Sulong and I. Siddiqi, Improving Codebook based Writer Recognition, Int’l Journal of Pattern Recognition and Artificial Intelligence, World Scientific, 27 (06), 2013. {IF: 0.56}.
  6. Djeddi, I. Siddiqi, L. Souici-Meslati, A. Ennaji,Text-Independent Writer Recognition Using Multi-script Handwritten Texts, Pattern Recognition Letters, Elsevier, 2013. {IF : 1.7}
  7. Cloppet, H. Daher, V. Eglin, H. Emptoz, M. Exbrayat, G. Joutel, F. Lebourgeois, L. Martin, I. Moalla, I. Siddiqi, N. Vincent, New Tools for Exploring, Analyzing and Categorizing Medieval Scripts. In Digital Medievalist, ISSN: 1715-0736 (7): 243-254, 2011
  8. Siddiqi, F. Cloppet, N.Vincent, Writing property descriptors, a proposal for typological groupings. In Gazette du livre médiéval (56-57): 42-57, 2011.
  9. Siddiqi and N. Vincent, Text independent writer recognition using redundant writing patterns with contour-based orientation and curvature features, Pattern Recognition {43} Issue 11, 3853-3865, 2010. {IF:3.17}

 

Conference Proceedings

2015

  1. Gattal, Y. Chibani, B. Hadjadji, N. Bouadjenek, I. Siddiqi, C. Djeddi, Segmentation-Verification Based on Fuzzy Integral for Connected Handwritten Digit Recognition, In Proc. of the 5th Int’l Conference on Image Processing Theory, Tools and Applications, France, 2015.(To Appear)
  2. Khattak, Z. Malik, I. Siddiqi and S. Khalid, Line and Ligature Segmentation in Printed Urdu Document Images, In Proc. of the 3rd Int’l Conference on Computational and Social Sciences, ICCSS, Malaysia, 2015. (To Appear)
  3. Djeddi, S. Al-Maadeed, A. Gattal, I.Siddiqi, L. Souici-Meslati and H. El Abed, ICDAR2015 Competition on Multi-script Writer Identification and Gender Classification using ‘QUWI’ Database, Proc. of the 13th Int’l Conference on Document Analysis and Recognition, ICDAR, France, 2015.
  4. Moetesum, I. Siddiqi, U. Masroor and C. Djeddi, Automated Scoring of Bender Gestalt Test Using Image Analysis Techniques, Proc. of the 13th Int’l Conference on Document Analysis and Recognition, ICDAR, France, 2015.
  5. Khattak, I. Siddiqi, S. Khalid and C. Djeddi, Recognition of Urdu Ligatures – A Holistic Approach, Proc. of the 13th Int’l Conference on Document Analysis and Recognition, ICDAR, France, 2015.
  6. Hannad, I. Siddiqi and M. E. Y. El Kettani, Arabic Writer Identification Using Local Binary Patterns (LBP) of Handwritten Fragments, 7th Iberian Conference on Pattern Recognition and Image Analysis, Spain, 2015.
  7. Naqvi, S. Khalid and I. Siddiqi, Framework for Human Identification Through Offline Handwritten Documents, Proceedings of the 2nd International Conference on Computer, Communication, and Control Technology , Malaysia, 2015.

 

2014

  1. Naz, A. Umar, S. Ahmed, S. H. Shirazi, M. I. Razzak and I. Siddiqi, An OCR System For Printed Nasta’liq Script: A Segmentation Based Approach, Proc. of the 17th IEEE Multi-topic Conference, Pakistan, 2014.
  2. Malik and I. Siddiqi, Detection and Recognition of Traffic Signs from Road Scene Images, Proceedings of the 12th International Conference on Frontiers in Information Technology, 2014.
  3. Gattal, Y. Chibani, C. Djeddi and I. Siddiqi, Improving Isolated Digit Recognition using a Combination of Multiple Features, Proc. Of 14th Int’l Conference on Frontiers in Handwriting Recognition, ICFHR, Greece, 2014.
  4. Djeddi, A. Gattal, L. Souici-Meslati, I. Siddiqi, Y. Chibani and H. El-Abed, LAMIS-MSHD: A Multi-Script offline Handwriting Database, Proc. Of 14th Int’l Conference on Frontiers in Handwriting Recognition, ICFHR, Greece, 2014.
  5. Djeddi, L. S. Meslati, I. Siddiqi, A. Ennaji, H. El-Abed and A. Gattal, Evaluation of Texture Features for Offline Arabic Writer Identification, Proc. Of 11th IAPR Int’l Workshop on Document Analysis Systems (DAS), Tours, France, 2014.

 

2013

  1. Raza, I. Siddiqi, C. Djeddi and A. Ennaji, Multilingual Artificial Text Detection using a Cascade of Transforms, In Proc. Of the 12th Int’l Conference on Document Analysis and Recognition, ICDAR 2013, Washington, USA, 2013.
  2. Djeddi, I. Siddiqi, L. Souici-Meslati and A. Ennaji, Codebook for Writer Characterization: A Vocabulary of Patterns or a Mere Representation Space?, In Proc. Of the 12th Int’l Conference on Document Analysis and Recognition, ICDAR 2013, Washington, USA, 2013.
  3. Raza, A. Abidi and I. Siddiqi, Multilingual artificial text detection and extraction from still images,  Proc. SPIE 8658, Document Recognition and Retrieval XX, February 2013, California, USA.

 

2012

 

  1. Djeddi, C., Siddiqi,I., Souici-Meslati, L. and Ennaji, A., Multi-script Writer Identification Optimized With Retrieval Mechanism, In Proceedings of the 13th International Conference on Frontiers in Handwriting Recognition, 18-20 September 2012 at Bari, Italy.
  2. Abidi, A., Jamil, A., Siddiqi, I. and Khurshid, K., Word Spotting based Retrieval of Urdu Handwritten Documents, In Proceedings of the 13th International Conference on Frontiers in Handwriting Recognition, September 2012 at Bari, Italy.
  3. Raza, A., Siddiqi, I., Abidi, A. and Arif, F., An Unconstrained Benchmark Urdu Handwritten Sentence Database with Automatic Line Segmentation, In Proceedings of the 13th International Conference on Frontiers in Handwriting Recognition, September 2012 at Bari, Italy.
  4. Siddiqi, I. and Raza, A., A Database of Artificial Urdu Text in Video Images with Semi-Automatic Text Line Labeling Scheme, In Proceedings of MMEDIA 2012, Chamonix, France.

 

2011

 

  1. Abidi, A., Siddiqi, I. and Khurshid, K., Towards Searchable Urdu Digital Libraries – A Word Spotting based Retrieval Approach, In ICDAR ’11: Eleventh International Conference on Document Analysis and Recognition, September 2011, Beijing, China.
  2. Jamil, A., Raza, A., Siddiqi, I. and Arif, F., Edge-based Features for Localization of Artificial Urdu Text in Video Images, In ICDAR ’11: Eleventh International Conference on Document Analysis and Recognition, September 2011, Beijing, China.
  3. Siddiqi, I., Khurshid, K. and Vincent, N.: Feature Relevance Analysis for Writer Identification, In DRR’11: Proceedings of the 18th Document Recognition and Retrieval Conference, 26–27 January 2011, San Francisco, CA, USA.

 

2010

 

  1. Khurshid, K., Siddiqi, I., Faure, C. and Vincent, N.: Information Retrieval from Historical Document Image Base, In KDIR’10: Proceedings of the Int’l Conference on Knowledge Discovery and Information Retrieval, 25–28 October 2010, Valencia, Spain.

 

2009

 

  1. Siddiqi, I., Cloppet, F. and Vincent, N.: Contour Based Features for the Classification of Ancient Manuscripts, In IGS’09: Proceedings of the 14th Conference of the International Graphonomics Society, 13th–16th September 2009, Dijon, France.
  2. Siddiqi, I. and Vincent, N.: Combining Contour Based Orientation and Curvature Features for Writer Recognition, In CAIP’09: Proceedings of the 13th International Conference on Computer Analysis of Images and Patterns, 2nd–4th September 2009, Münster, Germany.
  3. Siddiqi, I. and Vincent, N.: A Set of Chain Code Based Features for Writer Recognition. In ICDAR ’09: Proceedings of the Tenth International Conference on Document Analysis and Recognition, 26th–29th July 2009, Barcelona, Spain.
  4. Khurshid, K., Siddiqi, I., Faure, C. and Vincent, N.: Comparison of Niblack Inspired Binarization Methods for Ancient Documents, In DRR’09: Proceedings of the 16th Document Recognition and Retrieval Conference, 21st–22nd January 2009, San Jose, CA, USA.

 

2008

 

  1. Siddiqi, I. and Vincent, N.: Descripteurs Locaux de Forme pour la Reconnaissance de Scripteur, In CIFED’08: Xe Colloque International Francophone sur l’Ecrit et le Document, 28th–31st October 2008, Rouen, France.
  2. Siddiqi, I. and Vincent, N.: Stroke Width Independent Feature for Writer Identification and Handwriting Classification. In ICFHR ’08: Proceedings of the Eleventh International Conference on Frontiers in Handwriting Recognition, 19th– 21st August 2008, Montreal, Canada.
  3. Siddiqi, I. and Vincent, N.: Combining Global and Local Features for Writer Identification. In ICFHR ’08: Proceedings of the Eleventh International Conference on Frontiers in Handwriting Recognition, 19th–21st August 2008, Montreal, Canada.
  4. Siddiqi, I. and Vincent, N.: How to Define Local Shape Descriptors for Writer Identification and Verification. In PRIS’08: 8th Int’l workshop on Pattern Recognition in Information Systems, 12th–13th June 2008, Barcelona, Spain.

 

2007 & Prior

  1. Siddiqi, I. and Vincent, N.: In ICDAR ’07: Proceedings of the Ninth International Conference on Document Analysis and Recognition, 23rd–26th September 2007, Curitiba, Brazil.
  2. Qazi, A.A., Siddiqi, I. and Hussain, S.: Text Detection and Recognition for Video Indexing, In ICSES ’04: Proceedings of 26th IEEE International Conference on Signals and Electronic Systems, 13th–15th September, 2004, Poland.

 

National Events

 

  1. Legendre, V. Hasselmann, M., Vincent, N., Siddiqi, I., Kummerlen, C., Rahmani, H., Barbar, S.D.,  Guiot, P., Kopff-Uberall, M., Schultz, S., Sauder, P.: Peut-on mesurer les déterminants de la confiance accordée aux soignants par les proches de patients hospitalisés en Réanimation? 37ème Congrès de la Société de Réanimation de Langue Française, 14th–16th January 2009, Paris, France.
  2. Siddiqi, I. and Vincent, N.: Scriptor Identification, Document Image Analysis Workshop, 12th – 13th July, 2007, La Rochelle, France.

 

 

 

Dr. Khurram Shehzad

Articles published by refereed journals.

Journal Papers

  1. Shahzad, K.; Peng Cheng; Oelmann, B., “Architecture Exploration for a High-Performance and Low-Power Wireless Vibration Analyzer,” Sensors Journal, IEEE, vol.13, no.2, pp.670,682, Feb. 2013
  2. Imran, M.; Shahzad, K.; Ahmad, N.; O’Nils, M.; Lawal, N.; Oelmann, B., “Energy Efficient FPGA based Wireless Vision Sensor Node: SENTIOF-CAM,” IEEE Transactions on Circuits and Systems for Video Technology, vol. PP, no. 99, June 2014
  3. Abdul W. Malik, Qaiser Anwer, Tor Arne Johannson, Benny Thornberg, Khurram Shahzad “Real Time Decoding of Color Symbol for Optical Positioning System”, International Journal of Advanced Robotic Systems, 12:5, Jan 2015.

Papers published in refereed conference proceedings.

  1. Shahzad, K.; Peng Cheng; Oelmann, B., “SENTIOF: An FPGA based High-performance and Low-power Wireless Embedded Platform,” Computer Science and Information Systems (FedCSIS), Krakow, Poland, 901-906, Sep. 2013
  2. Shahzad, K.; Oelmann, B., “Investigating Energy Consumption of an SRAM based FPGA for Duty Cycle Applications”, International Conference on Parallel Computing – ParCo2013, pp. 547-560, Munich, Germany, Sep. 2013
  3. Shahzad, K.; Oelmann, B., “An FPGA-Based High-Performance Wireless Vibration Analyzer,” NORRCHIP 2013, IEEE Conference on, 1-5, Vilnius, Lithuania, Nov 2013
  4. Shahzad, K.; Oelmann, B., “Quantitative Evaluation of an FPGA based Wireless Vibration Monitoring System,” The Eleventh International Symposium on Wireless Communication Systems ISWCS’14, pp. 519-524, Barcelona, Spain
  5. Shahzad, K.; Oelmann, B., “A Comparative study of in-sensor processing vs. raw data transmission using ZigBee, BLE and Wi-Fi for data intensive monitoring applications,” 8th International Conference on Sensing Technology ICST 2014, pp. 510-516 , Liverpool, UK

 

Engr. AminaJameel

 

Journal Publications:

 

1) A. Jameel, A. Ghafor, M. Riaz, “Guided Filter and IHS based pan-sharpening”, IEEE Sensors Journal, September 2015 (IF: 1.852).

2) A. Jameel, A. Ghafor, M. Riaz, “Wavelet and guided filter based multi-focus fusion for noisy Images”, Optik-International Journal for Light and Electron Optics 126.23 (2015): 3920-3923. (IF: 0.769).

3) A. Jameel, A. Ghafor, M. Riaz, “All in focus fusion using guided filter”, Multidimensional Systems and Signal Processing, November 2014 (IF: 1.578).

4) A. Jameel, A. Ghafor, M. Riaz, “Adaptive compressive fusion for visible/IR sensors”, IEEE Sensors Journal, vol. 14, no. 7, pp. 2230-2231, July 2014 (IF 1.852).

5) A. Jameel, A. Ghafor, M. Riaz, “Improved guided image fusion for magnetic resonance and computed tomography imaging,” The Scientific World Journal, vol. 2014, pp. 1-7, 2014 (IF 1.219).

6) A. Jameel, A. Ghafor, M. Riaz, “Improved multi-focus fusion for dynamic scenes”, IEEE Signal Processing Letters, Submitted (IF: 1.639).

 

 

Conference Publications:

 

1) A. Jameel, F. Noor, “Improved Multi-Focus Image Fusion”,18th International Conference on Information Fusion, pp. 1346-1352, Washington, DC – July 6-9, 2015.

2) A. Jameel, A. Ghafor, M. Riaz, “Entropy dependent compressive sensing based image fusion”, International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), pp. 764-769, Okinawa, Japan, 2013.

3) A. Jameel, I. A. Khokhar, M. N. Jafri, “A Novel Approach for Random Interleavers in IDMA System”, WSEAS conference, Crete Island, Greece, July 2007.

4) Jameel, Imtiaz Khokhar, M.N.Jafri, Ahmad Raza “Random Interleaver Design”,5th National Research Conference, May 24, 2007 ,SZABIST Islamabad.

5) Jameel, Imtiaz Ahmad Khokhar, M.N.Jafri, “Interleaver Design for IDMA using Walsh Codes”, National Conference on Information and Communication Technologies (NCICT-2007),9th June, 2007, Pakistan.

 

Engr. Arsalan Akhtar

 

Research Papers

 

  1. Akhter A.*, Tahir M.*, Ajmal A., Hashmi S.M.U., “A Review of Techniques and Approaches in Robocup @Home”. In the Proceedings of the 6th International Conference on Information and Communication Technologies, Karachi, Pakistan, December 2015 (Accepted).
  2. Hashmi, S. M. U., Ajmal A., Akhter A., Khalid, S., Manzoor, W., Ahmed, A., “Application Layer Time Synchronization Utilizing Symbol Timing Recovery in Wireless Sensor Networks”. In the Proceedings of the 17th International Conference on Computer Modeling and Simulation (UKSim), Cambridge, United Kingdom, March 2015.
  3. Ali, S. U., Akhter A. and Faraz K. “Cellular Automata based Motion Planning for Mobile Robots”. In the Proceedings of the 12th International Conference on Control, Automation, Robotics and Vision (ICARCV 2012), Guangzhou, China, Dec 2012.

 

  1. Zaman, M. A., Shafqat, S., Imran, A., Noor, I., Akhter, A., and Faraz, K. “Online Vision-Based Techniques for Robotic Soccer Environment”. In Proceedings of the 43rd International Symposium on Robotics (ISR2012), Taipei, Taiwan, Aug 2012.

 

Engr. Suleman Awan

  1. “Memory conservation protocol with secure communications in wireless sensor networks” Principal author: Suleman Awan, presented and published in INMIC 2014 Oct 2014.

 

Engr. M Kashif Naseer

 

 

Research Papers

  1. “Trust Model at Service Layer of Cloud Computing for Educational Institutes”, The Journal of Supercomputing, Springer, (Recently Accepted), (IF: 0.84).

 

  1. “Distributed Mobility Management in 6LoWPAN-based Wireless Sensor Networks”, International Journal of Distributed Sensor Networks (IJDSN), 2015, (IF: 0.92).

 

  1. “A Novel Trust Model for Selection of Cloud Service Provider”, IEEE, WSCAR 2014.

 

  1. “Prolonging the Network Lifetime in WSN through Computational Intelligence”, World Congress on Engineering & Computer Science 2011, San Francisco USA (19-21 Oct, 2011).

 

Engr. Waleed Manzoor

 

Research Papers

  1. Application Layer Time Synchronization Utilizing Symbol Timing Recovery In Wireless Sensor Networks.

 

Muhammad Usman Akbar

  1. Adeel Muzaffar Syed, Muhammad Usman Akbar, Muhammad Usman Akram and Joddat Fatima, “Automated Laser Mark Segmentation from Colored Retinal Images”, 17th IEEE INMIC 2014 Karachi

 

  1. Mazhar Iqbal Rana, Dr. Shehzad Khalid and Muhammad Usman Akbar, “News Classification Based On Their Headlines: A Review”, 17th IEEE INMIC 2014 Karachi

Self Diagnostic and Telemedicine System for Detection and Grading of Diabetic Retinopathy

An eye abnormality caused by prolonged diabetes is known as Diabetic retinopathy (DR) and eventually leads to complete vision loss. The surveys have highlighted that the most patients with DR are normally from rural areas and it is really important to provide them an easy access to regular screening. An early detection of DR is very important in order to save patients’ vision. In view of all these, a telemedicine system along with self diagnosis of DR is proposed in this project. The proposed system utilized the advancements in image processing and pattern recognition for self diagnosis of DR. The algorithms detects different lesions i.e. microaneurysms, hemorrhages, exudates and abnormal blood vessels from digital fundus image and grades it using different clinically defined DR levels. The proposed system also consists of a framework for telemedicine module to provide data from remote station to main hospital. It is a cost effective system which can assess patients faster and ophthalmologists can evaluate greater number of cases in minimum time.

Project1

 M. Usman Akram, Shehzad Khalid, Anam Tariq, Shoab A Khan, Farooque Azam, “Detection and Classification of Retinal Lesions for Grading of Diabetic Retinopathy”, Computers in Biology and Medicines, Volume 45, Issue 1, pp. 161–171, , February 2014.

Automated Detection and Grading of Diabetic Maculopathy in Digital Retinal Images

Computer Aided Diagnosis (CAD) systems are very popular now days as they assist doctors in early detection of different diseases. In medical imaging, digital images are analyzed to develop such CAD systems using state of the art image processing and pattern recognition techniques. Diabetic maculopathy is one of the retinal abnormalities in which diabetic patient suffer from severe vision loss due to affected macula. It affects the central vision of the person and causes blindness in severe cases. In this project, we propose an automated medical system for the grading of diabetic maculopathy that will assist the ophthalmologists in early detection of the disease. The proposed system extracts the macula from digital retinal image using the vascular structure and optic disc location. It creates a binary map for possible exudate regions using filter banks and formulates a detailed feature vector for all regions. The system uses a Gaussian Mixture Model (GMM) based classifier to the retinal image in different stages of maculopathy by using the macula coordinates and exudate feature set. The evaluation of proposed system is performed by using publicly available standard retinal image databases. The results of our system have been compared with other methods in the literature in terms of sensitivity, specificity, positive predictive value and accuracy. Our system gives higher values as compared to others on the same databases which make it suitable for an automated medical system for grading of diabetic maculopathy.

Anam Tariq, M. Usman Akram, Arslan Shaukat, Shoab A Khan, Automated Detection and Grading of Diabetic Maculopathy in Digital Retinal Images Springer Journal of Digital Imaging, Vol. 26, No. 4, pp. 803-812, 2013.

Structure tensor based automated detection of macular edema from OCT images

Macula is an oval shaped area near the center of human retina that covers the area of 5500 microns and at its center, there is a small pit known as fovea with the diameter of 1500 microns. Fovea contains large concentration of cones cells and is responsible for high resolution vision. Macular disorders involve diseases which damages macula resulting in blindness or vision loss. Macular Edema (ME) is one of the most common macular disease. The symptoms for this disease usually appear in final stages and causes severe damage to central vision but Optical Coherence Tomography (OCT) imaging can detect ME in early stages as it provides a cross sectional view of macular pathology. Many researchers worked on identification of macular edema from OCT images but this project proposes a fully automated method for the classification of macular edema from OCT images using an ensemble of Support Vector Machines (SVM), Naïve Bayes (NB) and K-Nearest Neighbor (KNN). The classification on based on analyzing the thickness variation highlighted by coherent tensors of candidate images. The custom dataset is used to train these classifiers for predicting ME on the set of unlabeled OCT images. Total 71 OCT images of 64 patients were used in which 15 persons had ME and 49 patients were healthy. Our proposed system correctly classified 100% of ME patients and 93.75% of healthy persons. We have also applied the proposed implementation on SD-OCT images of Duke dataset and it correctly classified all the healthy and ME images in Duke dataset.

Ayaz, S. Sahar, M. Zafar, M. U. Akram, Y. Nadeem “Analysis of OCT Images for Detection of Choroidal Neovascularization in Retinal Pigment Epithelial Layer”, 21st International Conference on Neural Information Processing, LNCS, pp. 226-233, Malaysia, Nov 2014.

Removal of False Blood Vessels using Shape based Features and Image Inpainting

Automated quantification of blood vessels in human retina is the fundamental step in designing any computer-aided diagnosis system for ophthalmic disorders. Detection and analysis of variations in blood vessels can be used to diagnose several ocular diseases like diabetic retinopathy. Diabetic Retinopathy is a progressive vascular disorder caused due to variations in blood vessels of retina. These variations bring different abnormalities like lesions, exudates and hemorrhages in human retina which make the vessel detection problematic. Therefore, automated retinal analysis is required to cater the effect of lesions while segmenting blood vessels. The proposed framework presents two improved approaches to carry out vessel segmentation in the presence of lesions. The project mainly aims to extract true vessels by reducing the effect of abnormal structures significantly. First method is a supervised approach which extracts true vessels by performing region based analysis of retinal image. While second method intends to remove lesions before extracting blood vessels by using an inpainting technique. Both methods are evaluated on STARE, DRIVE and on our own database AFIO. Experimental results demonstrate the excellence of proposed system

 Amna Waheed, Zahra Waheed, M. Usman Akram, Arslan Shaukat, “Removal of False Blood Vessels Using Shape Based Features and Image Inpainting,” Journal of Sensors, vol. 2015, Article ID 839894, 13 pages, 2015. doi:10.1155/2015/839894.

Assessment of Generalized Arteriolar Narrowing for diagnosis of Hypertensive Retinopathy using a Hybrid Classifier

Retinal image analysis is unique in a sense that it allows non-invasive and thorough examination of retina. Advancement in fundus imaging tools has led to the creation of computer-aided systems for automatic analysis of various anatomical structures. These tools are quite useful as they provide significant assistance to ophthalmologists for an early detection of retinal diseases. Hypertensive retinopathy is an eye disease occurs due to increase in systolic blood pressure. It may even lead to vision loss, if not detected and diagnosed earlier. This disease primarily affects the retinal blood vessels by attenuating the arteriolar caliber. The damage is evaluated by calculation of arteriovenous ratio, which quantifies the change in diameter of retinal blood vessels. It is basically the ratio of arterioles to venules diameter. In this project, an automated system is presented for grading of hypertensive retinopathy. The proposed system automatically calculates arteriovenous ratio in retinal fundus images by removing the background mask, segmenting retinal blood vessels, locating the position of optic disk, defining the region of analysis, differentiating vessels into arteries and veins, determining the vessel width and finally calculating arteriovenous ratio. The proposed system consists of a novel approach for retinal blood vessel differentiation and caliber measurement. A hybrid classifier is presented which combines the K-Nearest Neighbor, Gaussian Mixture Model and Support Vector Machine in an ensemble for improved vessel classification which leads to reliable grading of retinal image in different stages of hypertensive retinopathy. Evaluation of proposed system is carried out on a publically available VICAVR, INSPIRE-AVR and a local database. Performance comparison shows the system achieves higher accuracy than those reported in the past.

Sarmad Khitran, M. Usman Akram, Anam Usman, Ubaidullah Yasin, “Automated System for the Detection of Hypertensive Retinopathy”, 4th International Conference on Image Processing Theory, tools and applications, France, Oct 2014.

ECG Security System

Now-a-days security and privacy is an essential field in the Technology world. We are working on a security system based on ECG signals. A number of different kind of ECG machines are available in the market and it is also highlighted in the research that single channel ECG can be acquired by making a closed loop with a circuit placed on human wrist. In this project, we have designed an embedded device which can be placed as a wrist band and is acquiring a single channel ECG. The main principle of the project is to gather ECG signals of certain people and add it into the database. Now based on this database we have cross checked any person’s ECG who tries to access the system. The security system allows only valid/matched ECGs to access the system.
The project methodology is based on several portions which includes Integration of Sensors where We have Integrated sensors which are getting the required data from the concerned person (in the form of ECG) and then we have transferred that data through so that we could apply pre-processing to get a smooth and workable signal form and then we have Extracted the features of that signal (peaks and intervals) and then have cross checked it against the database by using some classifier and then on the bases of the result deduced by the classifier the system confirm that whether the current input sample can/cannot access the system. Our main aim is to have a system which can ensure security based on ECG signals

 Najam Dar, M. Usman Akram, Muazzam A Khan, Arslan Shaukat, ECG Based Biometric Identification For Population With Normal And Cardiac Anomalies Using Hybrid HRV And DWT Features, 5th International Conference on IT Convergence and Security August 24th-27th, 2015, Kuala Lumpur, Malaysia.

Pseudo real-time system for the Detection & analysis of Diabetes using EEG signals and implementation on Raspberry Pi

Diabetes causes the body to produce insufficient amounts of insulin (responsible for keeping the blood sugar levels in body in check) and therefore, resulting in uncontrollable sugar levels, that lead to many complications like gastrointestinal tracts, diabetic retinopathy, mental disorders in the human body. The aim of this project is to determine the effects of Diabetes on human brain and analyze brain signals (EEG) to detect different sugar levels. This in turn has an adverse effect on parts of the human brain, such as the cerebellum, hypothalamus etc. This also effects the performance of the brain, as it’s not able to perform its normal functions, the EEG’s clearly show us the brain scans of a normal person and the ones of a diabetic patient. Prolonged effect of diabetes may cause heavy brain damage and in severe cases brain death. Therefore the main working of our project is to detect and then analyze the EEG signals of normal (control) patients and those of diabetic patients. Thus we will be able to see which areas of the brain are heavily affected by the disease so the medical personnel can easily target their attentions to that are of the brain instead of searching all over. The resulting signals processed by the raspberry pi will show us the different effects on brain activity in its five different stages (alpha, beta, gamma, delta, theta) so we can determine which area is affected most during which phase of brain activity.

EYE XPLORER

Human Eye is the most complex part of the human body but it helps to reveal information about several diseases. Among these diseases are Anemia and Cataract. Anemia is a condition in which there is a deficiency of hemoglobin in the red blood cells, whereas cataract is an eye disease that causes clouding of the eye lens that causes permanent blindness if not treated in time. Anemia is diagnosed by measuring hemoglobin by drawing blood from the body and Cataract is diagnosed by first dilating the pupil and then examining the eye in the slit lamp. Both of the above methods are invasive that involve direct contact with the human body in one way or another. Computer Aided Diagnostic (CAD) systems with their mobility of usage in low resource settings can be very useful for the detection of Anemia and Cataract. We have put forward an idea in the form of mobile application named EYE XPLORER that determines the user’s risk of being anemic or having a cataract just by taking a picture from a smartphone camera. The user for the diagnosis of anemia first lowers his/ her conjunctiva and takes image and then our method first localizes the conjunctiva region from the image. Localization bins are formed to assess the hemoglobin value that further assesses the degree of anemia. For the diagnosis of Cataract, the user takes a picture of his/her eye with retina in focus. Then our proposed method localizes the iris and the pupil of the eye. Texture analysis of the obtained image is performed enabling us to tell whether the eye is normal or it has a cataract. The system is developed and tested using locally gathered dataset of anemia and cataract.


Motion Data Mining and Activity Recognition

 

Techniques for understanding video object motion activity are becoming increasingly important with the widespread adoption of CCTV surveillance systems. Motion trajectories provide rich spatiotemporal information about an object’s activity. Examples of the object trajectory include tracking results from video trackers, tracking of players and ball on playing field, sign language data measurements gathered from wired glove interfaces fitted with sensors, Global Positioning System (GPS) coordinates of satellite phones, cars using Car Navigation Systems (CNS), animal mobility experiments, satellite tracking of ships and planes etc. This project presents a novel technique for clustering and classification of object trajectory-based video motion clips using basis function approximation. Motion cues from video sequences are extracted using a tracking algorithm that can track multiple objects over the sequence of frames, while solving the problem of shadows and occlusion. In the proposed motion learning system, trajectories are treated as time series and modelled using orthogonal basis function representation. A novel framework (HSACT-SOM) is proposed that exploits the chosen feature subspace and performs efficient and effective motion learning. An extension of HSACT-SOM algorithm, namely Iterative HSACT-SOM, is also presented for learning of patterns in the presence of significant number of anomalies in training data. A novel modelling technique, referred to as m-Mediods, is proposed that models the class containing n members with m-Mediods. Once the m-Mediods based model for all the classes have been learnt, the classification of new trajectories and anomaly detection can be performed by checking the closeness of said trajectory to the models of known classes. Our proposed techniques are validated using variety of simulated and complex real life trajectory datasets.

 Shehzad Khalid, “Motion based behaviour learning, profiling and classification in the presence on anomalies”, Pattern Recognition, Vol. 43, No. 1, pp. 173-186, 2010.


Framework for m-Mediods based modeling and classification in Euclidean and general feature spaces

 There has been a growth of research attention aimed at the development of sophisticated approaches for pattern modeling and data classification. Detecting anomalous events is an important ability of any good classification system. Classification of unseen samples and anomaly detection require building models of normality. Once the models of normal classes are learnt, these can then be used for classifying new unseen trajectory data as normal (i.e. belonging to one of the modeled classes) or anomalous (not lying in the normality region of modeled classes). Most of the existing classifiers assumes a unimodal distribution within a pattern and hence can not cater for the dynamic distribution of samples within a pattern. In addition to this, majority of existing classifiers are strongly dependent on the selected feature space representation. They normally operate on vectorized/Euclidean feature space representation and cannot handle other non-Euclidean feature spaces.
This project aimed to develop a m-mediods based modeling approach, wherein the multimodal distribution of samples in each pattern is represented using multivariate m-mediods. An approach for multivariate model based classification and anomaly detection is also presented. The proposed mechanism is based on a soft classification approach which enables the proposed multivariate classifier to adapt to the multimodal distribution of samples within different patterns. We have proposed two frameworks, namely MMC-ES and MMC-GFS, to enable our proposed multivarite m-mediods based modeling and classification approach workable for any feature space with a computable distance metric. MMC-ES framework is specialized for finite dimensional features in Euclidean space whereas MMC-GFS works on any feature space with a computable distance metric. Experimental results using simulated and complex real life dataset show that multivariate m-mediods based frameworks are effective and give superior performance than competitive modeling and classification techniques especially when the patterns exhibit multivariate probability density functions. This enables our multivariate m-mediods based approach to be used for classification and anomaly detection in any feature space with a given distance function

 S.Khalid, S.Razzaq, “Frameworks for multivariate m-mediods based modeling and classification in Euclidean and general feature spaces, Pattern Recognition, Vol. 45, No. 3,  pp. 1092-1103, March 2012.


Robust Ensemble Framework Combining Heterogeneous Classifiers

Classifier ensembles are known to be very useful methods for improving the classification accuracy as well as diversity. Individual classifiers may be expert in one type of distribution whereas they may not perform that well on other distribution scenarios. Classifier ensembles handle this issue by combining multiple classifiers together to get a single stronger one whose performance is more precise and accurate as compared to its individual members. In this research project, we have presented a classification framework that combines multiple heterogeneous classifiers in the presence of class label noise. An extension of m-Mediods based modeling is presented that generates model of various classes whilst identifying and filtering noisy training data. This noise free data is further used to learn model for other classifiers such as GMM and SVM. A weight learning method is then introduced to learn weights on each class for different classifiers to construct an ensemble. For this purpose, we applied genetic algorithm to search for an optimal weight vector on which classifier ensemble is expected to give the best accuracy. The proposed approach is evaluated on variety of real life datasets. It is also compared with existing standard ensemble techniques such as Adaboost, Bagging, and Random Subspace Methods. Experimental results show the superiority of proposed ensemble method as compared to its competitors, especially in the presence of class label noise and imbalance classes.

 Shehzad Khalid, Sannia Arshad, Sohail Jabbar, Seungmin Rho, “Robust Framework to Combine Diverse Classifiers Assigning Distributed Confidence to Individual Classifiers at Class Level”, Scientific World Journal, 2014.