Electrical and Computer Engineering

Research

The main focus of my research is on developing new unsupervised and supervised machine learning techniques for segmentation and visualization of 3D images. Visualizing 3D images (e.g. MRI, CT-Scan data)  properly is still a major challenge due to the complex nature of the raw data.  My target is to combine the new techniques to extract important information from these images and use intuitive user interfaces for  easy visualization with automated color assignment, occlusion handling, segmentation etc.

I was an intern at  Microsoft Research Asia from October 2013 to January 2014. There I have worked on developing a skeleton based performance evaluation framework for Microsoft Kinect, which can be used for physical rehabilitation and sports training. This project also inrporporated the principles of visualization to provide the user an easily interpretable performance feedback. A demo will be posted on this website soon.

 My Masters thesis was on efficient Content-Based Image Retrieval (CBIR). 

Publications

Journals

  • Naimul Mefraz Khan, Riadh Ksantini, Imran Shafiq Ahmad and Ling Guan. "Covariance-guided One Class Support Vector Machine", Pattern Recognition. [In Press]
  • Naimul Mefraz Khan, Matthew Kyan and Ling Guan. "Intuitive Volume Exploration through Spherical Self-Organizing Map and Color Harmonization". Neurocomputing. [Accepted] [Invited Article]
  • Naimul Mefraz Khan, Riadh Ksantini, Imran Shafiq Ahmad and Ling Guan. "SN-SVM: A Sparse Nonparametric Support Vector Machine Classifier". Signal, Image and Video Processing. (link)
  • Naimul Mefraz Khan, Riadh Ksantini, Imran Shafiq Ahmad and Boubaker Boufama. "A Novel SVM + NDA Model for Classification with an Application to Face Recognition". Pattern Recognition, vol. 45 no. 1 pp. 66-79, 2012. (link)
  • Naimul Mefraz Khan and Imran Shafiq Ahmad. "An Efficient Signature Representation for Retrieval of Spatially Similar Images". Signal, Image and Video Processing, vol. 6 no. 1 pp. 55-70, 2012. [Invited Article] (link) 

Conferences and Workshops

  • Naimul Mefraz Khan, Riadh Ksantini, Imran Shafiq Ahmad and Ling Guan. "Incorporating Covariance Information in One Class Support Vector Classification". In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2013), Vancouver, Canada, pp. 35552-3556, 2013.
  • Naimul Mefraz Khan, Matthew Kyan and Ling Guan. "Intuitive Volume Exploration through Spherical Self-Organizing Map". In Proceedings of the Workshop on Self-Organizing Maps (WSOM 2012), Santiago, Chile, pp. 75-84, 2012. (link)
  • Naimul Mefraz Khan, Riadh Ksantini, Imran Shafiq Ahmad and Ling Guan. "A Sparse Support Vector Machine Classifier with Nonparametric Discriminants". In Proceedings of the International Conference on Artificial Neural Networks (ICANN 2012),Lausanne, Switzerland, pp. 330-338, 2012. (link)
  • Naimul Mefraz Khan and Kaamran Raahemifar. "A Novel Accelerated Greedy Snake Algorithm for Active Contours". In Proceedings of the 24th Canadian Conference on Electrical and Computer Engineering (CCECE 2011), Niagara Falls, Canada, pp. 186-190, 2011.  (link)
  • Riadh Ksantini, Boubaker Boufama, Imran Shafiq Ahmad and Naimul Mefraz Khan. "A New Combined KSVM and KFD Model for Classification and Recognition". In Proceedings of the Fifth International Conference on Digital Information Management (ICDIM 2010), Thunder Bay, Canada, pp. 188-193, 2010. (link)
  • Naimul Mefraz Khan, Riadh Ksantini, Imran Shafiq Ahmad and Boubaker Boufama. "A New SVM + NDA Model for Improved Classification and Recognition". In Proceedings of the International Conference on Image Analysis and Recognition (ICIAR 2010), Povoa de Varzim, Portugal, pp. 127-136, 2010. (link)
  • Naimul Mefraz Khan and Imran Shafiq Ahmad. "A New Signature for Quadtree based Image Matching". In Proceedings of the 7th International Conference on Advances in Mobile Computing and Multimedia (MoMM 2009), Kuala Lumpur, Malaysia, pp. 20-27, 2009. (link)

UPDATED: 16 January, 2014