Portrait of Kaleem Siddiqi

Kaleem Siddiqi

Associate Academic Member
Professor, McGill University, School of Computer Science
Research Topics
Computational Biology
Computational Neuroscience
Computer Vision
Medical Machine Learning
Website
Google Scholar

Biography

Kaleem Siddiqi is a professor of computer science at McGill University and a member of McGill’s Centre for Intelligent Machines. He is also an associate academic member of Mila – Quebec Artificial Intelligence Institute, McGill’s Department of Mathematics and Statistics, and the Goodman Centre for Cancer Research at McGill. He holds an FRQS Dual Chair in Artificial Intelligence and Health with Keith Murai. Siddiqi’s research interests lie in computer vision, biological image analysis, neuroscience, visual perception and robotics. He is field chief editor for Frontiers in Computer Science and has served as an associate editor of IEEE Transactions on Pattern Analysis and Machine Intelligence, Pattern Recognition and Frontiers in ICT. He is co-author with Steve Pizer of the book Medial Representations: Mathematics, Algorithms and Applications (Springer, 2008).

Current Students

Kathie Cai
PhD - McGill University
Github
Elise Donszelmann-Lund
Master's Research - McGill University
Github
Sophie Ellwood
Master's Research - McGill University
Github
Dima Fedorenko
PhD - McGill University
Github
Google Scholar
Isabel Frolick
Master's Research - McGill University
Github
Faizan Jilani
Master's Research - McGill University
Arnab Kumar-Mondal
PhD - McGill University
Principal supervisor :
Siamak Ravanbakhsh
Website
Github
Google Scholar
Justin Lacoste
Undergraduate - McGill University
Ben Lo
Master's Research - McGill University
Megan Ng
PhD - McGill University
Marc Theveneau
PhD - McGill University
Github
Yanan Wang
Master's Research - McGill University
Marina Zhou
Master's Research - McGill University

Publications

Medial Spectral Coordinates for 3D Shape Analysis
Morteza Rezanejad
Mohammad Khodadad
H. Mahyar
Hervé Lombaert
M. Gruninger
Dirk. B. Walther
Kaleem Siddiqi
In recent years there has been a resurgence of interest in our community in the shape analysis of 3D objects repre-sented by surface meshes,… (see more) their voxelized interiors, or surface point clouds. In part, this interest has been stimulated by the increased availability of RGBD cameras, and by applications of computer vision to autonomous driving, medical imaging, and robotics. In these settings, spectral co-ordinates have shown promise for shape representation due to their ability to incorporate both local and global shape properties in a manner that is qualitatively invariant to iso-metric transformations. Yet, surprisingly, such coordinates have thus far typically considered only local surface positional or derivative information. In the present article, we propose to equip spectral coordinates with medial (object width) information, so as to enrich them. The key idea is to couple surface points that share a medial ball, via the weights of the adjacency matrix. We develop a spectral feature using this idea, and the algorithms to compute it. The incorporation of object width and medial coupling has direct benefits, as illustrated by our experiments on object classification, object part segmentation, and surface point correspondence.
2021-11-26
ArXiv (preprint)
doi.org
arxiv.org