K
Kaleem Siddiqi
Researcher at McGill University
Publications - 167
Citations - 10203
Kaleem Siddiqi is an academic researcher from McGill University. The author has contributed to research in topics: Medial axis & Matching (graph theory). The author has an hindex of 47, co-authored 167 publications receiving 9616 citations. Previous affiliations of Kaleem Siddiqi include Yale University & Adobe Systems.
Papers
More filters
Journal ArticleDOI
TurboPixels: Fast Superpixels Using Geometric Flows
Alex Levinshtein,A. Stere,Kiriakos N. Kutulakos,David J. Fleet,Sven Dickinson,Kaleem Siddiqi +5 more
TL;DR: A geometric-flow-based algorithm for computing a dense oversegmentation of an image, often referred to as superpixels, which yields less undersegmentation than algorithms that lack a compactness constraint while offering a significant speedup over N-cuts, which does enforce compactness.
Journal ArticleDOI
Shock graphs and shape matching
TL;DR: A novel tree matching algorithm is introduced which finds the best set of corresponding nodes between two shock trees in polynomial time and is demonstrated under articulation, occlusion, and moderate changes in viewpoint.
Journal ArticleDOI
Matching hierarchical structures using association graphs
TL;DR: It is proved that, in the new formulation, there is a one-to-one correspondence between maximal cliques and maximal subtree isomorphisms, which allows the tree matching problem to be cast as an indefinite quadratic program using the Motzkin-Straus theorem.
Book
Medial Representations: Mathematics, Algorithms and Applications
Kaleem Siddiqi,Stephen M. Pizer +1 more
TL;DR: This book will serve the science and engineering communities using medial models and will provide learning material for students entering this field.
Journal ArticleDOI
Flux maximizing geometric flows
A. Vasilevskiy,Kaleem Siddiqi +1 more
TL;DR: The gradient flows which maximize the rate of increase of flux of an appropriate vector field through a curve (in 2D) or a surface (in 3D), which lead to a simple and elegant interpretation which is essentially parameter free and has the same form in both dimensions.