TY - JOUR
T1 - Unsupervised category modeling, recognition, and segmentation in images
AU - Todorovic, Sinisa
AU - Ahuja, Narendra
N1 - The support of the US National Science Foundation under grant NSF IIS 07-43014 is gratefully acknowledged. The authors would like to thank Himanshu Arora and the anonymous reviewers whose thoughtful comments and suggestions improved the quality of the paper.
PY - 2008
Y1 - 2008
N2 - Suppose a set of arbitrary (unlabeled) images contains frequent occurrences of 2D objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupervised identification of photometric, geometric, and topological properties of multiscale regions comprising instances of the 2D category; (2) learning a region-based structural model of the category in terms of these properties; and (3) detection, recognition and segmentation of objects from the category in new images. To this end, each image is represented by a tree that captures a multiscale image segmentation. The trees are matched to extract the maximally matching subtrees across the set, which are taken as instances of the target category. The extracted subtrees are then fused into a tree-union that represents the canonical category model. Detection, recognition, and segmentation of objects from the learned category are achieved simultaneously by finding matches of the category model with the segmentation tree of a new image. Experimental validation on benchmark datasets demonstrates the robustness and high accuracy of the learned category models, when only a few training examples are used for learning without any human supervision.
AB - Suppose a set of arbitrary (unlabeled) images contains frequent occurrences of 2D objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: (1) unsupervised identification of photometric, geometric, and topological properties of multiscale regions comprising instances of the 2D category; (2) learning a region-based structural model of the category in terms of these properties; and (3) detection, recognition and segmentation of objects from the category in new images. To this end, each image is represented by a tree that captures a multiscale image segmentation. The trees are matched to extract the maximally matching subtrees across the set, which are taken as instances of the target category. The extracted subtrees are then fused into a tree-union that represents the canonical category model. Detection, recognition, and segmentation of objects from the learned category are achieved simultaneously by finding matches of the category model with the segmentation tree of a new image. Experimental validation on benchmark datasets demonstrates the robustness and high accuracy of the learned category models, when only a few training examples are used for learning without any human supervision.
KW - Graph matching
KW - Hierarchical object representation
KW - Image segmentation tree
KW - Object recognition
KW - Tree union
KW - Unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=56549126210&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=56549126210&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2008.24
DO - 10.1109/TPAMI.2008.24
M3 - Article
C2 - 18988949
AN - SCOPUS:56549126210
SN - 0162-8828
VL - 30
SP - 2158
EP - 2174
JO - IEEE transactions on pattern analysis and machine intelligence
JF - IEEE transactions on pattern analysis and machine intelligence
IS - 12
ER -