DocumentCode :
2400120
Title :
Connected Segmentation Tree — A joint representation of region layout and hierarchy
Author :
Ahuja, Narendra ; Todorovic, Sinisa
Author_Institution :
Beckman Inst., Univ. of Illinois at Urbana-Champaign, Urbana, IL
fYear :
2008
fDate :
23-28 June 2008
Firstpage :
1
Lastpage :
8
Abstract :
This paper proposes a new object representation, called connected segmentation tree (CST), which captures canonical characteristics of the object in terms of the photometric, geometric, and spatial adjacency and containment properties of its constituent image regions. CST is obtained by augmenting the objectpsilas segmentation tree (ST) with inter-region neighbor links, in addition to their recursive embedding structure already present in ST. This makes CST a hierarchy of region adjacency graphs. A regionpsilas neighbors are computed using an extension to regions of the Voronoi diagram for point patterns. Unsupervised learning of the CST model of a category is formulated as matching the CST graph representations of unlabeled training images, and fusing their maximally matching subgraphs. A new learning algorithm is proposed that optimizes the model structure by simultaneously searching for both the most salient nodes (regions) and the most salient edges (containment and neighbor relationships of regions) across the image graphs. Matching of the category model to the CST of a new image results in simultaneous detection, segmentation and recognition of all occurrences of the category, and a semantic explanation of these results.
Keywords :
computational geometry; image matching; image representation; image segmentation; trees (mathematics); unsupervised learning; CST graph representations; Voronoi diagram; connected segmentation tree; containment properties; inter-region neighbor links; joint representation; object representation; object segmentation tree; point patterns; recursive embedding structure; region adjacency graphs; region layout; spatial adjacency; unsupervised learning; Encoding; Image edge detection; Image recognition; Image segmentation; Object segmentation; Photometry; Sociotechnical systems; Solid modeling; Tree graphs; Unsupervised learning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on
Conference_Location :
Anchorage, AK
ISSN :
1063-6919
Print_ISBN :
978-1-4244-2242-5
Electronic_ISBN :
1063-6919
Type :
conf
DOI :
10.1109/CVPR.2008.4587626
Filename :
4587626
Link To Document :
بازگشت