TY - GEN
T1 - Spatialized epitome and its applications
AU - Chu, Xinqi
AU - Yan, Shuicheng
AU - Li, Yuan
AU - Chan, Kap Luk
AU - Huang, Thomas S.
N1 - Copyright:
Copyright 2010 Elsevier B.V., All rights reserved.
PY - 2010
Y1 - 2010
N2 - Due to the lack of explicit spatial consideration, existing epitome model may fail for image recognition and target detection, which directly motivates us to propose the so-called spatialized epitome in this paper. Extended from the original graphical model of epitome, the spatialized epitome provides a general framework to integrate both appearance and spatial arrangement of patches in the image to achieve a more precise likelihood representation for image(s) and eliminate ambiguities in image reconstruction and recognition. From the extended graphical model of epitome, an EM learning procedure is derived under the framework of variational approximation. The learning procedure can generate an optimized summary of the image appearance with spatial distribution of the similar patches. From the spatialized epitome, we present a principled way of inferring the probability of a new input image under the learnt model and thereby enabling image recognition and target detection. We show how the incorporation of spatial information enhances the epitome's ability for discrimination on several vision tasks, e.g., misalignment/cross-pose face recognition and vehicle detection with a few training samples.
AB - Due to the lack of explicit spatial consideration, existing epitome model may fail for image recognition and target detection, which directly motivates us to propose the so-called spatialized epitome in this paper. Extended from the original graphical model of epitome, the spatialized epitome provides a general framework to integrate both appearance and spatial arrangement of patches in the image to achieve a more precise likelihood representation for image(s) and eliminate ambiguities in image reconstruction and recognition. From the extended graphical model of epitome, an EM learning procedure is derived under the framework of variational approximation. The learning procedure can generate an optimized summary of the image appearance with spatial distribution of the similar patches. From the spatialized epitome, we present a principled way of inferring the probability of a new input image under the learnt model and thereby enabling image recognition and target detection. We show how the incorporation of spatial information enhances the epitome's ability for discrimination on several vision tasks, e.g., misalignment/cross-pose face recognition and vehicle detection with a few training samples.
UR - http://www.scopus.com/inward/record.url?scp=77956002825&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77956002825&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2010.5540196
DO - 10.1109/CVPR.2010.5540196
M3 - Conference contribution
AN - SCOPUS:77956002825
SN - 9781424469840
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 311
EP - 318
BT - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
T2 - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
Y2 - 13 June 2010 through 18 June 2010
ER -