TY - GEN
T1 - Visual pattern discovery for architecture image classification and product image search
AU - Chu, Wei Ta
AU - Tsai, Ming Hung
N1 - Copyright:
Copyright 2012 Elsevier B.V., All rights reserved.
PY - 2012
Y1 - 2012
N2 - Many objects have repetitive elements, and finding repetitive patterns facilitates object recognition and numerous applications. We devise a representation to describe configurations of repetitive elements. By modeling spatial configurations, visual patterns are more discriminative than local features, and are able to tackle with object scaling, rotation, and deformation. We transfer the pattern discovery problem into finding frequent subgraphs from a graph, and exploit a graph mining algorithm to solve this problem. Visual patterns are then exploited in architecture image classification and product image retrieval, based on the idea that visual pattern can describe elements conveying architecture styles and emblematic motifs of brands. Experimental results show that our pattern discovery approach has promising performance and is superior to the conventional bag-of-words approach.
AB - Many objects have repetitive elements, and finding repetitive patterns facilitates object recognition and numerous applications. We devise a representation to describe configurations of repetitive elements. By modeling spatial configurations, visual patterns are more discriminative than local features, and are able to tackle with object scaling, rotation, and deformation. We transfer the pattern discovery problem into finding frequent subgraphs from a graph, and exploit a graph mining algorithm to solve this problem. Visual patterns are then exploited in architecture image classification and product image retrieval, based on the idea that visual pattern can describe elements conveying architecture styles and emblematic motifs of brands. Experimental results show that our pattern discovery approach has promising performance and is superior to the conventional bag-of-words approach.
UR - http://www.scopus.com/inward/record.url?scp=84864129485&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84864129485&partnerID=8YFLogxK
U2 - 10.1145/2324796.2324831
DO - 10.1145/2324796.2324831
M3 - Conference contribution
AN - SCOPUS:84864129485
SN - 9781450313292
T3 - Proceedings of the 2nd ACM International Conference on Multimedia Retrieval, ICMR 2012
BT - Proceedings of the 2nd ACM International Conference on Multimedia Retrieval, ICMR 2012
T2 - 2nd ACM International Conference on Multimedia Retrieval, ICMR 2012
Y2 - 5 June 2012 through 8 June 2012
ER -