Global and Efficient Self-Similarity for Object Classification and Detection
published: July 19, 2010, recorded: June 2010, views: 1243
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Self-similarity is an attractive image property which has recently found its way into object recognition in the form of local self-similarity descriptors [5, 6, 14, 18, 23, 27] In this paper we explore global self-similarity (GSS) and its advantages over local self-similarity (LSS). We make three contributions: (a) we propose computationally efficient algorithms to extract GSS descriptors for classification. These capture the spatial arrangements of self-similarities within the entire image; (b) we show how to use these descriptors efficiently for detection in a sliding-window framework and in a branch-and-bound framework; (c) we experimentally demonstrate on Pascal VOC 2007 and on ETHZ Shape Classes that GSS outperforms LSS for both classification and detection, and that GSS descriptors are complementary to conventional descriptors such as gradients or color.
Download slides: cvpr2010_deselaers_gess_01.v1.pdf (2.6 MB)
Download slides: cvpr2010_deselaers_gess_01.ppt (7.1 MB)
Download article: cvpr2010_deselaers_gess_01.pdf (1.4 MB)
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !