Global and Efficient Self-Similarity for Object Classification and Detection
Thomas Deselaers and Vittorio Ferrari
In: CVPR 2010, 13-18 June 2010, San Francisco, CA, USA.
Self-similarity is an attractive image property which has recently found its way into object recognition in the form of local self-similarity descriptors. 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 withing 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 Classes that GSS outperforms LSS for both classification and detection, and that GSS descriptors are complementary to conventional descriptors such as gradients or color.
|EPrint Type:||Conference or Workshop Item (Oral)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Thomas Deselaers|
|Deposited On:||15 May 2010|