Efficient retrieval of deformable shape classes using local self-similarities
Authors:
- 1 September 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 264-271
Abstract
We present an efficient object retrieval system based on the identification of abstract deformable `shape' classes using the self-similarity descriptor of Shechtman and Irani. Given a user-specified query object, we retrieve other images which share a common `shape' even if their appearance differs greatly in terms of colour, texture, edges and other common photometric properties. In order to use the self-similarity descriptor for efficient retrieval we make three contributions: (i) we sparsify the descriptor points by locating discriminative regions within each image, thus reducing the computational expense of shape matching; (ii) we extend to enable matching despite changes in scale; and (iii) we show that vector quantizing the descriptor does not inhibit performance, thus providing the basis of a large-scale shape-based retrieval system using a bag-of-visual-words approach. Performance is demonstrated on the challenging ETHZ deformable shape dataset and a full episode from the television series Lost, and is shown to be superior to appearance-based approaches for matching non-rigid shape classes.Keywords
This publication has 7 references indexed in Scilit:
- Matching Local Self-Similarities across Images and Videos2007
- Object retrieval with large vocabularies and fast spatial matching2007
- Fast Non-Rigid Surface Detection, Registration and Realistic AugmentationInternational Journal of Computer Vision, 2007
- Scalable Recognition with a Vocabulary Tree2006
- Contour-based learning for object detection2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Video Google: a text retrieval approach to object matching in videos2003