Mining concise and distinctive affine-stable features for object detection in large corpus

Abstract

Invariant features extraction is important for object detection. Affine-SIFT (ASIFT) [J.M. Morel and G. Yu, ASIFT: A new framework for fully affine invariant image comparison, SIAM J. Imaging Sci. 2(2) (2009)] has been proved to be fully affine-invariant. However, the high cost of memory and query time hampers its application in large-scale object detection tasks. In this paper, we present a novel algorithm for mining concise and distinctive invariant features called affine-stable characteristics (ASC). Two new notions, global stability and local stability, are introduced to calculate the robustness of each feature from two mutually complementary aspects. Furthermore, to make these stable characteristics more distinctive, spatial information taken from several representative scales is encoded in a concise method. Experiments show that the robustness of our ASC is comparable with ASIFT, while the cost of memory can be reduced significantly to only 5%. Moreover, compared with the traditional SIFT method [D. Lowe, Distinctive image features from scale invariant keypoints, Int. J. Comput. Vis. 60(2) (2004), pp. 91–110], the accuracy of object detection can be improved 38.6% by our ASC using similar amount of features.

Keywords:

• object detection
• feature extraction
• affine-stable features
• data mining
• spatial information

2010 AMS subject classifications :

• 62H35
• 68T10

Acknowledgements

This work is supported by the National Basic Research Programme of China (973 Program, 2007CB311100), National High Technology and Research Development Programme of China (863 Program, 2007AA01Z416), National Nature Science Foundation of China (60873165, 60902090, 61003163), Beijing New Star Project on Science & Technology (2007B071) and Co-building Programme of Beijing Municipal Education Commission.