Pruning Local Feature Correspondences Using Shape Context

We propose a novel approach to improve the distinctiveness of local image features without significantly affecting their robustness with respect to image deformations. Local image features have proven to be successful in computer vision tasks involving partial occlusion, background noise, and various types of image deformations. However, the relatively high number of outliers that have to be rejected from the correspondences set, formed during the search for similar features, still plagues this approach. The task of rejecting outliers is usually based on estimating the global spatial transform suffered by the features in the correspondences set. This presents two problems: i) it cannot properly deal with non-rigid objects, and ii) it is sensitive to a high number of outliers. Here, we address these problems by combining typical local features [2, 7] with shape context [1]. A performance evaluation shows that this new semilocal feature generally provides higher distinctiveness and robu...

• Type: Conference
• Year: 2004
• Where: ICPR
• Authors: Allan D. Jepson, Gustavo Carneiro
• Keywords: Computer Vision, ICPR 2004, Image Deformations, Local Image Features, Non-rigid Deformations