Using Non-symmetry and Anti-packing Representation Model for Object Detection

Abstract

In this paper, we present a non-symmetry and anti-packing object pattern representation model (NAM) for object detection. A set of distinctive sub-patterns (object parts) is constructed from a set of sample images of the object class; object pattern are then represented using sub-patterns, together with spatial relations observed among the sub-patterns. Many feature descriptors can be used to describe these sub-patterns. he NAM model codes the global geometry of object category, and the local feature descriptor of sub-patterns deal with the local variation of object. By using Edge Direction Histogram (EDH) features to describe local sub-pattern contour shape within an image, we found that richer shape information is helpful in improving recognition performance. Based on this representation, several learning classifiers are used to detect instances of the object class in a new image. The experimental results on a variety of categories demonstrate that our approach provides successful detection of the object within the image.