Enhanced Shape Context for Object Recognition

Abstract

This paper presents an enhanced approach to recognize objects based on a similarity measure obtained from shape context. Typically, shape context computation samples at regular interval on the contour of an object without regard to landmarks. Corner points of an object being landmarks on the contour; set of corner points is a good descriptor of shape. The paper explores the possibility of computing shape context by sampling the corner points using arch height. Sampling on this boundary feature of the object considerably reduces the number of points. Landmark based shape context provides a stricter algorithm on similarity. Shape context based object recognition being an iterative process involving comparisons and transformations, the reduction in the number of sample points provides a basis for faster recognition of similar objects.

Investigating Jaccard Distance similarity measurement constriction on handwritten pen-based input digit

“…There were 4 sets of handwritten digit samples written by them respectively in the laboratory. Each set contained 9 digit of numbers (1,2,3,4,5,6,7,8,9), therefore altogether 400 handwritten digits were collected. We divided the digits into two groups randomly where each contained 200.…”

An improved 3D shape context registration method for non-rigid surface registration

“…Efforts were made for improving the performance of shape context. Singh et al [9] proposed an enhanced shape context by identifying corner points on object contours as landmarks. Urschler et al [1] incorporated local grey value information from images, normalized cross correlation of neighborhood grey values between points, into shape context.…”