A Pixel-level Statistical Structural Descriptor for Shape Measure and Recognition

Abstract

A novel shape descriptor based on the histogram matrix of pixel-level structural features is presented. First, length ratios and angles between the centroid and contour points of a shape are calculated as two structural attributes. Then, the attributes are combined to construct a new histogram matrix in the feature space statistically. The proposed shape descriptor can measure circularity, smoothness, and symmetry of shapes, and be used to recognize shapes. Experimental results demonstrate the effectiveness of our method.