A spatial pyramidal decomposition method for ear representation using local dual cross patterns

Abstract

In recent years, several scientific works are oriented to develop optimal ear representation, for ear recognition, which is discriminant, compact, and easy-to-implement to ensure the best performance in terms of accuracy, computation cost, and storage requirement. In this manner, this paper presents a novel ear representation based on texture analysis framework, which relies mainly on Dual Cross Pattern (DCP) descriptor and Spatial Pyramid Histogram (SPH) method. The features are extracted using DCP descriptor to capture the textural structure then, the SPH of horizontal ear decomposition is applied to obtain the local information. The feature vector representations of ear image are constructed by concatenating all normalized histograms calculated at each level of the SPH method. Experiments conducted on three ear databases (IITDelhi-1, IIT-Delhi-2 and USTB-1) confirm its performance compared to the recent existing methods.