Palmprint recognition based on translation invariant Zernike moments and modular neural network

This paper introduces a new approach for palmprint recognition, using translation invariant Zernike moments (TIZMs) as palm features, and a modular neural network (MNN) as classifier. Translation invariance is added to the general Zernike moments which have a good property of rotation invariance. The pattern set is set up by eight-order TIZMs with 25 dimensions. A modular neural network is presented in order to decompose the palmprint recognition task into a series of smaller and simpler two-class sub-problems. Simulations have been done on the Polyu_PalmprintDB database, which is composed of 3200 palmprints (10 palmprints/person). Experimental results demonstrate that higher identification rate and recognition rate are achieved by the proposed method in contrast with the straight-line segments (SLS) based method and the Fuzzy Directional Element Energy Feature (FDEEF) method.