Palm Recognition Using the Adaptive LWT Based Sparse Representation Method.

To extract the essential features from a relatively small number of sampling set and further improve the feature recognition precision of images, a novel palm recognition method using the adaptive lifting wavelet transform (ALWT) based sparse representation (SR) algorithm is proposed here. This lifting wavelet behaves local texture features in spatial and the fast operation speed. While SR method can effectively represent structure features of images and behaves adaptive denoising characteristics. First, the ALWT method is used to extract high frequency coefficient set and low frequency coefficient set of test images, and then, respectively using the high frequency and low frequency set as the input samples of SR model, the high frequency dictionary denoised and low sparse dictionary can be learned. Furthermore, the high and low frequency dictionaries are fused by weighted coefficient, the sparse dictionary behaved texture features can be obtained. Here the SR model is selected as the one based on fast sparse coding (FSC). Finally, using several classical classifiers to test the validity of extracted features. In test, all palmprint images are selected randomly from the PolyU palmprint database. Experimental results testify the better recognition performance of the proposed algorithm compared with PCA and the common SR model.