Block Statistic under Wavelet Decomposition for Palmprint Recognition

In the information society, information security is particularly important. Palmprint recognition for identification provides a new scheme for information security. This paper presents a block statistic method for palmprint identification. Firstly, the method denoised region of interest (ROI) of the palmprint with the first-level wavelet decomposition. Then it blocked the low-frequency sub-image. Low and column vectors of all the sub-image were subtracted in turn. All the differences of the means and the standard deviations constituted feature vector for the image. At last the nearest neighbor classifier was used to classify the images. The method was tested on the basis of UST palmprint image database. From the experimental results, the method can satisfy the uses without excessive demands for collection images.