Palmprint Recognition Based on Gabor Transforms and Invariant Moments*

Abstract—Proposed a method of combining two-dimensional Gabor transforms and invariant moments to extract palmprint feature, and using multilayer towards feedback neural network for training palmprint images to recognize. This method first pretreated the collected palmprint images and got the region of interest (ROI), then constructed a set of Gabor filters to get ROI eigenvectors, combined with the palm images ’ invariant moment features together as the input of the neural network to train and recognize. Experiments show that the method is effective. Index Terms—palmprint recognition, Gabor transforms, invariant moment