Research on Method of Palmprint Feature Extraction

摘要

This paper proposes a method of palmprint feature extraction using Gabor wavelet and improved generalized K-L transform. The new method makes use of Gabor wavelet transform to obtain Gabor eigenvector of palmprint from palmprint ROI (region of interest) images in testing samples, then the improved generalized K-L transform is used to extract the master components and reduce dimensions of Gabor features. Finally, the method of Euclidean distance is used to match the dimensional reduced features with other features in training samples to realize recognition. The method integrates the feature extraction algorithm based on time-frequency transformation with the algorithm based on subspace transformation, and makes full use of Gabor function’s fine capability of feature extraction and also effectively solves the problem of feature’s high dimensions.