An Improved Palmprint Image Recognition Algorithm via Image Restoration

Palmprint recognition has the advantages of high precision, fast speed, low price, easy to be accepted by users and so on.So it has a broad development prospect. As the palmprint image is easy to get blurred, it needs to be blurred before the recognition. In this paper, the recognition accuracy is improved by deblitting. On the basis of comparing a variety of defuzzification algorithms, the palmprint images nonlocally centralized sparse representation (PINCSR) is used to reconstruct the palmprint image. In the fact, it simulates that due to the defects of the palmprint acquisition device, resulting in the phenomenon of palmprint image blur. On the basis of palmprint image restoration, feature extraction is performed with a competition code and then classified based on the CR using a regularized least square method(CRC_RLS).Experimental results show that the algorithm has a good recognition effect.