An Improved Palmprint Image Recognition Algorithm via Image Restoration

In this study, we Improved Palm-print Image Recognition Algorithm via Image Restoration. Palm-print 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 palm print-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 palm-print images non locally centralized sparse representation (PINCSR) is used to reconstruct the palm-print image. In the fact, it simulates that due to the defects of the palm-print acquisition device, resulting in the phenomenon of palm-print image blur. On the basis of palm-print 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.