Fingerprint Image Enhancement Using Voting Algorithm(Thai)

Abstract

The performance of fingerprint identification highly depends upon the quality of input fingerprint images. We introduce a new method for enhancing the images by applying the concept of voting algorithm. The first step, the corresponding pixels of image enhanced by Short Time Fourier Transform (STFT) and the same image enhanced by Gabor filtering are voted by taking the one which has higher value of gradients. Step two, the enhanced image will be enhanced again with STFT algorithm. We measured the performance of our method by measuring the percentage of minutiae matching. Experimental results show that the percentage of minutiae matching of the proposed method is significantly higher than that of STFT algorithm and Gabor filtering.