Fingerprint matching by using 2D discrete cosine transform and 2D Fourier transforms

Abstract

In this paper, we proposed a fingerprint matching using the two dimensional discrete cosine transform features. In this paper we crop input images from the size 480x640 pixels into 128x128 pixels, and then divided the image into 64 sub-images, earth sub-images have the size 16x16 pixels. We measure our algorithm performs by the correlation value of the 2D discrete cosine transform (DCT) and 2D Fourier transforms (FFT). And we used images for testing are obtained from FVC-2004 (DB-1A) and FVC - 2002 (DB2-A). From this evaluation and results, we can see that this method offers better performance when compared to other individual matching. Moreover, our method is not sensitive to rotational effect. The proposed technique is based on the availability of core point, therefore, the proposed technique introduce some errors if the core point cannot be located or improperly located. The matching is performed using the two dimensional discrete cosine transform and two dimensional Fourier transform to find the magnitude of the spectrum, spectrum phase, and the value of line angle. copy;2012 IEEE.