Palmprint is one of the relatively new physiological biometric that rich with unique and stable texture information. An important issue in palmprint verification is extract palmprint features that can discriminate a person from the other. This paper proposes a new technique to extract the palmprint features based on fractal characteristics. The binary palmprint image is formed based on position of range block of fractal codes. The fractal dimension image is formed from the binary image. The fractal dimension image is divided into a set n blocks and the mean value of each block is used to form the feature vector. The normalized correlation metrics is used to measure the degree of similarity of two features vectors of palmprint images. We collected 1050 palmprint images, 5 samples from each person, for 210 persons. Experimental results show that our proposed method can achieve an acceptable accuracy rate with FRR = 0.4785, and FAR = 0.3435.
展开▼
