Authentication of Individuals based on Wrist Vein Images by Extracting Phase of Fractional Fourier Transform

Abstract

Nowadays, biometric systems play a main role in personal information protection. Each person has a distinct pattern of wrist veins that can be used for authentication. Fractional Fourier transform (FrFT) changes signal to complex form. In this paper, FrFT was utilized for the time-frequency analysis of images. After the pre-processing stage and extracting veins from the background, the phase of FrFT coefficients was computed for each image. The PUT database was used in the proposed method for verifying individuals. This database consists of 1200 wrist and 1200 palm vein images. In this paper, wrist vein images were only utilized. Receiver Operating Characteristic (ROC) and Support Vector Machine (SVM) were used for feature selection and classification, respectively. The results showed that wrist vein images can be used for verification and FrFT is a capable tool for feature extraction as the average accuracy was obtained 99.65±0.95% in the operating point.