Minutiae Extraction for Fingerprint and Palm Print Images Using Convolutional Neural Networks

With the growing use of biometric authentication systems in the recent years, spoof fingerprint detection has become increasingly important. To make it more secure palm print detection is used in addition. In this study, we use Convolutional Neural Networks (CNN) for fingerprint and palm print liveness detection. The proposed method consists of two stages. In the first stage, Local Binary Pattern (LBP) is used to change the pixel intensity in the original image. In the second stage, the minutiae extraction and Region of Interest (ROI) are applied to get minute authentication. Experimental results show that the proposed algorithm gives high security compared to existing methods such as Weber Local Descriptor (WLD) and Local Binary Pattern (LBP).