Personal authentication using partial palmprint and palmvein images with image quality measures

Nowadays, biometric identification technology is used for authentication purposes. Of that, Multimodal biometric authentication systems are gaining much popularity. In this paper, we propose a system that can be used in place of ATM cards. This ensures a sense of security as well as privacy to the user. Here, partial palmprint and partial palmvein are combined for identification of an individual. Partial palmprint matching is accomplished by recursive adjoint minutiae matching method where a coarse to fine matching technique is used. Maximum curvature method is used for extracting the vein pattern. The binarised patterns thus formed are used as templates. Palmvein matching is done using Hamming distance. Even after making the system multimodal, it is prone to spoof attacks. So in order to make the system more robust, image quality measures are used to classify the input image as real or fake. The proposed method extracts 25 image quality measures. This algorithm has practical value and is efficient and reliable.