Aiming to identify the finger vein and considering the rich texture characteristics of the finger vein, a near infrared finger vein recognition approach based on wavelet grayscale surface matching is proposed. The region of interest of the original image is adjusted by using the histogram equalization, the different resolution images are extracted after decomposition, and the images for matching are constructed. The gray difference surface is obtained by computing the gray difference of two pixels from two different images. The variance is calculated by using the gray difference surface, and is considered as the distance between two feature surfaces of the finger vein images, and the result is used to determine whether the two finger vein images are from the same finger. The comparison experiments are performed with the typical and popular approaches on two databases. The experimental results show that the lowest equal error rate (EER) is 0% and 4.6281% respectively, and the recognition time is only 0.061 s and 0.0502 s, respectively, when the different resolution images are extracted after Haar wavelet decomposition. The superiority and feasibility of the proposed approach is indicated , and high accuracy, good security and fast running speed of the approach are exhibited.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.