Authentication by Hand Vein Patterns using Back Propagation Network

With the advancement of computing systems, biometric validation has required to each field for secure nature and furthermore user-friendly. As per diverse researchers, vein biometric is a better biometric quality among systems. This approach describes the design and implementation of a system for identifying individuals based on their hand vein pattern. The main goal has been to produce a system with a low false acceptance rate. Near Infrared Imaging has been used since this produces a clearer vein pattern than visible light. For this purpose, a consumer webcam is modified to capture images in the NIR spectrum. The system first preprocesses, then image segmentation is performed using a filter that emphasizes the directional nature of veins along with local thresholding. After post processed to remove noise, using morphological operations and blob removal. Later, the entire pattern is thinned to a 1-pixel thick skeleton which is for matching and recognition. Images are matched using a Modified Hausdorff Distance which produces an average distance between two thinned vein patterns. A threshold is used to decide if two vein patterns are similar or not.