EXTRACTION AND MATCHING OF FINGER VEIN AND IRIS PATTERN BASED AUTHENTICATION SYSTEM USING NEURAL NET

Biometric identity is based on the biological characteristics of individuals. The Iris and Vein recognition system are considered to be the most reliable and accurate biometric identification system. Traditional private recognition system consist of several intuitive defects. Biometric system is an effectual technology to overcome these defects. In this paper, the iris and vein pattern based authentication system is proposed. The 2D filtering techniques are used in both authentication systems. Here, if the user left eye iris as well as right finger vein and right iris and left finger vein are matched the condition is true, it is an authenticated user, it not matched, and the condition is false. The linear process used to the median filters, eliminates noise like reflections. The Edge Detection is used to vessels is extracted and analyzed datasets prediction level. The threshold segmentation is applied for all images segment to input as ROI selection. ROI process is determined in an image or in a volume, to the intention of measurement its size. The Hamming Distance is measured the advantage of dissimilarity between input iris and vein templates and enrolled the templates. Experimental results prove that the proposed approach is more proficient likened to existing approaches for the deemed datasets. It can be seen that the proposed approach of iris and vein segmentation takes reasonable time and authentication Neural net accuracy is also reasonable.