Dental extraction & matching using contour algorithm on JPG and DICOM images for human identification

In this paper, Dental radiographs of JPG and DICOM images are collected from authenticate sources. Two Identical Images are to be considered to match with all images. Proposed algorithm is developed to match, In proposed algorithm adjacent pixels and Pattern are generated to match with all other images to identify the person. Adjacent pixels are considered in manners where difference between any pixels value to be considered as matching points, after applying this method to entire image matrix, all points are to be connected and pattern is generated. This Patterns coordinates values are matched with method of Euclidian distance with all other images after applying above procedure. After getting results, FAR (False Acceptence rate) and FRR (False Rejection Rate) derieved and optimum value of EER (Equal Error Rate) is defined. Also GUI of all work is prepared so as and when practical application is needed, this software we can directly connected to any security system.