Finger Print Detection Technique

Abstract

Fingerprint recognition refers to the automatic method of verifying a match between two human finger prints. Whether two sets of fingerprint ridge descriptions come from a single finger or not is determined by a process of fingerprint matching. This system used minutiae and fuzzy logic as recognition technique. And for the analyzing purpose PSNR and MSE. The matching of fingerprint and features of a fingerprint image are the major feature of Minutiae. Depending on the fingerprint scanner resolution and placement of finger on the sensor, a good quality fingerprint image can be between 25 to 80 minutes. Fuzzy C-mean (FCM) is a data clustering technique in which each data point is related to the cluster which is up to a certain degree specified by the membership grade. The main advantage of fuzzy C- Clustering means that it allows groups to sequentially subscribe to data points, which gives flexibility to express data points, may be related to more than one cluster. The main purpose of this paper is to develop a precise, fast and very efficient system of fingerprint verification techniques. The test included the various process such as fingerprint verification is done by using fuzzy c on the image, clustering of image by finding two center point, enhancement, making mask, finding minutiae, filtering false minutiae, matching of input image with the database, generating PSNR and MSE of the image. A quality measurement between the original and a compressed image is commonly known as Peak Signal to Noise Ratio where as MSE represents the cumulative squared error between the compressed and the original image. The greater the PSNR, the enhanced the quality of the compressed, or reconstructed image whereas lower the value of MSE, the lower the error.