Use of Fuzzy Set and Neural Network to Extract Fingerprint Minutiae Points and Location

Abstract

In biometric identification, fingerprint recognition is most popular and widely used method Fingerprints were used as a means of positively identifying a person as an author of the document and are used in law enforcement. Fingerprint recognition has a lot of advantages, a fingerprint is compact, unique for every person, and stable over the lifetime. A predominate approach to fingerprint technique is the uses of minutiae. This thesis presents an investigation and comparative study to extract minutiae points in a particular fingerprint image. In most cases, fingerprint images available are not of good quality; they may be corrupted and degraded due to variation in skin and effective condition. So first a fuzzy logic based image enhancement method has been applied to obtain a more reliable estimation of minutiae points and their location and then a different algorithm used to extract them. Neural network is used to give the training to the location of these minutiae point and to improve the performance of the system. All the implementation work has been done in MATLAB 7.0 Image Processing Toolbox. Experimental result shows that proposed algorithm gives the better result compare to others.