الفهرس | Only 14 pages are availabe for public view |
Abstract As our everyday life is getting more and more computerized, automated security systems are getting more and more important. Today most personal banking tasks can be performed over the Internet and soon they can also be performed on mobile devices such as cell phones and Personal Digital Assistant (PDAs). An accurate automatic personal identification is critical in a wide range of application domains such as national ID, electronic commerce, and automated banking. The recent developments in the biometrics area have lead to smaller, faster and cheaper systems, which in turn has increased the number of possible application areas for biometric identity verification. Biometrics, which refers to automatic identification of a person based on physiological of behavioral characteristics, is inherently more reliable and more capable in differentiating between an authorized person and a fraudulent impostor than traditional methods such as passwords and PIN numbers. Automatic Fingerprint Identification System (AFIS) is one of the most reliable biometric technologies. In this thesis, our objective is to find a new method for fingerprint image representation. The new representation method can be used in fingerprint image enhancement, classification through the identification system stages We have identified and explode the following issue: fingerprint images capturing and structures- define the different types of capturing process and different types of fingerprint structures that can be used in the identification system. Feature extraction- finding the representative features from an input fingerprint image for purpose of fingerprint matching. Fingerprint matching- determining whether two sets of fingerprint features are extracted from the same finger. Fingerprint image enhancement- improving the clarity of ridge structure of fingerprint images to facilitate automatic extraction of features or for visual inspection. (v) Fingerprint classification- assigning a fingerprint into one of several prespecified categories according to its pattern formation. We developed three new techniques: fingerprint image enhancement based on frequency domain representation, fingerprint image enhancement algorithm based on using the new representation method called wavelet domain, and fingerprint classification based on frequency domain representation. Our developed methods have been evaluated extensively on a large number of fingerprint images captured with the traditional inked method and more recent inkless optical scanner. Experimental results show that our proposed algorithms perform very well on the different fingerprint databases. |