Fingerprint Classification Using Singularities

• Main Authors: Cheng-Lin Jen, 任正麟
• Other Authors: Chaur-Chin Chen
• Format: Others
• Language: en_US
• Published: 2001
• Online Access: http://ndltd.ncl.edu.tw/handle/67813355446298106764

碩士 === 國立清華大學 === 資訊工程學系 === 89 === Fingerprint is an important biometric feature because it’s believed that fingerprint is unique and easiness and the research is studied for a long time. Fingerprint classification provides information for identification. According to the definition of the FBI, fingerprints are classified to eight classes. In the thesis, we only classify fingerprints to four classes: Arch, Left Loop, Right Loop, and Whorl. The thesis describes a set of algorithms using directional image and singularities for fingerprint classification. The approach consists of four major steps. (i)Enhancement, (ii)Directional image computing, (iii)Singular points detection, and (iv)Classification We test the algorithm for the first 800 thumb fingerprint images from NIST Special Database 14. The average recognition rate is 87%.