RotationCorrectionandClassificationofFingerprintImage指纹图像.PDFVIP

Computer Science and Application 计算机科学与应用, 2014, 4, 85-94 Published Online May 2014 in Hans. /journal/csa /10.12677/csa.2014.45014 Rotation Correction and Classification of Fingerprint Image 1 1,2 1,2 Wanlin Yin , Hua Ye , Yanlan Yang 1 School of Automation, Southeast University, Nanjing 2 Key Laboratory of Measurement and Control of Complex Systems of Engineering of Ministry of Education, Southeast University, Nanjing Email: zhineng@ th st th Received: Apr. 8 , 2014; revised: May 1 , 2014; accepted: May 8 , 2014 Copyright © 2014 by authors and Hans Publishers Inc. This work is licensed under the Creative Commons Attribution International License (CC BY). /licenses/by/4.0/ Abstract In order not only to improve the speed and accuracy of fingerprint recognition in the large-capacity database, but also to extract more detailed features, this paper presents a classification algorithm by using the features of cores, which are extracted from a corrected fingerprint. In the first phase, according to the smallest external ellipse and rectangle, the declining fingerprint is corrected by the affine transformation. In the second phase, to heighten anti-noise capability of traditional Poincare index, an improved algorithm is proposed, and then false points are denoised by sum- marizing the human recognition experience. Finally, the absolute direction, the diameter of screw and other features are the basis for fingerprint classification. 400 fingerprint images collected by FPC1011F fingerprint sensor are used for an experimental test, and the accuracy rate on classifi- cation is 91.25%. The ex