期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2016
卷号：4
期号：2
页码：2716
DOI：10.15680/IJIRCCE.2016.0402259
出版社：S&S Publications
摘要：One of the open come outs in fingerprint confirmation is the lack of robustness against image quality degradation. Poor - quality images result in specious and missing features, thus degrading the performance of the overall system. Therefore, it is very import ant for a fingerprint acknowledgement system to estimate the quality and validity of the captured fingerprint images. Also the elastic distortion of fingerprints is one of the major causes for false non - match. While this problem impacts all fingerprint ack nowledged applications, it is especially unsafe in negative recognition applications, such as watch list and reduplication applications. In such applications, malicious users may purposely distort their fingerprints to elude identification. In this paper, we proposed novel algorithms to detect and rectify skin distortion based on a individual fingerprint image. Distortion notification is viewed as a two - class classification problem, for which the registered ridge orientation map and period map of a fingerpr int are used as the feature vector and a SVM classifier is prepared to perform the classification task.. Distortion detection is displayed as a two - class categorization problem, for which the registered ridge orientation map and period map of a fingerpri nt are beneficial as the feature vector and a SVM classifier is trained to act the classification task. Distortion rectification (or equivalently distortion field estimation) is viewed as a regression complication, where the input is a distorted fingerprin t and the output is the distortion field. To clarify this problem, a database (called reference database) of various distorted reference fingerprints and corresponding distortion fields is built in the offline stage, and then in the online stage, the close st neighbor of the input fingerprint is organized in the reference database and the corresponding distortion field is used to transform (Convert) the input fingerprint into a normal fingerprints. Promising results have been obtained on three databases havi ng many distorted fingerprints, namely FVC2004 DB1, Tsinghua Distorted Fingerprint database, and the NIST SD27 latent fingerprint database
