文章基本信息

标题：Identification of Distortion and Rectification of Fingerprints in Negative Fingerprint Recognition
本地全文：下载
作者：Harsh Anand
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：2017
卷号：5
期号：2
页码：1373
DOI：10.15680/IJIRCCE.2017.0502012
出版社：S&S Publications
摘要：Automatic fingerprint recognition technologies have rapidly adapting during the last few years, therestill exists several challenging research problems, for example, recognizing low quality fingerprints. One of thedisadvantages of fingerprint confirmation is the lack of robustness against image quality degradation. Low qualityimages result in misleading and missing features, thus degrading the performance of the overall system. Hence it is ofutter importance for a fingerprint acknowledgement system to estimate the quality and validity of the capturedfingerprint image samples. Distortion of fingerprint hides the identity of the person, while this problem affects theprocedure of identifications. It is very dangerous in negative recognition application. Many places malicious usersdistort their fingerprints to hide their identification. We proposed novel algorithm to detect and rectify skin distortionbased on a single fingerprint image. Distortion detection is viewed as two-class classification problem, the registeredridge orientation map and period map of fingerprint are used. SVM classifier performs the classification task
关键词：Fingerprint; distortion; registration; nearest neighbour regression