期刊名称：International Journal of Computer Science and Security (IJCSS)
电子版ISSN：1985-1553
出版年度：2007
卷号：1
期号：2
页码：45-51
出版社：Computer Science Journals
摘要：Recognition systems based on biometrics (faces, hand shapes and fingerprints etc.) are finally taking off although it has taken a long way to come. Fingerprints have been a precious tool for law enforcement, forensics and recently in commercial use for over a century. Evaluate the performance of these emerging technologies is tricky problem. Most fingerprint verification algorithms rely on minutiae features, and these algorithms can only be as robust as the underlying minutiae features. Therefore, reliable minutiae extraction is vital to a systemââ,¬â"¢s performance. Most of the feature extraction techniques extract features from thinned images but while dealing with binarization and skeletization of image it introduces noise or superfluous information, which creates troubles for genuine feature extraction. In this paper we have used the mathematical morphology to remove the superfluous information for genuine feature extraction and measure the feature extraction performance through sensitivity and specificity.
关键词：Feature Extraction; Morphology; Fingerprints; superfluous information etc
