《Fingerprint Enhancement》.pdfVIP

Fingerprint Enhancement Lin Hong1 1 2 2 , Anil Jain , Sharathcha Pankanti , and Ruud Bolle 1 Pattern Recognition and Image Processing Laboratory Department of Computer Science Michigan State University East Lansing, MI 48824 fhonglin,jaing@ 2 Exploratory Computer Vision Group IBM J. T. Watson Research Center Yorktown Heights, NY 10598 fsharat,bolleg@ Abstract (Figure 1(a)), which are usually called minutiae, are the two most prominent structures used in an automatic fingerprint Fingerprint images vary in quality. In order to ensure identification system. Automatic and reliable extraction of that the performance of an automatic fingerprint identifica- minutiae from a digital fingerprint image is an extremely tion system (AFIS) will be robust with respect to the qual- difficult task. The performance of currently available ity of input fingerprint images, it is essential to incorporate minutia extraction algorithms relies heavily on the quality a fingerprint enhancement module in the AFIS system. In of input digital fingerprint images. Due to a number of this paper, we introduce a new fingerprint enhancement al- factors (aberrant format