期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2013
卷号：4
期号：4
页码：254-258
语种：English
出版社：Ayushmaan Technologies
摘要：The fingerprint images of people always vary in quality. Fingerprint identification is one of the most popular biometric technologies and is used in criminal investigations, commercial applications and so on. The performance of a fingerprint imagematching algorithm depends heavily on the quality of the input fingerprint images. Fingerprint recognition is one of the basic tasks of the Automated Fingerprint Identification Service (AFIS) of the most famous police agencies. In this paper we introduce a special method called fine enhancement method to analyze the fingerprint images both in space and in frequency. This helps to eliminate the multispectral noise in the image, and then the image is filtered with median filter. From the filtered image we extract the minutiae. As a result more than 45 minutiae points are extracted. Further the orientation field is estimated with the specified angle. The spatial domain methods such as Contrast, Negative and Histogram image enhancement which operate directly on pixels are calculated. Experimental results show that our enhancement method improves the performance of the fingerprint Images and makes it more robust with respect to the quality of input compared to other methods.
