A method for fingerprint enhancement in the frequency domain based on directional log-Gabor filtering is proposed. Experimental results show that the method can successfully enhance even low-quality fingerprint images obtained by the ink method, outperforming standard, well-known techniques including Gabor filtering.Introduction: To utilise automatic fingerprint identification systems (AFIS) in law enforcement agencies, the first step is to digitalise an archive of fingerprints obtained by the ink method. The quality of those fingerprint images greatly depends on the fingerprint acquisition device (equipment and technique) that is used, but there are also a number of factors (postnatal marks, occupational marks, creases, etc.) that contribute to a large number of spurious minutiae detected, decreasing the overall AFIS performance. That is the reason why enhancement is usually performed before minutiae extraction [1]. When dealing with a particular fingerprint image, i.e. latent, we can apply any of many digital techniques and filters, even combining and adjusting them for that particular case. However, in the case of making a database of fingerprint templates for AFIS from an archive of cards of fingerprints usually taken by ink, the process of automatic minutiae extraction is rarely intervened with by a human expert, so an enhancement method needs to be robust and applicable to a wide range of input images. In the literature, several filters have been proposed in the spatial [2] and frequency [3,4] domains. In this Letter, a robust enhancement algorithm in the frequency domain is proposed. It is based first on amplifying the dominant frequencies by a factor of raised power spectrum (noise reduction) and then by appropriate filtering with a log-Gabor filter (directional enhancement). The results prove to be preferable compared to the standard Gaborbased filtering method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.