Contactless fingerprint enhancement via intrinsic image decomposition and guided image filtering

Abstract

Although contactless fingerprint images are rarely affected by skin conditions and finger pressure in comparison with touch-based fingerprint images, they are usually noisy and suffer from low ridge-valley contrast. This paper proposes a robust contactless fingerprint enhancement method based on intrinsic image decomposition and guided image filtering. In order to strengthen the contrast of ridge and valley, intrinsic image decomposition is firstly performed on the observed fingerprint image. Then, the obtained intrinsic fingerprint image is used as the guided image to filter the observed fingerprint image, which can efficiently eliminate noise while preserving the ridge-valley information. Finally, an improved Gabor-based contextual filter is adopted to further enhance the fingerprint image quality. Experimental results of minutiae extraction based on the enhanced fingerprint image demonstrate the validity of the proposed method.