An effective quality improvement approach for low quality finger vein image
Wei Pi, Jinook Shin, Dongsun Park · 2010
In recent years, finger vein authentication technology becomes a new highlight in biometric technology. However, the acquired images are low quality because of near-infrared conditions and different structures in different parts of finger, which will severely impacts identification accuracy of the whole system. Therefore, it is necessary to improve the quality of images. In this paper, an effective approach for improving the quality of images is proposed. At first, edge-preserving filter is used for denoising, and then the small blurred finger vein textures are enhanced by elliptic highpass filter. Finally, histogram equalization enhances the contrast of images. The experimental images and estimation results show that the finger vein images become much clearer than original ones, and prove the proposed approach is efficient to improve the quality of images.