Fingerprint enhancement using the second-order oriented partial differential equation

The automatic fingerprint identification systems (AFIS) have wide and long practical application nowadays, however, there still exists a lot of challenging and established image processing and pattern recognition problems. In this paper, we improve the second-order oriented PDE model (SOOPDE) from a simple technical processing and apply it to Fingerprint Images (FI). The main advantage of SOOPDE is that it makes the diffusion only along fringe orientation; the fringe will be protected during filtering. Besides, it can also join broken fingerprint ridges, fill out the holes of fingerprint images, smooth irregular ridges as well as remove some annoying small artifacts between ridges. To demonstrate the performance of the SOOPDE, we test it on three fingerprint images of poor quality and compare with the fast fingerprint image enhancement algorithm using a parabolic mask (FEAPM). The experimental results prove that the SOOPDE model can achieve a good performance. In addition, we make a comparison on two methods that widely used for evaluation of the angle θ of fingerprint orientation.