Towards Accurate Estimation of Fingerprint Ridge Orientation Using BPNN and Ternarization

Abstract

Accurate estimation of ridge orientation is a crucial step in fingerprint image enhancement because the performance of a minutiae extraction algorithm and matching heavily relies on the quality of the input fingerprint images, which in turn relies on proper estimation of ridge orientation. When ridge structure is not clear in a noisy fingerprint image, ridge orientation estimation becomes tough and it is considered as one of the most challenging tasks in fingerprint image enhancement process. A new methodology based on neural network approach and Ternarization for ridge orientation estimation is proposed in this paper. In the present work a trained Back Propagation Neural Network (BPNN) is used for accurate ridge orientation. The advantage with the Ternarization process is that it eradicates the false ridge orientation for which the neural network wrongly responds with the larger value and at the same time, it keeps the correct ridge orientation blocks intact without making them blur. This helps in qualitative extraction of minutiae points from the fingerprint image. The experimental results have shown that the proposed method for estimating ridge orientation works far better than the traditional gradient based approach.