Personal Identification System Based on Fingerprint features

Abstract

Fingerprint-based identification is one of the core methodologies for personal identification. It remains a reliable, efficient and commonly accepted biometric. We propose a fingerprint recognition system for identifying the low quality fingerprint images from inkedprinted images on paper. Traditional minutia based approach is not robust to poor quality fingerprint images. In proposed system, the texture-based approach for fingerprint recognition using Discrete Wavelet Transform (DWT) is developed. The input image is preprocessed and gabor filtering is applied for ridge line enhancement. The system finds the local features of the fingerprint using DWT and it is compared to the database using Euclidean distance metric. We trained 150 images and obtained an overall performance up to 95%.The effectiveness of the proposed system can be confirmed through the experimental results.