ANALYSIS OF BIOMATRICS USING MINUTIAE AND TEXTURE FEATURES

Fingerprint is a reliable biometric which is used for personal verification. Current fingerprint verification techniques can be broadly classified as Minutiae-based, ridge feature-based, correlation-based and gradient-based. Biometrics recognition has been one of the standout research areas in the past decades as the demand for security systems increases, and fingerprint recognition remains as a popular choice due to the ease of acquiring such data and fingerprint is universally accepted as a feature that is unique to all individuals. One of the limitations of existing fingerprint ecognition techniques is that these systems tend to fall short when the available fingerprint is of low quality. This work describes a simple hybrid method that improves the performance of fingerprint recognition technique by fusing minutiae-based and image-based techniques, extracting features from both techniques to compensate the limitations of each of them. Results show that the proposed hybrid method is capable of achieving better recognition rate. Further analyses indicate that the percentage of similarity score and the Euclidean distance computation are both improved, in general. Minutiaebased matching algorithms, which consider ridge activity only in the vicinity of minutiae points, are not likely to perform well on these images due to the insufficient number of corresponding points in the input and template images. We present a hybrid matching algorithm that uses both minutiae (point) information and texture (region) information for matching the fingerprints.