Fingerprint Feature Extraction and Identification using Direction Oriented Matrix with Color Band

Fingerprint recognition is the method of biometric authentication that uses pattern recognition techniques based on the high resolution fingerprint images. Fingerprints have several advantages over other biometrics such as the following: high universality, distinctiveness, permanence and performance, easy collectable and wide acceptability. The fingerprint image is made up of pattern of ridges and valleys; they are replica of the human fingertips. The fingerprint image represents a system of oriented texture and has very rich structural information within the image. A new algorithm to extract the fingerprint features using direction matrix is proposed. The work flow is to transform the fingerprint image into 16X16 matrix by computing the orientation field using gradient information. The feature matrix is used to identify the features, in this regard, a color band information is derived which follows a different pattern for different feature based fingerprint images. The algorithm was implemented in MATLAB environment using the images from FVC databases.