A Novel Approach for Person Authentication Using Finger Knuckle Print Based Biometric System

The identification and authentication are done by passwords, pin number, which is easily cracked by others. Biometrics is a powerful and unique tool based on the functional and behavioral characteristics of the human beings in order to prove their authentication. One of the current trends in biometric human identification is the development of new developing modalities. Knuckle biometrics is one of such favorable modalities. This thesis proposes a novel identificationmethod of biometrics named as Finger Knuckle Print (FKP). The texture pattern produced by the finger knuckle bending is highly unique and makes the surface a distinctive biometric identifier. At the preprocessing stage the gray scale values generate from the original image. The generated gray scale values are then passed to prewitt edge detection technique for the purpose of edge detection. The output of the image of edge detection process is used to increase the intensity values of the original image. The extraction of features of FKP using Scale Invariant Feature Transform (SIFT) and key points are derived from FKP using Support Vector Machine (SVM). The performance of the system for recognition of knuckle achieves 88.75 % accuracy rate.