Implementation of translational and rotational palm print recognition

Abstract

Biometrics based personal identification is regarded as an effective method for automatically recognizing, with a high confidence, a person's identity. Computer-aided personal recognition is becoming increasingly important in our information society. Biometric identification is an emerging technology that can solve security problem in our networked society. Many biometric methods are closely connected with methods of pattern recognition and image analysis the reliability of personal identification using face is currently low as the researchers today continue to grapple with the problems of pose, lighting, orientation and gesture. As the important implementation of biometric technology, palm print verification is one of the most reliable personal identification methods. Human palm print recognition has become an active area of research over the last decade. In this paper a new approach to the palm print pre-processing phase is presented and the personal identification using hand images to improve the performance of palm printbased verification system by integrating hand geometry features. The method proposed to implement palm print recognition is pseudo Zernike moments. A rotational as well as translational invariant scheme is a problem by which it can be overcome while pre-processing the image before the feature extraction of the palm print. Pseudo Zernike moments will reduce the computational time by which accurate and robust biometric system will be developed under different hand gesture examination. Unlike other bimodal biometric systems, the users do not have to undergo the inconvenience of using two different sensors since the palm print and hand geometry features can be acquired from the same image, using a digital camera, at the same time. The extracted feature set is then used to train a neural network. (5 pages)