Palm print recognition using liveness detection technique

Abstract

Biometric based identification (or biometric authentication) is one of the fields emerging recently, used as a form of identification and access control in various places. Biometric authentication uses many different aspects of human behavior and physiology. History of threats, failures and spoofs have been recorded for biometric authentication, that seems to indicate that their authentication quality has not yet met the expectation. There are various threats known, of which the so called direct or spoofing attacks, have motivated the need to study the vulnerable points against this type of fraudulent actions. Number of systems exist for biometric detection with anti spoofing methods. But due to increase in spoofing techniques these anti spoofing methods become less efficient. This paper presents a system, that is based on palm print recognition. Palm Print is chosen since it is feature rich and less likely to destruction. The system presented detects the bio metric traits using Liveness detection method and after enhancing the trait using weber's local descriptor algorithm. The proposed system is not specific to any spoofing method. It assess the image quality to detect if the trait is real or fake one. And Euclidean distance formula is used for authentication to reduce both false rejection and false acceptance rate.