Robust human identity identification system by using hand biometric traits

Abstract

Automatic personal identification has become an important issue in several applications, such as physical buildings and information systems. Nowadays, biometric techniques are an important and effective solution for automatic personal identification. One of the most popular biometric systems is based on the hand due to its ease of use. Hand has several modalities to be extracted, among them, Finger-Knuckle-Print (FKP) and PaLMprint (PLM), has attracted an increasing amount of attention. This paper investigates these modalities for elaborating an efficient multimodal biometric identification system. For that, the texture information of FKP and PLM is characterized by the Local Binary Pattern (LBP). During the matching phase, an Euclidian distance score is employed to measure the similarity between templates. The proposed system is tested and evaluated using a database of 165 users. Our experimental results show the effectiveness and reliability of the proposed system, which brings high identification accuracy rate.