Authentication by Palmprint Using Difference of Block Means Code

Abstract

Biometrics is an automatic identification of people with their physiological and behavioural characteristics. There are various modes used in biometrics, such as face, iris, retina, fingerprint, palmprint, palm vein, ear, handwriting, speech, gait, and so on. All these types of biometrics have some shortcomings. Palmprint identification is the biometric methodology used in this chapter, has several advantages over other biometric features which includes user friendliness, environment flexibility, and discriminating capacity. For several years, palmprint identification has been employed in a variety of applications. In the proposed system, the difference of block means approach is used to recognize palmprint which only requires fundamental operations (addition and subtractions), resulting in a significantly lower computing cost compared to existing systems. Even with low-resolution images, the palmprint authentication method yields substantially better results. CASIA Multispectral Palmprint database is used in the experiments. The proposed approach achieves better accuracy.