Evaluation of Periocular over Face Biometric: A Case Study

Abstract

Recognition of a person through his face is the primitive mean of human identification. Identifying a person through face biometric have grown its importance through the last decade and researchers have attempted to find unique facial feature-points. Facial data also contains change with expression and age, which makes recognition through face difficult. And there has developed a stringent necessity to identify a person on partial facial data. These motives led researchers derive auxiliary biometric traits from facial image, viz. ear, lip and periocular region. In particular, periocular region has been exploited to examine the existence of uniqueness as there are many nodal points in periocular region. Classification and recognition is achieved through periocular region which shows significant accuracy, given the fact that periocular biometric uses only 25% of a complete face data.