Performance evaluation of local appearance based periocular recognition

The human periocular region is known to be one of the most discriminative regions of a face image, and recent studies have indicated its potential as a biometric trait. However, the bulk of the previous work concerning the periocular region consists of feasibility studies that report recognition results on controlled data, and lacks rigorous performance evaluation, thus leaving various open questions regarding the effectiveness of periocular region as a biométrie modality. In this paper we present a performance evaluation of a local periocular texture based recognition approach. Specifically, the paper investigates the effect of input image quality on recognition performance, the uniqueness of texture between different color channels, and texture information present in different color channels. Recognition results of periocular texture features are compared to those of full face texture features and suggest that periocular texture features are robust to varying image quality.