Illumination Invariant Eye Detection in Facial Images Based on the Retinex Theory

Abstract

Eye detection plays an important role in face recognition because eye features provide a high recognition rate. However, illumination effects such as heavy shadows and drastic lighting change make it difficult to detect eyes well in actual faces. In this paper, we provide a new framework for illumination invariant eye detection robust against varying lighting conditions. First, we use an adaptive smoothing based on the Retinex theory to remove the illumination effects. Second, an eye candidate detection using the edge histogram descriptor (EHD) is performed on the illumination normalized images. Third, SVM classification is utilized for eye verification. Finally, eye positions are determined by the eye probability map (EPM). Experimental results on the CMU-PIE, Yale B, and AR face datasets demonstrate that the proposed method achieves high detection accuracy and fast computation results in eye detection.