Eye corner detection with texture image fusion

The localization of eye corner is of great importance since it offers crucial information in various face-related applications including face tracking, gaze estimation, and facial expression recognition. In this paper, a new approach is proposed which localizes eye corners in a precise and robust way. In our approach, we first estimate a rough location about an eye corner. Then, a set of texture images are derived from regions around the estimated eye corner location. These regions are then fused together to decide the reliability of the estimated eye corner location, and an eye corner´s location will be re-estimated if the current estimated eye corner is evaluated as unreliable. Finally, a local refinement process is also applied which refines the location of the estimated eye corner to create a more satisfactory result. Experiments show that our approach can achieve better detection results than the existing methods.