Hybrid eye center localization using cascaded regression and robust circle fitting

We propose a new cascaded regressor for eye center detection. Previous methods start from a face or an eye detector and use either advanced features or powerful regressors for eye center localization, but not both. Instead, we detect the eyes more accurately using an existing facial feature alignment method. We improve the robustness of localization by using both advanced features and powerful regression machinery. Finally, unlike most other methods that do not refine the regression results, we make the localization more accurate by adding a robust circle fitting post-processing step. We evaluate our new approach and show that it achieves state-of-the-art performance on the BioID, GI4E, and the TalkingFace datasets. At an average normalized error of less than 5%, the regressor trained on manually annotated data yields an accuracy of 95.07% (BioID), 99.27% (GI4E), and 95.68% (TalkingFace).