Probabilistic Automatic Red Eye Detection and Correction

In this paper we propose a new probabilistic approach to red eye detection and correction. It is based on stepwise refinement of a pixel-wise red eye probability map. Red eye detection starts with a fast non red eye region rejection step. A classification step then adjusts the probabilities attributed to the detected red eye candidates. The correction step finally applies a soft red eye correction based on the resulting probability map. The proposed approach is fast and allows achieving an excellent correction of strong red eyes while producing a still significant correction of weaker red eyes