A Composed Confidence Measure for Automatic Face Recognition in Uncontrolled Environment

摘要: This paper is focused on automatic face recognition in order to annotate people in photographs taken in completely uncontrolled environment. Recognition accuracy of the current approaches is not sufficient in this case and it is thus beneficial to improve the results. We would like to solve this issue by proposing a novel confidence measure method to identify the incorrectly classified examples at the output of our classifier. The proposed approach combines two measures based on the posterior probability and two ones based on the predictor features in a supervised way. The experiments show that the proposed approach is very efficient, because it detects almost all erroneous examples.