Confidence Measure Using Composite Features for Eye Detection in a Face Recognition System

Abstract

We propose a new confidence measure to evaluate the eye detection results and combine two different eye detectors. The confidence for the results of eye detection is measured by the distances from the test sample and the positive samples, where the distance is calculated in the composite feature space. By using the proposed confidence measure, we construct a hybrid detector by combining two different detectors, which are complementary to each other. The experimental results show that the proposed detector provides more accurate eye detection results and consequently results in better face recognition rates compared to when using an individual eye detector.