Combining Template-based and feature-based face detectors

In this work we present the preliminary results of a face detection system based on an hybrid approach: it combines typical feature-based techniques with image-based analysis, in order to better exploit the main characteristics available in the input image. Different modules contribute to the face detection task: 1) a template-based approach initially proposed in [9], 2) an image-based analysis specifically designed to discard false positives, and 3) multiple-classifiers specifically designed to detect faces. The experimental results show that the new approach is able to achieve an accuracy better than previously reported on a face database with complex backgrounds.