Combining rectangular and triangular image regions to perform real-time face detection

Nowadays, face detection techniques assume growing relevance in a wide range of applications (e.g., biometrics and automatic surveillance)and constitute a pre-requisite of many image processing stages. Among a large number of published approaches, one of the most relevant is the method proposed by Viola and Jones to perform real-time face detection through a cascade schema of weak classifiers that act together to compose a strong and robust classifier. This method was the basis of our work and motivated the key contributions given in this paper. At first, based on the computer graphics concept of ldquotriangle meshrdquo we propose the notion of ldquotriangular integral featurerdquo to describe and model face properties. Also, we show results of our face detection experiments that point to an increase of the detection accuracy when the triangular features are mixed with the rectangular in the candidate feature set, which is considered an achievement. Also, it should be stressed that this optimization is obtained without any relevant increase in the computational requirements, either spatial or temporal, of the detection method.