Feature Points Extraction of Thermal Face Using Harris Interest Point Detection

Facial feature extraction has become an important issue in automatic recognition of human faces. Thermal images have the advantage over visual images because of its illumination invariant property. But locating facial feature in thermal image is a difficult task due to less important texture information. In this paper, Harris interest point detector is used to locate the thermal facial features. Harris interest point detector is based on intensity and computes the presence of interest point directly fr om the grey values. Experiment result shows that Harris operator can detect good number of interest points even in illumination variation, rotation, and scaling condition.