Novel Pose-Variant Face Detection Method for Human-Robot Interaction Application

We propose an efective facial features detection method for human–robot interaction (HRI) with indoor mobile robot. In case of human-robot interaction at mobile robot, its vision system has to cope with dificult problems such as pose variations, illumination changes, and complex backgrounds, which problems mainly arise from the movement of mobile robot. In this paper, in order to overcome such problems, we suggest a new facial feature detection approach based on local image region and direct pixel-intensity distributions. For this, we propose two novel concepts; the directional template for evaluating intensity distributions and the edge-like blob map image with multiple strength intensity. Using this blob map image, we show that the locations of major facial features – two eyes and a mouth – can be reliably estimated. Without boundary information of facial area, final candidate face region is determined by both obtained locations of facial features and weighted correlations with stored facial templates. Our approach is also flexible that can be applicable to both color and gray image. In case of color image, all detection tasks of both facial features and face are rapidly achieved by using the chromatic property of facial color. Experimental results from various color images and well-known gray level face database images show the usefulness of proposed method in HRI applications.