Extraction of facial sketch image based on morphological processing

This paper proposes a new method to extract a facial sketch image from a facial image robustly. The extraction process consists of two processing steps and morphology plays an important role in the whole processing. Firstly, a generalized symmetry operator, rectangle-filter and a geometric template are used to detect the eyes and mouth. Based on the detected facial parts, the locations of other facial parts are detected using their geometrical locations and characteristic shapes. Secondly, the feature points are determined from the edges of each facial part. Line-drawings connecting them give the facial sketch image. Experiments using 300 facial images were performed and the rate of extracting the facial sketch image correctly was 91%. This result shows the effectiveness of the proposed system.