Interactive facial caricaturing system based on eye camera

Abstract

Face is the most effective visual media for supporting human interface and communication. We have proposed a typical KANSEI machine vision system to generate the facial caricature so far. The basic principle of this system uses the "mean face assumption" to extract individual features of a given face. This system did not provide for feedback from the galleiy of the caricature; therefore, to allow for such feedbaclç in this paper, we propose a caricaturing system by using KANSEI visual information acquiid from the Eye-camera mounted on the head of a gallery because it is well known that the gaze distribution repisents not only where but also how he is looking at the face. The caiicatures created in this way could be based on several measures which are provided fmm the distiibulion of the number of fixations to the facial parts, the number of times the gaze came to a particular area of the face, and the matiix of the tnmsitions from a facial region to the other. These measures of the galleiy's KANSEI information were used to create caricatures with feedback from the galleiy.