Naoya Tokuda

Caricature generation system PICASSO-2 exhibited at expo2005 and its performance improvement

We had been researching and developed the original caricature generation system PICASSO. We realized an automated PICASSO system called PICASSO-2. We exhibited the robot that used PICASSO-2 system in the named COOPER in which PICASSO-2 is fabricated, at Aichi Expo EXPO2005. This robot acquires the face image of the visitor, extracts the facial features automatically, deforms them as his caricature, describes it on the shrimp rice cracker, and finally presents the facial caricature to the visitor. COOPER takes a couple of facial images with CCD camera, extracts the facial features from the images, and generates the facial caricature. Afterwards we evaluated the performance of the caricatures by two approaches; accuracy of the facial feature extraction in the image processing and quality of the facial parts drawing in the caricature generation. In this paper, we introduce the subjects which are obtained from the experimental performance evaluation, and we propose the improvement method in order to cope with these subjects.

Complete vision-based modeling of human behavior in visual inspection

This paper proposes a vision-based human modeling by using both analytical property of human body performance and the concurrent gaze pattern for visual inspection. We developed two systems required for 3D motion analysis: firefly capturing camera (FCC) characterized by the monocular camera with large spherical aberration of lens measures the 3D positions of point light sources attached on an object in real time without any special lighting, and passive eye camera (PEC) attached in front of the head extracts irises motion based on the facial image processing such as Hough transform for iris detection and gaze analysis. We demonstrated FCC and PEC are effective to construct the vision-based model of human behavior in visual inspection.

Vision-based modeling of human behavior in visual inspection process

This paper proposes a vision-based human modeling by using both analytical property of human body performance and the concurrent gaze pattern for visual inspection. We developed two systems required for 3D motion analysis: firefly capturing camera (FCC) characterized by the monocular camera with large spherical aberration of lens measures the 3D positions of point light sources attached on an object in real time without any special lighting, and passive eye camera (PEC) attached in front of the head extracts irises motion based on the facial image processing such as Hough transform for iris detection and gaze analysis. We demonstrated FCC and PEC are effective to construct the vision-based model of human behavior in visual inspection.