Masafumi Tominaga

Facial caricaturing with motion caricaturing in PICASSO system

The paper discusses how motion features of emotion expression processes could enforce facial caricaturing. It is known from experiments that there are various kinds of motion features in the laughing processes. We implemented a system to deform the motion features caused by emotional expression for enforcing facial caricaturing. In this paper, we propose a new idea to extend the extraction mechanism of the individuality features to the time-axis in addition to spatial extension.

On the detection of feature points of 3D facial image and its application to 3D facial caricature

The paper proposes an automated method for extracting 27 feature points from a 3D facial image. It also shows that 3D facial caricaturing can be realized by such a small number of feature points and that these 27 feature points can be extracted automatically. As a result, it was clarified by comparing a 3D caricature of a 3D PICASSO system with that of a famous caricaturist, Mr. Yoshida, that 3D features of the facial image could be utilized to generate a more impressive facial caricature than the 2D version.

Hierarchical face tracking by using PTZ camera

Since, the basic configuration of the facial caricaturing system PICASSO has been constructed, it is strongly expected to get sufficient input image from a person who is naturally performing in front of the PICASSO camera system. From this viewpoint, we developed a face tracking PC system for capturing sufficient facial image especially in size by means of PTZ (pan-tilt-zoom) camera collaborated with a fixed CCD camera. Irises are successfully recognized from the motion images captured from PTZ camera. These irises can be utilized to provide a key feature for realizing an automated facial recognizing system. In this system, a person performing naturally in pose and in facial expression within the scope of the fixed CCD camera can be stably tracked and the sufficient images in resolution of PTZ camera were successfully analyzed for iris recognition and facial parts extractions.

Web-PICASSO: Internet Implementation of Facial Caricature System PICASSO

The expansion of the site for the facial caricature presentation and evaluation could be opened toward the world through the Internet door. In order to show the works of caricatures and to get the evaluations for them, it is indispensable to have the open channel which can break the limited scope of the community. This is the reason why we proposed the Internet implementation of facial caricature system Web-PICASSO. And, in order to expand the database of this system at the same time, a mechanism to collect the face data was also implemented. Web-PICASSO was located at the Internet home page addressed by http://www.koshi-lab.sccs.chukyo-u.ac.jp/~fuji/pica2/. Web-PICASSO system was described by Java in order to cope with the various client environments. First this paper presents the basis for generating facial caricature, and the outline and experiments of Web-PICASSO are explained to show the possibilities for collecting the evaluations and questionnaires from visitors. In the future these collected evaluations will be utilized to polish the caricature due to the visitors individual KANSEI, and furthermore the mechanism to get the visitors face image through Web-PICASSO environment can be constructed in the caricaturing process.

Facial caricaturing system PICASSO with emotional motion deformation

Discusses how motion features of emotional expression processes could enforce facial caricaturing. A still caricature is not enough to express individual character. It was experimentally known that there are various kinds of motion features in the laughing processes. We implemented a system to deform the motion features caused by emotional expression for enforcing facial caricaturing. We propose an idea to extend the extraction mechanism of the individuality features to the time-axis by means of the in-betweening method. It is clarified that individual facial features can be enforced by emotional motion deformation in caricaturing.

Estimation of human motion from multiple cameras for gesture recognition

We have been researching human sensing technologies based on computer vision for the realization of the Percept-Room as an intelligent environment. This room offers several services such as the control of electrical appliances by use of gestures. A more caring technology is strongly, expected for providing more human-friendly interfaces. As a first step, the recognition of human motion in the Percept-Room is an important task. We propose a method for extracting humans and then hand gestures from multichannel motion images captured in the Percept-Room. The human position and the rising hand gestures are estimated by integrating the silhouettes from multiple cameras by a background image subtraction and a frame subtraction. We describe the proposed methods and the experimental results obtained by use of a PC system implemented in the Percept-Room.

An interactive facial caricaturing system based on the gaze direction of gallery

We propose a dynamic and interactive caricaturing system. In our system, the utilization of in-between method realizes the generation mechanism from the caricaturist to the gallery, and on the contrary, the utilization of eye-camera vision realizes the feedback mechanism from the gallery to the caricaturist. The gallery mounts an eye-camera on the head, and the system reflects visual characteristics of the gallery directly onto the works of facial caricature. After observing the image of the model and analyzing the gaze direction and distribution, the system deforms some of the characteristic and impressive facial parts more strongly than other non-impressive facial parts, and generates the caricature which is suited especially for the gallery. In this paper, we demonstrate experimentally the effectiveness of this method to integrate these kinds of viewpoints.

Dynamic facial caricaturing system based on the gaze direction of gallery

Facial caricaturing is a representation process of human visual impression onto paper or other media. Facial caricaturing should be discussed from multiple viewpoints of three relations among the model, the caricaturist and the gallery. Furthermore, some kinds of interactive mechanism should be required between the caricaturist and the gallery. We propose a dynamic caricaturing system. In our system the utilization of an in-betweening method realizes the generation mechanism from the caricaturist to the gallery, and on the contrary, the utilization of eye-camera vision realizes the feedback mechanism from the gallery to the caricaturist. This is an original and unique point of our system. The gallery mounts an eye-camera on the head, and the system reflects visual characteristics of the gallery directly onto the works of facial caricature. After observing the image of the model and analyzing the gaze direction and distribution, the system deforms some characteristic and impressive facial parts more strongly than other non-impressive facial parts, and generates the caricature which is suited especially for the gallery. We demonstrate experimentally the effectivity of this method to integrate these kinds of viewpoints.

Realization of an efficient line detection by askant glance camera vision system using extended Hough transform

We propose a new vision mechanism which can saccadicly move its fixation point for detecting straight lines within the image frame. This system, askant glance camera vision (AGCV) system, can extract straight lines precisely around the fixation point and rather coarsely at the periphery of the fixation point. This camera system works in such a way that the fixation point catches the moving object by the information of the center of gravity of edges, and the edges of the moving object can be extracted better than the edges of the stationary object. This system demonstrates a model of the center fine/peripheral-coarse characteristics of human vision. This system is constructed by a slab-system which uses extended Hough transform functions and another subsystem which tracks an object and shifts its fixation point to the center of gravity. In this paper, we show some experimental results to show the performance of AGCV system.

Re-generation of facial image eye-contacting with partner on TV conference environment

We have been developing a method for recognition of facial parts such as eyes, nose, mouth, etc. The paper concentrates on eye (iris) recognition using a Hough transform. Based on this iris recognition, the paper proposes a basic idea and method for re-generating a facial image which is making eye-contact with a partner in a TV conference environment. We propose a new methodology for realizing a natural human interface of face-to-face communication in a TV conference environment. Since a human is likely to look at the face of her partner on a TV monitor and not at the TV camera, she will usually fail to send her own eye-contacted facial images. The basic idea of the paper is to solve this unfortunate communication degradation by regenerating a facial image by changing the direction of the irises in the same original facial image. The proposed methods and experimental results are presented to demonstrate the effectiveness. Future problems include improving the regeneration method of irises, introducing a real time processing method, coping with the motion of the head, and finally proposing a new eye-camera system which could reduce the constraints caused by head mounted goggles. This new method of eye-camera is also introduced.