Takuma Funahashi

Face and eye tracking for gaze analysis

We propose a system for extracting eye gaze information, and develop a couple of new human interface media by eye gaze information. For example, the observer wants to know visually how effectively the partner is interesting to him or not even on the net environment. To do this it is usually expected to utilize motion images. But, the observer wants to know exclusively facial image and gaze. So, we paid attention to face tracking from the scene and analyzed the features of eye gaze pattern extracted from the facial images by iris recognition.

Facial Media for Non-verbal Communication in Production Processes

We took the face, especially eye or eye gaze, into consideration for discussing the non-verbal interface media. We first proposed a passive eye-camera system based on the facial image processing such as Hough transform for iris recognition. Next we proposed a method for generating eye-contacted facial images by computer image processing for enforcing and improving the quality of facial, nonverbal communication on the net such as VIDEO Conference. Finally we applied these two proposed methods to the real environment of E-mail daily conference in the production process of the company, and shortly discussed on the prospects of the facial new media on the net.

Fast and robust visual inspection system for tire surface thin defect

In this paper, we propose a new visual inspection method that can analyze the exterior surface of rubber tires with the light stripe projection. Image sensing of the tire surface was implemented by setting the tire on the rotating table so that the normal pattern of the tire surface could be suppressed. The proposed method detects the exterior thin defect after removing three kinds of uneven circularities due to the real shape of tire, the eccentricity of rotating table and the inconsistency between two. Thus, in this research, we realized a visual inspection method by transforming three-dimensional shape of tire surface into two-dimensional image information through the analysis of light stripe images.

Vision-based modeling of human behavior in production process

This paper proposes a vision-based human modeling by using both analytical property of human body performance and the concurrent gaze pattern for production process. Authors 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. Authors demonstrated FCC and PEC are effective to construct the vision-based model of human behavior in production process.

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.

Development of visual inspection robot based on motion and mind behaviors of expert inspector

In this research, we developed a visual inspection robot with human consciousness of attention based on body and sight motions. This robot could inspect cast metal object that is irregular both in illumination reflection and surface structure. We capture in advance images of body and sight motions of inspector performance by using 3D motion capture system and gaze analysis system, and analyzed the images for extracting expert skill through the consciousness of attention and concentration of inspection. Based on the consciousness model of inspection, we developed an inspection robot system with a smart mechanism of camera work and ROI control and finally dynamic image processing mechanism for rough detection and precise examination of defects.

3D inspection of electronic devices by means of stereo method on single camera environment

It is very important to guarantee the quality of the industrial products by means of visual inspection. In order to reduce the soldering defect with terminal deformation and terminal burr in the manufacturing process, this paper proposes a 3D visual inspection system based on a stereo vision with single camera. It is technically noted that the base line of this single camera stereo was precisely calibrated by the image processing procedure. Also to extract the measuring point coordinates for computing disparity; the error is reduced with original algorithm. Comparing its performance with that of human inspection using industrial microscope, the proposed 3D inspection could be an alternative in precision and in processing cost. Since the practical specification in 3D precision is less than 1 pixel and the experimental performance was around the same, it was demonstrated by the proposed system that the soldering defect with terminal deformation and terminal burr in inspection, especially in 3D inspection, was decreased. In order to realize the inline inspection, this paper will suggest how the human inspection of the products could be modeled and be implemented by the computer system especially in manufacturing process.

Coarse to fine hierarchical tracking system for face recognition

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. This face tracking and face recognition system was characterized by a novel template replacement scheme among the successive image frames. Experimental results were also demonstrated in this paper. This system works well in a practical speed 6-9 fps on a usual PC connected to these cameras.

Face and facial parts tracking and its applications to nonverbal communication interface

Since, at our laboratory, 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. This face tracking and face recognition system was characterized by a novel template replacement scheme among the successive image frames. Experimental results were also demonstrated in this paper. This system works well in a practical speed 6-9fps on a usual PC connected to these cameras.

Face Tracking System with Fixed CCD and PTZ Camera

We propose a method for face tracking and for providing sufficient image resolution to recognize irises by integrating fixed CCD and PTZ(Pan-Tilt-Zoom) cameras. This system works in a practical speed about 70ms/frame. Irises are successfully recognized from the motion images from PTZ camera. These irises can be utilized to provide a key feature for realizing an automated facial caricaturing system PICASSO.