In this paper, we propose the technique classifying background area automatically by calculating the color variance in the RGB space of the picture. By this technique, the background classification robust to change of the background brightness and the background color was enabled. Moreover, we show the effectiveness of this technique by performing particle detection and verifying the result of counting. We aim at development of the particle detector which performs particle counting automatically about the “dispersion staining method” which is one of the processes of asbestos analysis. We used the pictures taken by phase contrast microscopy used for a “dispersion staining method.”

This paper presents a method for designing classifier to automate an evaluation process of protein crystallization growth states. The classifier is designed by binary decision tree and its classification sequence is decided in descending order of classification accuracy. Furthermore, for applying to automated crystallization system, some functions reducing mis-classification are appended to the classifier. The performance of this method has been evaluated by comparing classification result by using proposed method with the result by manual classification

In our current research, we are developing a holonomic mobile system which is capable of running over the step. This system realizes omni-directional motion on flat floor using special wheels and passes over non-flat ground in forward or backward direction using the passive suspension mechanism. In order to realize the high mobile performance during step climbing, it is required to reduce wheel slippage for maximizing wheel traction. This paper proposes a new plural wheel control method based on wheel slip estimation. Our key idea is estimation of wheel slippage comparing with the loads and rotation velocities of all actuated wheels, and using this result for wheel control of the vehicle for reducing wheel slippage. The controller can adjust control tractions of plural wheels when the wheel begins to slip and can improve the mobile performance of the vehicle. The performance of our proposed control scheme is experimented by computer simulations and experiments

In our current research, we are developing a holonomic mobile system which is capable of running over the step. This system realizes omni-directional motion on flat floor using special wheels and passes over non-flat ground in forward or backward direction using the passive suspension mechanism. The vehicle changes its body shape according to ground condition when it runs over the rough terrain. This paper proposes a new wheel control method according to the change of the vehicle's body shape for passing over the step. Our key idea is the modification of its kinematic model referring to the body configuration dynamically and using this model for wheel control of the vehicle. The controller can adjust the wheel control references when the vehicle passes over the rough terrain changing the body shape and can reduce the slippage and the rotation error of the wheels. The performance of our proposed method is experimented by computer simulations and experiments.

This paper proposes a technique of the extended template matching that detects the object with two-dimensional standard shape under the outdoor environment. Under the outdoor environment, the intensity distribution of the object changes variously by the change in the lighting condition and the change in the surface properties of the object. On the other hand, the conventional template matching assumes the intensity distribution of the object does not change. Therefore, it proposes the technique for evaluating plural similarities calculated with partial and whole templates by the linear discriminant function. The effectiveness of the proposed technique was confirmed by the detection experiment of the corner fitting of the container under the outdoor environment.

In recent years, several projects have advanced the research and development related to the automation of the protein crystallization process. However, the evaluation of crystallization states has not been completely automated yet. In the usual crystallization process, the researchers evaluate the crystallization growth states of the protein solution samples based on one's visual impressions and assign them a score over and over again. Then it is required to make the work more efficient. The method presented here automates such evaluations. This method attempts to categorize the individual crystallization droplet images into five classes from A to E, based on their crystallization states. The algorithm is comprised of pre-processing, feature extraction from images using texture analysis and a categorization process utilizing linear discriminant analysis. The performance of this method has been tested on our experiments using actual protein solution images.

In this study, we propose a new holonomic mobile mechanism which is capable of step-climbing. This mechanism realizes to move in any direction on the flat floor and pass over steps and slopes in one (fore and hind) direction. The vehicle equips with seven omni-directional wheels with cylindrical free rollers and a passive body axis that provides to change the shape of the body on the rough terrain. There is no need for additional actuators or sensors for the passive body axis. In our previous work, we constructed a prototype mobile mechanism and analyzed its kinematic characteristics. In this paper, we design a new control scheme and improve the mechanism for passing over the steps more stably, The performance of the prototype system is verified through experiments and computer simulations.

This paper presents a working prototype system of a novel computer-human interface, named invisible messenger. It integrates visual face detection and tracking, and speaker array signal processing. By speaker array it is possible to form acoustic focus at the arbitrary location that is measured by the face tracking. Thus the implemented system can whisper in a person's ear as if an invisible virtual messenger were standing by the person. In this paper, the authors describe both ideas behind the system and key technology for the implementation. In order to confirm the effectiveness of the system, the authors conduct experiments using it. This paper also reports the experiment. Experimental remits demonstrate the effectiveness of the proposed idea.

This paper presents a face matching method through information theoretical attention points. The attention points are selected as the points where the outputs of Gabor filters applied to the contrast-filtered image (Gabor features) have rich information. The information value of Gabor features of the certain point is used as the weight and the weighed sum of the correlations is used as the similarity measure for the matching. To cope with the scale changes of a face, several images with different scales are generated by interpolation from the input image and the best match is searched. By using the attention points given from the information theoretical point of view, the matching becomes robust under various environments. This matching method is applied to face detection of a known person and face classification. The effectiveness of the proposed method is confirmed by experiments using the face images captured over years under the different environments.

This paper presents an efficient method to detect faces from image sequences such as news or visual surveillance. To speed up the search, the prior probabilities of the face locations in the image are adaptively estimated and are used in the Ising search algorithm. The search points in the Ising search are selected depending on the estimated prior probabilities. The information obtained by the previous search points in the given image is effectively utilized through spin flip dynamics of the Ising search. If a face is found, the prior probabilities are updated with forgetting. This makes adaptation to the changes of the environment possible. The proposed search method was applied to images captured in the news. The proposed method is about 10 times faster than Ising search method without prior probabilities estimation.

Convergence of a matrix dynamics for online LDA is analyzed. Especially, stable spurious solutions are pointed out and two schemes to prevent the spurious solutions are proposed. The performance of the algorithm is confirmed by simulations of face identification.

Proposes a face detection method intended to be used for a practical intelligent environment and human-interactive robot. Face detection and recognition are very crucial for such applications. However in the real situation, it is not easy to realize the robust detecting function because position, size, and brightness of the face image are very changeable. The proposed method solves these problems by combining correlation-based pattern matching, histogram equalization, skin color extraction, and multiple scale images generation. The authors have implemented a prototype system based upon the proposed method and conducted some experiments using the system. Results support the effectiveness of the proposed idea.

A human continuously directs his eyes toward interesting points to recognize an object. Such eye movement or visual attention plays an important role in human vision. To simulate such eye movements, the paper proposes a virtual active vision head with binocular fish-eye lenses. Moving objects are detected within the wide angle of view obtained through the fish-eye lens by comparing the input image with the background image estimated by an adaptive M-estimator. The location of the moving object is used as a visual cue to achieve the saccadic eye movement. The proposed virtual active vision system was implemented on a PC cluster. Two PCs are used to capture images through the left and right fish-eye lenses and a PC with four processors is used for image processing. Real time gaze control is achieved on the proposed virtual binocular active vision system.

We present a method to narrow down the search space for scale-invariant human face detection, which uses a dynamic attention map implemented by Ising dynamics. Combining the proposed method and the scale-invariant face detection method which is based on both higher-order local autocorrelation (HLAC) features of a log-polar image and linear discriminant analysis for "face" and "not face" classification, it is shown that the "face" region in the image can be detected faster with some experiments.

This paper proposes a feature extraction method for gesture recognition, which is based on higher order local autocorrelation (HLAC) of PARCOR images. To extract dominant information from a sequence of images, we apply linear prediction coding to the sequence of pixel values and PARCOR images are constructed from the PARCOR coefficients of the sequences of the pixel values. Then HLAC features, which are inherently shift-invariant and computationally inexpensive, are extracted from the PARCOR images. Thus the proposed features become robust to changes of shift of the person's position. Experimental results of gesture recognition are shown to evaluate the performance of the proposed features.