In a simulated world, a group of robots with diversified personalities performs a task where they carry several pieces of baggage to the destination. In this simulation, each robot makes a mutual concession to avoid collision and helps each other to carry some of baggage too big to be carried by one robot. Moreover, each robot makes learning the personalities of other robot in this simulation. We verify the influence that the learning the personalities exerts on the task efficiency. We give each robot three kinds of personalities; positivity, tenderness and temper. From the result, it was found that each robot has more versatile actions when each robot learns the personalities of the other robots, and the versatile actions of the robot result in better task efficiency. Thus, in this study, the learning of the others' personalities worked effectively, as in the case of biological evolution.

We propose a method for extracting the left ventricular (LV) contours from left ventriculograms by means of a neural edge detector (NED) in order to extract the contours which accord with those traced by a cardiologist. The NED is a supervised edge detector based on a modified multilayer neural network, and is trained by use of a modified back-propagation algorithm. The NED can acquire the function of a desired edge detector through training with a set of input images and the desired edges obtained from the contours traced by a cardiologist. The proposed contour-extraction method consists of 1) detection of "subjective edges" by use of the NED; 2) extraction of rough contours by use of low-pass filtering and edge enhancement; and 3) a contour-tracing method based on the contour candidates synthesized from the edges detected by the NED and the rough contours. Through experiments, it was shown that the proposed method was able to extract the contours in agreement with those traced by an experienced cardiologist, i.e., we achieved an average contour error of 6.2% for left ventriculograms at end-diastole and an average difference between the ejection fractions obtained from the manually traced contours and those obtained from the computer-extracted contours of 4.1%.

We propose a new edge enhancer based on a modified multilayer neural network, which is called a neural edge enhancer (NEE), for enhancing the desired edges clearly from noisy images. The NEE is a supervised edge enhancer: Through training with a set of input noisy images and teaching edges, the NEE acquires the function of a desired edge enhancer. The input images are synthesized from noiseless images by addition of noise. The teaching edges are made from the noiseless images by performing the desired edge enhancer. To investigate the performance, we carried out experiments to enhance edges from noisy artificial and natural images. By comparison with conventional edge enhancers, the following was demonstrated: The NEE was robust against noise, was able to enhance continuous edges from noisy images, and was superior to the conventional edge enhancers in similarity to the desired edges. To gain insight into the nonlinear kernel of the NEE, we performed analyses on the trained NEE. The results suggested that the trained NEE acquired directional gradient operators with smoothing. Furthermore, we propose a method for edge localization for the NEE. We compared the NEE, together with the proposed edge localization method, with a leading edge detector. The NEE was proven to be useful for enhancing edges from noisy images.

With the growth of multi-modal interfaces, the chance of listening to text, not reading, is increasing. In listening, it seems difficult to understand complex sentences. The authors present the results of a psychological experiment to investigate how syntactic complexity of a text affects its comprehensibility when a human listens to it. From the result, we conclude that systematically paraphrased text is easier to understand than an original text written for reading.

The detection of vehicle driving environments is necessary to secure transport facilities safe from accidents and to keep the performance smooth. The road condition is one of the most important factors toward detection of vehicle driving environments. Conventional discrimination methods for road conditions involved the use of optical or ultrasonic sensors. However, since these sensors can only provide spot information, detected results do not always reflect the spacious condition. To deal with this problem, a new algorithm that employs image analysis technology for discrimination of road conditions is proposed in this paper. In this algorithm, for discrimination of road conditions, we focused on features related to water and snow on the road, and we extracted these features by image analysis. Features related to water were extracted by the ratio of horizontal polarization image intensity to vertical polarization image intensity for each pixel. Features related to snow were extracted by texture analysis using the co-occurrence matrix. We employ a multivariate analysis to discriminate five kinds of the road conditions: "Dry," "Wet," "Slushy," "Icy" and "Snowy," on the basis of these features extracted from the road images as well as temperature. Furthermore, we conducted field tests to verify the accuracy of this algorithm and obtained favorable discrimination accuracy rate of 92.3% on the average.

Presents a fast algorithm for labeling connected components in binary images based on sequential local operations. A one-dimensional table, which memorizes label equivalences, is used for uniting equivalent labels successively during the operations in forward and backward raster directions. The proposed algorithm has a desirable characteristic: the execution time is directly proportional to the number of pixels in connected components in an image. By comparative evaluations, it has been shown that the efficiency of the proposed algorithm is superior to those of the conventional algorithms.

We discuss the uniqueness of 2-D shape recovery of a polyhedron from a single shading image. First, we analytically show that multiple convex (and concave) shape solutions usually exist for a simple polyhedron if interreflections are not considered. Then we propose a new approach to uniquely determine the concave shape solution using interreflections as a constraint. A numerical example, in which two convex shapes and two concave shapes exist for a trihedral corner, has been shown by Horn. However, it is difficult to prove the uniqueness using constraint equations. We analytically show that multiple convex (and concave) shape solutions usually exist for a pyramid using a reflectance map, if interreflection distribution is not considered. However, if interreflection distribution is used as a constraint that limits the shape solution (for a concave polyhedron), the polyhedral shape can be uniquely determined. Interreflections are used as a constraint to determine the shape solution in our approach.

This paper describes a mobile robot equipped with a real time sound localization system as well as a sonar system for obstacle detection. The sound localization method is based on a model of the precedence effect of the human auditory system to cope with echoes and reverberations. The sound localization and robot navigation experiments were conducted. The results show that the robot is capable of localizing sounding objects in a reverberant environment and approaching the objects without collisions, even when the objects were behind obstacles. Environment flexibility and error robustness of the system were discussed as well.

Many approaches have reported that knowledge-based layout recognition methods are very successful in classifying the meaningful data from document images automatically. However, these approaches are applicable to only the same kind of documents because they are based on the paradigm that specifies the structure definition information in advance so as to be able to analyze a particular class of documents intelligently. In this paper, the authors propose a method to recognize the layout structures of multi-kinds of table-form document images. For this purpose, the authors introduce a classification tree to manage the relationships among different classes of layout structures. The authors' recognition system has two modes: layout knowledge acquisition and layout structure recognition. In the layout knowledge acquisition mode, table-form document images are distinguished according to this. Classification tree and then the structure description trees which specify the logical structures of table-form documents are generated automatically. While, in the layout structure recognition mode, individual item fields in the table-form document images are extracted and classified successfully by searching the classification tree and interpreting the structure description tree.>

We propose a framework to manage interrelated tasks concurrently and successively, and address the issues of event handling and task scheduling: the event handler organizes interrelated tasks from a static point of view, and the task scheduler controls them on the basis of the dynamic behavior properties. In order to design our flexible control mechanism, we introduce the state transition graph and AND-OR graph in the event handler, whereas in the task scheduler the timestamp ordering method is applied to. Additionally, we describe the failure handling, concerning the cooperation between the event handler and task scheduler.>

The authors address visual interface and virtual manipulation for full text management. Their objective is to investigate the retrieval/reference mechanism of computer-readable full texts as if paper-form books were being manipulated directly in the real world. This mechanism is derived basically from the object-linking facility of hypersystems. Of course, the facility must be applicable to the manipulation of a great deal of electronic-formed books, like the traditional information retrieval systems, through hypersystems are suitable to only private filing applications.>

A framework of four-layer recognition processes is proposed for understanding documents, and a knowledge representation method adaptable to the understanding of table-form documents is addressed. Although Y. Nakano et al. (1986) looked upon the recognition of multi-kinds of table-form documents as an important subject from a practical point of view, they could not report any successful approach because their knowledge was based only on the physical coordinate data. In the approach presented, this recognition issue was solved, using both the classification tree based on the physical characteristics and the structure description tree based on the logical characteristics. At least, it is not so difficult to classify various kinds of documents into appropriate document classes since table-form documents are well designed on the basis of vertical and horizontal line segments. However, it is not easy in the case of the other documents because the geometric and spatial characteristics of documents are not well specified. It is necessary to investigate the application techniques for the other documents from the viewpoint of the knowledge representation.>

The main objective of document understanding is to extract and classify the meaningful data automatically from documents. Some researches, concerning this issue, have already been reported. However, these methods are not always successful because the recognition procedures analyze document images on the basis of only physical coordinate values of compositive items. This paper proposes a more advanced method based on the spatial relationships among neighboring segments of compositive items, in addition to the geometric aspects. The knowledge about documents is not a single layer, but organized as multi-level layers: knowledge about layout structures, knowledge about item sequences and knowledge about item properties. Three kinds of knowledge are not only specified hierarchically, but also interrelated mutually between the layout recognition, item recognition and character recognition procedures.>

A connectionist model which can store a sequence of various views of a 3D object is presented. The model consists of four components, each of which is realized as a network of neuron-like elements. The model can store several 3D objects in the same network in an overlapping manner. If the model is shown one view of a stored 3D object then a sequence of other views is recalled one by one. Since the storage is based on an associative matrix, the recall is possible even from an incomplete view. Instead of raw image data, a set of extracted features is stored

In tracking repetitive square waves, the latency of saccadic eye movement to a change in target position decreases as the tracking run progresses. The latency in the steady state takes its minimum value for frequencies between 0.5 and 1.0 Hz. A model is proposed to predict this behavior of the saccadic eye movement system. Forming an estimate of target motion and carrying out the optimal control based on the estimation are the main features of the model. The estimate, in particular that of the period of square waves, is assumed to be performed with some inevitable variance depending on the input frequency because of the sampled data nature of the system and the memory mechanism becoming more uncertain with increasing time. In relation to sinusoidal target motions, a similar model is suggested to explain the reduction of latency to the steady-state value soon after the onset of target motion. Further, the transfer characteristics in the steady state are obtained for both the open-loop and closed-loop systems. It turns out that in both cases the predictive controller can be approximated by a serial connection of a high-gain element and a predictive element.

It is well known that head rotation will induce eye movements known as rotational nystagmus, the slow phase of which compensates for head rotation fairly well, and the quick phase of which takes place intermittently in the opposite direction to the preceding slow phase. From both frequency and transient responses, it is confirmed that the slow phase velocity is proportional to the output of the semicircular canal, the main transducer of head rotation. The relationship between the canal output and the quick phase is also discussed. A simple model is proposed in which the quick phase and slow phase are separately generated. In cats under controlled ether anesthesia, it is found that both phases of the rotational nystagmus can be decomposed into primary and secondary components, and a new model of the vestibulo-ocular system is proposed which includes the simultaneous influence of these two components. The model is analyzed to find a condition where the summed effect of primary and secondary components of response constituting the slow phase of rotational ocular nystagmus can be made proportional to the canal output. Many simulation results are presented to demonstrate the validity of the model.