Toshinori Yamasaki

A new data tablet system for handwriting characters and drawing based on the image processing

This paper describes the new input system for data tablet based on the observation of handwriting by CCD camera. The system takes the pen movement on the writing plane with 64 gray level sequential images. As the system needs 0.25 sec. for one frame image, we can observe the slow handwriting by this system. The CCD camera takes the sequential images written on the writing pad with a 50/spl times/50 mm frame. After that, the system can extract the online stroke data, that is, the sequential position coordinates from the sequential input images. We can perform the style of the data tablet without sensor table and wired stylus pen. This system is useful for a new data tablet based human friendly input device.

Distance based vector field method for feature extraction of characters and figures

A new method is proposed for feature extraction and representation of character and figure patterns using a vector field. The vector field is constructed from a distance transformation like the gradient vector of the electric field caused by a charged pattern. Features are defined by a set of the source points, sink points, and locally homogeneous domains of the vector field. It is shown that these features are effective for detecting holes (loops) and directional segments of the input pattern. The pattern and the frame can be segmented naturally and the segmentation represents the juxtapositional relation among the locally homogeneous domains of flow-out vectors from the pattern. The authors discuss the relation between the distance transformation that the vector field is based on and scale-space filtering which can be regarded as a kind of diffusion and/or blurring processing of the shape of pattern.<<ETX>>

Japanese learning system for Chinese native speakers - development of database for learning Kanji which have difference between Chinese and Japanese

Although native speakers of Chinese have basic knowledge of Kanji (Chinese characters), learning Kanji is hard task to them. The difficulties of Kanji learning for Chinese speakers are different from those for non-Chinese character area learners. They are, for example, influenced by Chinese to their uses of Japanese, plural readings of each Kanji, and Kanjis different form (Ijitai in Japanese). Therefore, it is important for Chinese speakers to learn Kanji focusing on them. In this research, we develop a Kanji database that stores reading, meaning, letter shape and education level of Kanji and their compounds in order to implement Kanji and Japanese language learning systems for Chinese speakers.

Characters recognition method based on vector field and simple linear regression model

In order to obtain a low computational cost method (or rough classification) for automatic handwritten character recognition, the paper proposes a combined system of two feature representation methods based on a vector field: an autocorrelation matrix; a low frequency Fourier expansion. In each method, the similarity is defined as a weighted sum of the squared values of the inner product between the input pattern feature vectors and the reference pattern ones that are normalized eigenvectors of a KL (Karhunen-Loeve) expansion. The paper also describes a way of deciding the weight coefficients using a simple linear regression model, and shows the effectiveness of the proposed method by illustrating some experimental results for 3036 categories of handwritten Japanese characters.

VR-based interactive learning environment for power plant operator

This paper presents a VR-based ILE, which integrates virtual reality (VR) technology into interactive learning environment (ILE). It is said that ILE is composed of intelligent tutoring system (ITS) and micro world. ILE supports a students discovery learning activity and fosters his/her creativity and adaptability. Moreover, we integrate VR technology into ILE and build discovery learning environments with reality. Using VR-based ILE, it is possible for a student to relate knowledge to skills and to acquire both of them. A student gains confidence and experience with reality. We apply the VR-based ILE to a training system to power plant operators.

Forming square-styled brush-written Kanji through calligraphic skill knowledge

We propose a computer formation of brush-written Kanji characters for a brush writing training system using calligraphic knowledge. The style of brush handwriting depends mainly on the way of using a writing brush. Brush writing skills include the direction of the brush at the beginning, curvature and turning the brush, and the brush-up at the termination point in a stroke. We revise the calligraphic knowledge base according to the above mentioned brush writing skills. For simulating real brush movement, we represent the brush contact form that is the brush shape on the writing plane as a brush-touch. The system can control the size and direction of this brush-touch during the brush simulation. The system simulates the real brush writing to move the brush-touch along the skeleton letter shape in the standard database. We can get the brush written Kanji from the locus of the brush-touch movement. This system is also useful for students learning how to write Japanese letters beautifully with a brush.

Operation-style answering in multimedia testing system DrilLs-M for Kanji letter shape learning

There are some practical Web-based testing systems and drill type CAI with multimedia questioning. Many of these systems do not adapt adequate answering methods for multimedia materials. In this research, we propose a uniform model of multimedia questioning and its description form. And we develop DrilLs-M: multimedia testing system with operation style answering. It enables some natural user actions as answering, such as, designation of areas and drawing lines with a mouse and pen tablet. It supports experiential learning effectively. We introduce suitable answering methods and various practical examples for some learning items of Kanji letter shape.

Development of virtual learning environment for discovery learning in school education

This paper focuses on learning which emphasizes experience among discovery learning schemes. Knowledge gained by experience is clearly stable compared with learning acquired by simple symbol manipulations. Thus, realizing a learning environment supporting discovery learning using virtual reality (VR) technology is attempted. The VR technology has many characteristic functions and can provide an interactive learning environment with a high degree of freedom which is required in supporting discovery learning which relies on experience. In this paper, considering applications to curriculum education, in which discovery learning is performed frequently, a framework of a virtual learning environment (VLE), which is a learning environment, integrating the functions of a VR environment and an ITS environment is proposed.

Computer calligraphy-brush written Kanji formation based on the brush-touch movement

Concerns a CAI system to teach calligraphy. We developed the computer calligraphy, that is, a computer formation of brush-written Kanji characters using calligraphic knowledge. The style of brush handwriting depends mainly on the way of using a writing brush. Brush writing skills include the direction of brush at the beginning, curvature and turning the brush, the brush-up at the termination point in a stroke. We revise the calligraphic knowledge base according to the above mentioned brush writing skills. For simulating real brush movement, we represent the brush contact form that is the brush shape on the writing plane as a brush-touch. The system can control the size and direction of this brush-touch during the brush simulation. The system simulates the real brush writing to move the brush-touch along the skeleton letter shape in the standard database. We can get the brush written Kanji from the locus of the brush-touch movement. This system is also useful for students learning how to write Japanese letters beautifully with brush.

LEGO Robot Programming Exercise Support for Problem Solving Learning with Game Strategy Planning Tools

In an introduction to C programming exercise, it is important for college students to promote their interest and motivation. The goal of programming exercise is to obtain the skill for problem solving by algorithmic thinking and program implementation. A teacher must give them attractive and concrete subjects. Robot contest and group collaboration is one of the suitable styles for the purpose. We propose a game programming exercise using a simple robot kit LEGO Mindstorms. We are developing support environment GoalPost. In this paper, we introduce a framework of group programming exercise as a competition event with game-like problems for LEGO robot. Students learn to design their game strategy and realize it as an effective program. We discuss the four support levels of strategy design based on stepwise refinement. We offer support tools corresponding to visual representation product for each level. The aim of our research is to improve applicative ability and challenging activity of students through group works for the goal.