Search

This paper considers the unsupervised classification of handwritten character strokes in regards to speed, since handwritten strokes prove challenging with their high and variable dimensions for classification problems. Our approach employs a robust feature detection method for brief classification. The dimension is reduced by selecting feature points among all the points within strokes, and thus the need to compare stroke signals between two different dimensions is eliminated. Although there are some remaining problems with misclassification, we safely classify strokes according to handwriting styles through a refinement procedure. This paper illustrates that the equalization problem, the severe difference in small parts between two strokes, can be ignored by summing all of the differences via our method.

This manuscript introduces a fault diagnosis system for a turbine-governor system that is an important control system in a nuclear power plant. Because the turbine governor system is operated by high oil pressure, it is very difficult to maintain the operating condition properly. The turbine valves in the turbine governor system supply an oil pressure for operation. Using the pressure change data of the turbine valves, the condition of the turbine governor control system is evaluated. This study uses fuzzy logic and neural networks to evaluate the performance of the turbine governor. The pressure data of the turbine governor and stop valves is used in the turbine governor diagnosis algorithms. The features of the pressure signals are defined to be applied in the fuzzy diagnosis system. And Fourier transformed signals of the pressure signals are used in the neural network models for diagnosis. The diagnosis results both by fuzzy logic and neural networks are compared to evaluated the performance of the designed system.

As the amount of visual information is rapidly increasing, users want to find the more semantic information easily. Most retrieval systems by lowlevel features(such as color, texture) could not satisfy user's demand. To interpret semantic of image, many researchers use keywords as textual annotation. However, it's the image retrieval without ranking by text matching which is the simplest way to retrieval according to keyword's existence or nonexistence. In this paper, we propose conceptualization by similarity measure using relations among keywords for efficient image retrieval. We experiment annotated image retrieval by lowering the unrelated keyword's weight value and raising important keyword's one.

In spite of the importance of natural drawing with input device, the interface between the device and virtual brush's status has been dealt less in literatures. Through this paper, we present a natural interface between pen-tablet device and virtual brush. Proposed system uses pressure instead of z-coordinate of pen to allow drawing with the similar feeling to the real brush. The contribution of this paper is as follows: first, a brush model interacting with pressure is generated. Second, 3D brush model is allowed to be folded back decreasing droplet size intensively according to pen direction changes.

The learning of Chinese characters is important in the writing of Japanese text. However, current instruction in Chinese characters is ineffective due to insufficient time given to learning of characters, particularly at the elementary school level. The study of stroke orders by “Nazori” or “Rinnsyo” in Japanese is difficult for elementary or foreign students who are exposed to Chinese characters for the first time. In the present study, a system that displays the order of strokes by animation is presented. Since the system is able to display animation and a character that can be inputted interactively, a teacher’s instructive by OHP, video, etc., is automated, and auxiliary usefulness can be expanded. The system not only directs the order of strokes by animation, but it also indicates a wrong order of strokes by a stroke correspondence relation table, which ensures the correct order of stroke orders to be directed. A novel instruction method is proposed which directs letter-shape by using inter-stroke information, such as the relative position and relation among strokes. In this system, a letter-shape can be corrected by using inter-stroke information, and detailed instructions are realized.

This paper reports on a compression method for a reference character dictionary used for on-line Chinese handwriting character recognition, which is based on pattern matching between input and reference patterns. First, one reference pattern for each category is generated from the training data. Second, the reference dictionary is optimized by using the Generalized Learning Vector Quantization (GLVQ) algorithm. Third, the reference dictionaries are compressed to approximately one tenth of the original data using Vector Quantization with the K-means clustering algorithm. Then, the compressed reference dictionaries are again optimized by the GLVQ algorithm. Experimental results for Chinese character recognition show that the dictionary can be successfully compressed without decreasing the recognition rate, and the calculation time of distance between strokes can be reduced by a factor of approximately five.

For the purpose of improvement in computational time and recognition accuracy in the framework of stroke order- and number-free on-line handwriting character recognition, we performed structural analysis of the style of stroke order and stroke connection. From the real handwritten characters, chosen from among 2965 Chinese characters, we investigated the information on stroke order and connection, using the automatic stroke correspondence system. it was proved that the majority of real characters are written in fixed stroke order, and stroke order is predominantly in the standard stroke order; about 98.1% of characters were incated nearly in the standard order. Almost all stroke connections occur in the standard order (92.8 %), whereas 2 stroke connections occurred often, and stroke connections in nonstandard order occurred very rarely. in a comparison of our findings with the expected stroke connections, very few connections were found to actually occur. Moreover, we show the methods for incorprating the information on the completely stroke order- and number-free framework. The large improvement on both computational time and recognition accuracy are demonstrated by experiments.