본 논문에서는 복잡한 랜덤 배경 하에서 위치하고 있는 게임 플레이어의 얼굴 영상을 스테레오 매칭을 이용하여 배경과 분리하여 추출할 수 있는 방법에 대하여 기술한다. 사람과의 상호 작용이 필요한 게임일수록 사람의 동작이나 각 부위에 대한 인식이 필요하다. 이 방법은 게임 이외에도 보안 시스템, 의류 시뮬레이션, 3D 모델링 그리고 로보틱스와 같은 분야에 적용될 수 있다. 스테레오 매칭에 관해서는 많은 연구가 있어왔으며, 기본적으로 영역기반 방법과 특징기반 방법으로 분류될 수 있다. 본 논문의 제안 방법 에서는 영역기반 방법으로 처리를 시작하고, 다단계 크기의 윈도우를 적용하여 물체의 경계선을 찾는 작업을 진행한다. 각 윈도우 크기에 대하여 유사성 커브가 생성되며, 이 값은 물체의 경계선을 판별하는 특징으로 사용된다. 전단계에서 생성된 코어스(coarse) 영역은 유사성 커브 방식에 의하여 머지 작업을 거치며, 최종적으로 대상 물체의 영상을 추출하게 된다.

PTV는 비디오 카메라로 기록된 영상의 분석을 통하여 흐름속도를 측정한다. 이러한 PTV 방법을 이용하여 유사의 침강속도를 측정하였다. 실험을 통해 측정된 정지 유체내 유사의 침강속도를 기존문헌에 제시된 값과 비교 분석한 결과, 침강속도 측정에 PTV를 이용할 수 있음이 입증되었다. 따라서 PTV를 이용하면난류흐름 중의 침강속도 측정이 가능해져 난류흐름 중의 침강속도 특성 규명에 기여할 수 있을 것이다.

In general, neural networks are widely used for the category classification of multispectral images. Since the input multispectral images into neural networks we, however, low contrast images, neural networks converge very slowly and are of bad performance. To overcome this problem, we propose a new image enhancement method which consists of smoothing process, finding the main valley and enhancement process. In addition the enhanced images by the proposed method are used as the input of neural networks for the category classification. When the new category classification method is applied to multispectral LANDSAT TM images, we verified that the neural networks converge very lastly and that the overall category classification performance is improved.

침수지에 대한 신속하고 정확한 지도의 제작은 홍수재해 복구와 관리 및 예방을 위한 중요한 자료로 사용된다. 타 위성영상에 비하여 기상조건에 관계없이 영상자료의 획득이 용이한 레이더 영상을 이용하여 침수지 조사와 홍수후의 농경지 복구 상태를 파악하고자 하였다. 1999년 여름 경기도 북부 지역에 발생한 홍수 사상을 사례지로 하여 C-band RADARSAT 위성영상을 이용하였고, 침수 시점인 8월 4일 영상과 그 전후 영상을 포함하여 세 시기의 영상을 이

The purposes of the study were to detect and evaluate the historical land use and land cover changes on the Balan watersheds from three thematic mapper (TM) data, which were taken in 1985, 1993, and 1996. The supervised and unsupervised classification methods were adopted to classify five land cover categories: Paddy, upland, forest, residential, and water. The results indicated residential areas increased significantly during the past eleven years, Forest and paddy were converted to the urban areas. Future land cover patterns were forecasted using a Markov chain method, and the simulated land coiler change ratios presented.

The automated gate operating system is developed in this paper that controls the information of container at gate in the ACT. This system can be divided into three parts and consists of container identifier recognition car plate recognition container deformation perception. We linked each system and organized efficient gate operating system. To recognize container identifier the preprocess using LSPRD(Line Scan Proper Region Detection)is performed and the identifier is recognized by using neural network MBP When car plate is recognized only car image is extracted by using color information of car and hough transform. In the port of container deformation perception firstly background is removed by using moving window. Secondly edge is detected from the image removed characters on the surface of container deformation perception firstly background is removed by using moving window. Secondly edge is detected from the image removed characters on the surface of container. Thirdly edge is fitted into line segment so that container deformation is perceived. As a results of the experiment with this algorithm superior rate of identifier recognition is shown and the car plate recognition system and container deformation perception that are applied in real-time are developed.

Chung, Sang-Hun. 1998. An Image-Schematic Analysis of Values in Linguistic Expressions. Studies in Modern Grammatical Theories 12, 225-240. The purpose of this study is to analyze some aspects of value systems reflected in linguistic expressions by means of the image-schematic approach that Mark Johnson has presented, and axiological semantics which studies values with reference to the meaning of various linguistic expressions, and whose task is to describe those values and ways in which they determine both the structure and the functioning of human language as manifested in human communication. The concepts `good` and `bad`, and Tischner`s hierarchy of values have been used. The results of the study are as follows; First, image-schemata are primarily based on human bodily experiences. Second, image-schemata which are based on different clusters of experiences are bi-polar. They have a `good` pole and a `bad` pole. Third, center, link, whole, up, front, right are regarded as `good`, while periphery, no link, part, down, back, left as `bad`. Fourth, `bad` can be defined relative to `good`. but not the reverse. Things canbe `bad` only to the extent to which they are `not good`, for the experience of `bad` comes from the experience of `lack`. Fifth, positively charged concepts are more likely to be unmarked forms, while negatively charged concepts are more likely to be marked forms.

Kim Jong-do. 1998. The Study on the Image-Schema Transformations. Studies in Modern Grammatical Theories 12, 141-168. This paper is designed to show an appropriate way to analyse polysemie phenomena by taking a process morpheme. -er as an example. And it emphnsises that their appropriate analysis could be achieved when it is based on the schemathic network categorization model. The model is thought to be able to avoid the problems posed by the traditional categorization and the prototype model. -er is thought to have there contextual meanings: agent, instrument and setting. These meanings can be connected through image-schema transformations. Three schemas which represent their respective meanings can be united through the superschema. On the other hand, the present tense is thought to be polysemous. But its polysemy is caused by transformations applied on another grammatical category aspect. In this point the present tense is not polysemous. This paper also shows that image-schma transformations work on all the grammatical levels, for they are not the superficial grammatical gimmics, but mental activities. Thus all the grammatical phenomena should be analysed ultimately on the base of cognitive activities.

Nowadays, many satellites regularly produce digital multispectral images of the earth's surface. Multispectral images may be displayed as color pictures by selecting three components for assignment to the primary colors. It is desired to enhance these images to generate a display picture that are representativde of their features. in this paper, a false color image processing algorithm is proposed for the purpose of enchancement of the multispectral images based on the human perception. The mean of each primary component is transformed to equalo. Intensity and saturation are enhanced by modified piecewise linear contrast strectching and saturation enhancement method. The proposed method has been successfully applied the LANDSAT TM image and shows good enhancement.

Mathematical morphology skeleton image processing makes many partial skeleton image planes from an original binary image. And the original binary image can be reconstructed without any distortion by summing the first partial skeleton image plane and each dilated partial skeleton image planes using the same structuring element. Especially compression effects of Elias coding to the morphological globally minimal skeleton(GMS) image, is better than that of PCX and Huffman coding. And then this paper proposes mathematical morphological GMS image processing which can be applied to a binary image transmitting for facimile and big size(bigger than 64×64 size) bitmap fonts storing in a memory.