• Proceedings of the KSRS Conference
• /
• 2000.04a
• /
• pp.155-160
• /
• 2000

본 논문에서는 고해상도 영상에서 건물의 경계선을 추출하기 위해 선소 추출, 선소 연결 과정을 통해 건물의 corner 점을 찾아 이들을 이용하여 건물의 내부에 존재하는 삼각형을 찾아가는 과정을 수행함으로써 Closed 된 선소, 즉 건물의 경계를 추출 할 수가 있다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.7 no.1 s.13
• /
• pp.41-52
• /
• 1999

In order to correct mismatches between neighboring digital maps, the middle line method has been widely used. However, it may result in not only a corruption of the topological consistency between the objects near to boundaries but also degeneration of accuracy. In this paper, we propose two edge-matching methods to overcome the problem of the middle line method. The first method is based on the rubber sheeting, which performs an elastic transformation for the objects located around the boundaries. The second method transforms the geometry of objects by the function of the distance from the boundary. These methods have important advantages that they preserve the topology of the original maps and improve tile accuracy, compared with the previous methods.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.6
• /
• pp.59-64
• /
• 2009

Edge detection always influenced by the noise of original image, therefore need some methods to eliminate them in advance, and the Mean Shift algorithm has the smooth function which suit for this purpose, so adopt it to fade out the unimportant information and the sensitive noise portions. Above all, we use the Canny algorithm to pick up the contour of the objects we focus on. And, take tests and get better result than the former sole Canny algorithm. This combination method of Mean Shift algorithm and Canny algorithm is suitable for the edge detection processing.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1999.11a
• /
• pp.438-442
• /
• 1999

제스처 인식은 직관적일 뿐 아니라, 몇 가지의 기본 구성요소에 의하여 코드화(code)가 용이하여, 인간과 컴퓨터의 상호작용(HCI, Human-Computer Interaction)에 있어서 폭넓게 사용되고 있다. 본 논문에서는 손의 모양이나 크기와 같은 개인차 및 조명의 변화나 배율과 같은 입력환경의 영향을 최소화하여, 특별한 초기화 과정이나 모델의 준비과정 없이도 제스처를 인식할 수 있고, 적은 계산량으로 실시간 인식이 가능한 제스처 인식 시스템의 개발을 목표로 한다. 본 논문에서는 손에 부착하는 센서나 마커 없이, CCD 카메라에 의하여 입력된 컬러영상에서, 컬러정보 및 동작정보를 이용하여 손영역을 추출하고, 추출된 손의 경계선 정보를 이용하여 경계선-중심 거리 함수를 생성했다. 그리고, 손가락의 끝 부분에서는 경계선-중심 거리가 극대점을 이룬다는 원리를 이용하여 생성된 함수의 주파수를 분석하여 극대점을 구함으로써 각각의 손가락 끝 위치를 찾고, 손의 자세를 인식하여 제스처를 인식했다. 또한 본 논문에서 제안된 제스처 인식 방법은 PC상에서 구현되어 그 유용성과 실효성이 증명되었다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.10 no.3
• /
• pp.283-293
• /
• 2008

A study of interactive ground behaviour due to tunnelling adjacent to existing piles has not been recognized well for the most geotechnical engineers so far. Because this is a very sophisticated boundary condition problem. In this study, therefore, the author has conducted both the laboratory model test and finite element analysis (FEA) to figure out such a complicated ground behaviour related to shear strain formations. Based on the model testing and FEA results, a boundary line which divides into two distinctive shear strain formations in relation to the locations of end-bearing pile tips was proposed. The author believes that the proposed boundary line may be helpful for planning the appropriate tunnel positions for avoiding damage of buildings which supported by piled-foundations in urban areas.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.10
• /
• pp.1244-1251
• /
• 1988

Edge is one of the primitive features of an image and is widely used in image classification and analysis. New edge extration methods using central moments are presented and show various characteristics according to the order of moment, definition of both random variables and probability density functions. The proposed methods use the integral of differences between local mean and pixels in the window whereas most of conventional edge operators use only differential concepts. This gives good noise immunity and extracts fine edges.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.2
• /
• pp.151-157
• /
• 1990

This paper presents a method for rapid wire frame drawing of the 3D objects represented by the CSG scheme. When the two CSG trees are combined into one, the intersection parts of the polygons constituting the object corresponds to each subtree are computed, and the boundary representation of the combined object is obtained according to the given combinational operator and stored in the root node. The boundary representation in the root node is used in the wireframe drawing of the object and later computation of boundary representation. Bezier surface is taken as one of the primitive object the scan-line algorithm is used, which subdivides each scan-line into the spans where no polygon is intersected, and renders each span with the CSG representation of the object.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.1041-1044
• /
• 2005

홍채인식 시스템에 있어서 동공 검출은 가장 먼저 이루어져아 할 전처리 과정이다. 현재 홍채인식 시스템에 있어서 사용되는 동공 검출은 영상의 모든 위치에서 원형돌출부(circular projection)를 구한 후, 경계선을 검출하여 원형의 경계 성분이 가장 강한 위치를 찾는 방법으로 연산량이 너무 많은 단점을 가지고 있다. 본 논문에서 제안하는 알고리즘은 같은 고주파성분에 해당 되더라도 경계선의Amplitude는 잡음의 경계선에 비해 그 값이 크다는 것을 이용하여, 경계선과 잡음을 구별할 수 있게 되고, 따라서 잡음 제거 성능을 기존의 방법에 비하여 상당히 향상시킨 웨이블렛 변환을 이용하여 동공의 특징을 추출할 수 있었다.

• Journal of Korea Game Society
• /
• v.20 no.2
• /
• pp.91-100
• /
• 2020

Life-and-death problem in Go is a fundamental problem to be overcome for implementing a computer Go. To solve it, an important consideration is to find out who surrounds or is surrounded between black and white players. To figure out the boundary between black and white groups, we applied an influence function and a contour tracing algorithm. We found that applying the Moore-neighbor tracing among various contour tracing algorithms can create boundaries, and also suggested the possibility of tremendously reducing the search space of a game tree.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.1
• /
• pp.79-87
• /
• 2005

This paper presents an active contour model for extracting accurate facial regions in complex environments. In the model, a contour is represented by a zero level set of level function φ, and evolved via level set partial differential equations. Then, unlike general active contours, skin color information that is represented by 2D Gaussian model is used for evolving and slopping a curve, which allows the proposed method to be robust to noise and varying pose. To assess the effectiveness of the proposed method it was tested with several natural scenes, and the results were compared with those of geodesic active contours. Experimental results demonstrate the superior performance of the proposed method.