• The Transactions of the Korea Information Processing Society
• /
• v.7 no.8
• /
• pp.2575-2586
• /
• 2000

In this paper, we propose an algorithm which can automatically extract the road information in a map image. The proposed method extracts the road image in the complex map image. The extracted image is converted into the skeleton image by thining method. The converted image contains various problems. In order to correct these problems, after the road is classified by the number of Rutovitz-connectivity which represents the characteristic of road, those are respectively corrected according to the load characteristic. In the simulation, the proposed method has obtained good results for the various type of map images.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.675-683
• /
• 2001

In this paper, we propose the edge compensation algorithm which connects the adjacent edges without losing the information of the skeletons on the edge image. The proposed edge compensation algorithm is composed of succeeding two steps. In the first step, the uplifted image is obtained by uplifting the edge image repeatedly. The next step is to extract the edge image from the uplifted image using the skeleton extraction algorithm. Experimental results show that the proposed method connects the adjacent edges without the distortion of the original edge information compared to the traditional method.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.687-690
• /
• 1988

Algorithms that represent given pattern in the form of an ARG (Attributed relational graph) using not only structural relations but also symbolic or numerical attributes, and then recognize that pattern by graph matching process are presented in this paper. Based on definitions of pattern deformational models, algorithms that can find GPECI(Graph preserved error correcting isomorphism). SGECI(subgraph ECI) and DSECI(Double subgraph ECI) are proposed and comparisons among these algorithms are described. To be useful in performig practical tasks, efficient schemes for extraction of ARG representation fron raw image are needed. In this study, given patterns are restricted within objects having distinct skeleton, and then the information which is necessary for recognition and analysis is successfully extracted.

• Journal of the Korean Ceramic Society
• /
• v.39 no.7
• /
• pp.693-698
• /
• 2002

Reaction-Bonded Silicon Carbide (RBSC) Ceramics were fabricated which satisfies the maximum packing density of silicon carbide skeleton in the green compacts. Such a high packing density induced incomplete infiltration during reaction-sintering; forms linear void around the interface of large alpha silicon carbide powders. During reaction-sintering, the limited extraction and entrapped gas induced by residue oxide was considered to be a reason of linear void formation. In order to improve infiltration behavior in the highly packed preform, the pre-treatment methods for residue oxide removal were proposed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.531-533
• /
• 2017

본 논문에서는 퍼지 영상처리 기법을 이용하여 손뼈의 X-Ray 영상에서 손뼈의 윤곽선을 추출하는 방법을 제안한다. 제안된 방법에서는 전 처리 단계로써 감마 상관관계를 이용하여 X-Ray 영상에서 손뼈를 제외한 피부층을 제거한다. 피부층이 제거된 영상에서 손뼈를 뚜렷하게 만들기 위해 샤프닝 기법을 사용한다. 샤프닝 기법이 적용된 영상에서 손뼈의 명암대비를 선명하게 하기 위해 사다리꼴 형태의 Fuzzy Stretching 기법을 적용한다. 사다리꼴 형태의 Fuzzy Stretching 기법을 적용한 영상에서 Canny Edge 기법을 적용하여 손뼈의 윤곽선을 추출한다. 제안된 추출 방법을 20개의 실험 영상을 대상으로 실험한 결과, 16개의 실험 영상에서는 손뼈의 윤곽선이 정확히 추출되었고 4개의 실험 영상에서는 손뼈의 윤곽선이 손실된 상태로 추출되었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.01a
• /
• pp.107-108
• /
• 2016

본 논문에서는 승강기 내에서 사람과 사람 사이의 접촉되는 부분을 추출하고자 한다. 승강기에 사람이 많이 타는 경우에는 접촉 현상은 흔히 발생하지 않는다. 하지만 승강기에 사람이 한 두 명 정도 적게 타는 경우에는 종종 발생하곤 한다. 신체적 접촉을 추출하기 위한 방법은 영상을 이진으로 변환하여 이 이진영상에서 뼈대를 추출하여 접촉 여부를 판단한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.234-235
• /
• 2019

본 논문은 실사 객체를 360도 전방위에서 관찰이 가능한 3D 그래픽 모델로 변환하는 시스템에서 뼈대를 추출하는 방법을 제시한다. 각 카메라로부터 촬영된 텍스쳐 영상을 이용하여 뼈대를 추출하고, 깊이 정보로부터 얻어진 포인트 클라우드 정보를 이용하여 뼈대 정보를 정합, 보정하는 과정을 수행한다. 카메라로부터 촬영된 텍스쳐 영상에 대해 딥러닝 기술 등을 이용하여 뼈대를 획득한다. 텍스쳐 영상으로부터 획득된 뼈대 정보는 동일 위치에서 획득된 외부 파라미터를 이용하여 월드좌표계로 변환하여 공간상에 위치시킨다. 이러한 과정을 모든 카메라로부터 획득된 뼈대 정보에 동일하게 적용함으로써 모든 뼈대 정보를 공간상에 표현하여 최종적인 뼈대 정보를 추출하는 방법을 제시한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.297-299
• /
• 2020

본 논문에서는 다시점 카메라 시스템을 통해 실사기반의 3D 모델을 획득하여 모션센서와 같은 별도의 기기 없이 해당 모델에 대한 고정밀 스켈레톤 추출 기법에 대해서 제시한다. 다시점 카메라 시스템을 이용하여 생성한 3D 모델을 앞, 뒤, 좌, 우 각 위치에서의 사상 매트릭스로 사상 영상을 생성하고 딥러닝 기술을 이용하여 2D 스켈레톤을 추출한다. 그리고 사상 매트릭스의 역변환 과정을 통해 2D 스켈레톤의 삼차원 좌표를 계산하고 추가적인 후처리를 통해 고정밀 스켈레톤을 획득한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.127-133
• /
• 2021

A recent study of people physically falling focused on analyzing the motions of the falls using a recurrent neural network (RNN) and a deep learning approach to get good results from detecting 2D human poses from a single color image. In this paper, we investigate a detection method for estimating the position of the head and shoulder keypoints and the acceleration of positional change using the skeletal keypoints information extracted using PoseNet from an image obtained with a low-cost 2D RGB camera, increasing the accuracy of judgments about the falls. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion-analysis method. A public data set was used to extract human skeletal features, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than a conventional, primitive skeletal data-use method.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.28 no.3
• /
• pp.421-429
• /
• 2001

Since Non-Extraction treatment in some orthodontic case shows unstable result and unfavorable profile, extraction is selected as inevitable treatment option for the harmonious profile, facial skeleton, and the stable dentition on both arches. For the achievement of proper goal, premolars, molars, sometimes incisors or canines are selected to be extracted. The first Premolar is usually extracted for relieving the crowded dentition with which the molar relations are class I to gain stable dentition and proper profile, but often results in the depression of profile or the loss of vortical dimension. On the contrary, the extracton of the second molar helps maintaining the fullness of profile and the vertical dimension, prevents additional space closural procedures which often make the procedures complicated, relieves both anterior and posterior crowding, and substitutes the extraction fossae for newly erupting 3rd molars. From the point of recurrence, the second molar extraction procedure, therefore, is more beneficial. This cases showed the good results of second molar extraction procedures in the patients with class I crowding.