• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2012년도 추계학술대회
• /
• pp.874-877
• /
• 2012

This paper proposes the new method based on contour following method with directional angle to segment the cell into the nuclei. The object image was the Thyroid Gland cell image that was diagnosed as normal and abnormal(two types of abnormal : follicular neoplastic cell, and papillary neoplastic cell), respectively. The nuclei were successfully diagnosed as normal and abnormal. this paper, improved method of digital image analysis required in basic medical science for diagnosis of cells was proposed. The object image was the Thyroid Gland cell image with difference of chromatin patterns. To segment the cell nucleus from background, the region segmentation algorithm by edge tracing was proposed. And feature parameter was obtained from discrete Fourier transformation of image. After construct a feature sample group of each cells, experiment of discrimination was executed with any verification cells. As a result of experiment using features proposed in this paper, get a better segmentation rate(70-90%) than previously reported papers, and this method give shape to get objectivity and fixed quantity in diagnosis of cells. The methods described in this paper be used immediately for discrimination of neoplastic cells.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권5호
• /
• pp.447-454
• /
• 2007

최근 TFT-LCD (Thin film transistor liquid crystal display)패널의 수요증가에 비례하여 공정상 발생하는 LCD 불량의 수도 증가하고 있다. LCD 불량은 배경화면과 미세한 밝기대비 차이를 가지는 패널상의 불균등한 영역으로서 크게 정형과 비정형으로 나누어지며 사람의 눈에 매끄럽지 않게 보여진다. 이러한 불량은 배경과의 대비 차이가 미세하여 기존의 임계수준 검출이나 윤곽선 검출로는 불량을 검출할 수 없다. 본 논문은 비정형 LCD 불량을 독립성분분석, 적응 임계수준 검출 그리고 왜도를 이용하여 검출하는 방법을 제시한다. 본 검출방법은 잡음이 심한 영상에 대해서도 대응력이 뛰어나며, 생산라인에서 성공적으로 적용된다.

• 정보처리학회논문지B
• /
• 제10B권6호
• /
• pp.705-710
• /
• 2003

본 연구는 동영상으로부터 내용기반 검색을 위하여 동영상의 연속된 프레임간의 영상의 내용 변화를 찾아내어 프레임의 시간정보와 번호판 프레임 영상을 통하여 얻어진 정보를 데이터베이스화하여 검색하는 시스템을 제안한다. 얻어진 동영상을 배경프레임과 처리프레임의 비교영역의 영상의 특징정보를 비교하여 원하는 프레임을 찾는다. 차량의 통과 시간과 차량의 번호판 프레임을 자동으로 추출하여 동영상을 내용과 함께 저장하여 원하는 차량의 동영상 부분을 보여주는 웹에서의 검색시스템이다. 이는 교통정보를 구축 동영상이 포함하고 있는 내용 즉 통과 차량의 정보를 제공할 수 있게 된다.

• Asian Journal of Innovation and Policy
• /
• 제9권2호
• /
• pp.164-186
• /
• 2020

It is generally known that a Science and Technology Park - as a representative example of an Innovation Cluster - produces network synergy among industry, university, research institutes, and other innovation actors in a specific area, so that it has a competitive edge over other regions in technological innovation. However, as the novel Coronavirus (COVID-19) pandemic unfolds, it has become necessary to reduce face-to-face contacts and this could lead to lesser network synergy being produced in an Innovation Cluster. With this background, this research was designed and conducted to evaluate how COVID-19 has changed the activities in Innovation Clusters and explore future development scenarios. In order to find out the changes occurring in an Innovation Cluster, a survey was conducted among the people in Science and Technology Parks. The survey result shows that people are experiencing difficulties in technological innovation and support activities, and face-to-face contacts have been reduced in the Innovation Cluster. A scenario planning sought to explore the future development of the Innovation Cluster. It suggests that the transformation into a Digital Innovation Cluster, which is less affected by physical distance, but can still maintain the effectiveness of the networks, can be the key strategy for the future Innovation Cluster.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권4호
• /
• pp.1128-1139
• /
• 2012

With the development of three-dimensional display and related technologies, depth video coding becomes a new topic and attracts great attention from industries and research institutes. Because (1) the depth video is not a sequence of images for final viewing by end users but an aid for rendering, and (2) depth video is simpler than the corresponding color video, fast algorithm for depth video is necessary and possible to reduce the computational burden of the encoder. This paper proposes a fast mode decision algorithm for depth video coding based on depth segmentation. Firstly, based on depth perception, the depth video is segmented into three regions: edge, foreground and background. Then, different mode candidates are searched to decide the encoding macroblock mode. Finally, encoding time, bit rate and video quality of virtual view of the proposed algorithm are tested. Experimental results show that the proposed algorithm save encoding time ranging from 82.49% to 93.21% with negligible quality degradation of rendered virtual view image and bit rate increment.

• 한국언어정보학회지:언어와정보
• /
• 제9권2호
• /
• pp.69-83
• /
• 2005

This paper discusses the distribution of a null complementizer C, as opposed to an overt counterpart 'that', presenting empirical support both for and against the PF-merge analysis of C proposed by Boscovic and Lasnik (2003, henceafter B&L) who in turn attribute to the proposal in Pesetsky (1992) and Halle & Marantz (1993). In Section I, as a background, I discuss B&L's proposal that a null complementizer C is a PF-affix which undergoes a PF-merger operation at the PF component. In Section 2, after a brief sketch of the distribution of a null C mostly in bare-relatives, I explore the possibility of extending B&L's analysis to accomodate the null C's in the bare-relative constructions. In Section 3, I argue that despite some empirical difficulties, B&L's analysis of a null C as a PF-affix can still be maintained, if Adverb Fronting is an operation to Spec-C position. Furthermore, I propose a rule - PF Spell-Out Constraint - to account for the C-trace (i.e. that-trace) effect in relative constructions. With the PF Spell-Out Constraint and B&L's PF-merge account, the distribution of a null C can better be analyzed.

• 제어로봇시스템학회논문지
• /
• 제17권5호
• /
• pp.490-498
• /
• 2011

In this paper, we present a two-stage vision-based approach to detect multi views of pedestrian in road scene images. The first stage is HG (Hypothesis Generation), in which potential pedestrian are hypothesized. During the hypothesis generation step, we use a vertical, horizontal edge map, and different colors between road background and pedestrian's clothes to determine the leg position of pedestrian, then a novel symmetry peaks processing is performed to define how many pedestrians is covered in one potential candidate region. Finally, the real candidate region where pedestrian exists will be constructed. The second stage is HV (Hypothesis Verification). In this stage, all hypotheses are verified by Support Vector Machine for classification, which is robust for multi views of pedestrian detection and recognition problems.

• 전자공학회논문지B
• /
• 제30B권7호
• /
• pp.92-101
• /
• 1993

This paper describes algorithms to extract license plates in vehicle images. Conventional methods perform preprocessing on the entire vehicle image to produce the edge image and binarize it. Hough transform is applied to the binary image to find horizontal and vertical lines, and the license plate area is extracted using the charateristics of license plates (the boundary information of license plates). Problems with this approach are that real-time processing is not feasible due to long processing time and that the license plate area is not extracted when lighting is irregular such as at night or when the plate boundary does not show up in the image. This research uses the gray level transition characteristics of license plates to verify the digit area by examining the digit width and the gray level difference between the background area the digit area, and then extracts the plate area by testing the distance between the verified digits. This research solves the probelm of failure in extracting the license plates due to degraded plate boundary as in the conventional methods and resolves the provlem of the time requirement by processing in real time such that practical application is possible.

• Journal of the Korean Institute of Landscape Architecture International Edition
• /
• 제2호
• /
• pp.120-129
• /
• 2004

Urban stream restoration projects can improve water quality, wildlife habitats, urban landscape, outdoor recreation spaces, and urban microclimate. The objectives of this research were to investigate temperature cooling effect of urban streams by using satellite imagery, to evaluate environmental variables related to stream cooling effect, and to estimate the cooling effect of the Cheonggye stream restoration project of Seoul, Korea. Findings of this research can be summarized as follows. First, a method of estimating temperature distribution around urban streams by using satellite imagery was developed. Scatter plots of distance from stream edges and average temperature obtained through multiple buffering were used for the estimation. Second, urban temperature cooling effect of streams was estimated by comparing background temperature and temperature of each buffer zone. Third, environmental factors affecting stream cooling effect were also identified. Fourth, the temperature cooling effect of the restoration project was estimated based on three scenarios. An estimated cooling effect based on the average cooling effect of existing tributaries showed the most significant effect; $2.0^{\circ}C$ lower than the present level at the edge of the renovated stream. It was estimated that the temperature of the same area would be $1.4^{\circ}C$ cooler than the present level if the cooling effect of the Yangjaechun was used as the bench mark But the effect would be $1.2^{\circ}C$ lower than the present level if environmental variables related to the temperature cooling effect of urban streams were used as the bench mark.

• 한국정보통신학회논문지
• /
• 제14권8호
• /
• pp.1819-1826
• /
• 2010

본 논문은 어류영상 검색을 위해 어류영상에서 어류객체를 추출하기 위한 영상분할 알고리즘을 제안하고 있다. 명암 유사도를 이용한 기존 알고리즘은 객체와 배경의 명암이 유사한 경계 영역에서 잘못된 영상분할 결과를 초래한다. 제안된 알고리즘은 대비가 약한 경계영역에 대응하기 위해 강화된 에지와 적응적 블록단위의 임계값을 사용하고, 대비가 없는 경계 영역에서 침식 혹은 단절된 객체를 개선하기 위해 가상 객체를 사용하고 있다. 모의실험 결과는 시각적으로 좋은 어류객체를 추출하는 비율이 기존 알고리즘에서는 90% 이하인 반면 제안된 알고리즘에서는 97.7%인 것을 보여주고 있다.