• 한국정보과학회논문지:소프트웨어및응용
• /
• 제27권6호
• /
• pp.660-667
• /
• 2000

본 논문에서는 필기 한글 문자열 영상에 대한 단어 분리 방법을 제안한다. 제안된 방법은 gap 의 크기 정보를 사용하여 단어를 분리하는데, 이때 gap은 문자열 영상을 수직방향으로 투영한 후 흰-런 (white-run)을 찾음으로써 구할 수 있다. 문자열 영상으로부터 얻어지는 gap들의 크기를 측정한 후, 각각의 gap을 단어와 단어사이에 존재하는 gap과 문자와 문자사이에 존재하는 gap 중 하나로 분류한다. 본 논문에서는 필기 영문 문자열의 단어 분리를 위해 제안된 기존의 세 가지 거리 척도를 채택하고 군집화에 기반한 세 가지 분류방법을 적용하여 한글 문자열의 단어 분리를 위한 최적의 조합을 선정하였다. 우편봉투 상에 작성된 주소열로부터 수작업으로 추출한 305 개의 문자열 영상을 사용하여 실험한 결과 BB(bounding box) 거리를 사용하여 순차적 군집 방법을 적용하는 경우 3 순위까지의 누적 단어 분리 성공률이 88.52% 로서 가장 우수한 성능을 보여 주었다. 또한 하나의 문자열 영상에 대한 단어 분리 속도는 약 0.05초이다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권2호
• /
• pp.203-212
• /
• 2004

워터마킹은 멀티미디어 컨텐츠의 저작권을 보호하기 위한 방법이다. 이러한 미디어 중에서 텍스트 문서는 블록/줄/단어의 계층 구조와 배경/전경의 확연한 구분 같은 고유한 특성을 나타내므로, 텍스트 문서를 위한 워터마킹 알고리즘은 이러한 특성을 잘 반영하여 설계하여야 한다. 본 논문은 명암을 갖는 텍스트 문서 영상을 위한 워터마킹 알고리즘을 제안한다. 워터마크 신호는 에지 방향 히스토그램을 통해서 삽입된다. 문서 영상의 부분 영상들은 모두 유사한 성질을 갖는다는 ‘부분 영상 일관성’을 제시한다. 한글 영상, 영문 영상, 한문 문서 영상을 대상으로 부분 영상 일관성을 조사하여, 부분 영상 일관성은 언어에 무관하며 다양한 문서 영상에 적용할 수 있음을 보인다. 워터마크 신호를 삽입하기 위하여 에지방향 히스토그램을 조작하였으며 다양한 실험을 통해 알고리즘의 비 인지성과 강인성을 분석하고 평가하였다.

• 대한화장품학회지
• /
• 제28권2호
• /
• pp.58-72
• /
• 2002

원자스케일로 재료의 내부구조를 직접 관찰 가능한 고분해 투과전자현미경(HRIEM)은 재료개발을 수행하는데 있어서 아주 유력한 수단이다. HRIEM의 영상은 최근 논문에는 일반적으로 많이 등재되기 시작하였고 산업제품의 개발에도 크게 공헌하기에 이르렀다. 고분해능 HRTEM의 발달로 인해 최신의 HRTEM기종은 점 분해능이 0.1nm order에 달하고 있다. 본 논문에서는 HRTEM 영상과정과 나노 소재에 대한 HRTEM의 실질적인 응용을 논술하였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.814-816
• /
• 2003

Remote sensing allows automatic and continual spatial data acquisition. However, it is powerless to accumulate spatial data from the past. On the other hand, social and human scientists have already created rich academic descriptions of the past with fragmentary images, but without accurate geo-references. Such a legacy of information will eventually become useless, regardless of its importance or the researcher's passion. There is thus an urgent need to help assemble the lifetime research results of social scientists, so that future generations can easily access them.

• Journal of Computing Science and Engineering
• /
• 제11권1호
• /
• pp.24-31
• /
• 2017

Face-based video retrieval has become an active and important branch of intelligent video analysis. Face profiling and matching is a fundamental step and is crucial to the effectiveness of video retrieval. Although many algorithms have been developed for processing static face images, their effectiveness in face-based video retrieval is still unknown, simply because videos have different resolutions, faces vary in scale, and different lighting conditions and angles are used. In this paper, we combined content-based and semantic-based image analysis techniques, and systematically evaluated four mainstream local features to represent face images in the video retrieval task: Harris operators, SIFT and SURF descriptors, and eigenfaces. Results of ten independent runs of 10-fold cross-validation on datasets consisting of TED (Technology Entertainment Design) talk videos showed the effectiveness of our approach, where the SIFT descriptors achieved an average F-score of 0.725 in video retrieval and thus were the most effective, while the SURF descriptors were computed in 0.3 seconds per image on average and were the most efficient in most cases.

• Journal of Computing Science and Engineering
• /
• 제6권2호
• /
• pp.168-177
• /
• 2012

The search for relevant and actionable information is a key to achieving clinical and research goals in biomedicine. Biomedical information exists in different forms: as text and illustrations in journal articles and other documents, in images stored in databases, and as patients' cases in electronic health records. This paper presents ways to move beyond conventional text-based searching of these resources, by combining text and visual features in search queries and document representation. A combination of techniques and tools from the fields of natural language processing, information retrieval, and content-based image retrieval allows the development of building blocks for advanced information services. Such services enable searching by textual as well as visual queries, and retrieving documents enriched by relevant images, charts, and other illustrations from the journal literature, patient records and image databases.

• 복식문화연구
• /
• 제19권2호
• /
• pp.316-323
• /
• 2011

This research aim concerns questioning how we can generate environments suggestive of nature fused with built environments through textiles. Through literature reviews and experiments with available the 3D imaging techniques of Holography, Lenticular and other new technologies. We also have researched towards finding the most effective method for 3D imaging techniques for textile applications. The advantage of the combining technique is to create the possibility of seeing a number of different floating 3D illusory images, depending on the viewing angle. This objective is to produce intriguing textile patterns and images in which the objects and colours change as viewpoints change. Experimental work was carried out in collaboration with professional textile researchers, scientists, artists and designers conducting research in this field.

• Journal of Computing Science and Engineering
• /
• 제4권4호
• /
• pp.350-367
• /
• 2010

Microarray technology is an interdisciplinary technique that promises a revolutionary progress toward better health and improved quality of life. The paper focuses on the development of an efficient software package, equipped with already well-known methods; also some new methods are proposed that will allow the processing and analysis of thousands of genes on microarray images. The microarray analysis software package (called SmartArray), newly proposed in this paper verifies, through microarray analysis, dramatic changes in the mRNA, protein, and activity level in the rat retina during light deprivation, which have been demonstrated in previous biological experiments. The analysis results demonstrate that SmartArray can successfully find many changes in gene expression levels in each subarray and classify them according to their significance.

• Journal of Computing Science and Engineering
• /
• 제8권3호
• /
• pp.149-156
• /
• 2014

Skeletonization is a morphological operation that transforms an original object into a subset, which is called a 'skeleton'. Skeletonization has been intensively studied for decades and is a challenging issue especially for special target objects. This paper proposes a novel approach to the skeletonization of text images based on stroke width detection. First, the preliminary skeleton is detected by using a Canny edge detector with a Tensor Voting framework. Second, the preliminary skeleton is smoothed, and junction points are connected by interpolation compensation. Experimental results show the validity of the proposed approach.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1998년도 가을 학술발표논문집 Vol.25 No.2 (2)
• /
• pp.297-299
• /
• 1998

As there comes out better and better solutions for delivering multimedia data on the internet, the number of WebCAM sites which transmits pictures of any spot to the user's system is getting increased. WebCAM service over the internet can be compared with the CATV in that it is beyond the spatial constraints. In this project, we construct a WebCAM site Which performs not only the fundamental WebCAM functions of capturing images and of transmitting them periodically but also various kinds of modules carrying out tasks such as image processing, remote control of the camera, processing multiple user requests, making panorama views and so on using Java which is the most popular language for the internet or CGI. The past images are stored in a database implemented for the WebCAM system, so the system can be extended to get over the constraints in time also.