• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.380-389
• /
• 2007

In Korea, undoubtedly, the cancer is one of the most common reasons of death, and hepatoma is the second highest fatal cancer regardless of the gender only next to the stomach cancer In the middle and prime-aged between 40 and 60 years, the incidence of hepatoma is the highest in the world, and the death rate due to hepatoma is the highest among OECD countries. In this paper, we propose a novel method for automatic identification of hepatoma from a contrast enhanced CT images, which is used in an expert system that helps medical specialists. First, consecutive $40{\sim}50$ contrail enhanced CT images are photographed by every 5mm from the upper part of the chest, and using position information on the rib, we classify the internal area including only internal organs and the external one that consists of the rib, subcutaneous fat layers, and the background from the CT images. Then, the region of the liver is extracted from the classified internal area by using information on the intensity, the distribution of brightness, and using the regions extracted from consecutive images, we restore information on the 5 mm space occurred between the consecutive two slides tty applying a shape-based interpolation method. Lastly, using the characteristics such as the brightness and the morphology, we are able to extract the regions of hepatoma. The expert system based on our method is sufficiently competitive when it is compared with the diagnoses by specialists in the diagnostic radiology.

• Journal of KIISE:Software and Applications
• /
• v.29 no.6
• /
• pp.417-424
• /
• 2002

Automatic text categorization is a problem of assigning predefined categories to free text documents. In order to classify text documents, we have to extract good features from them. In previous researches, a text document is commonly represented by the frequency of each feature. But there is a difference between important and unimportant sentences in a text document. It has an effect on the importance of features in a text document. In this paper, we measure the importance of sentences in a text document using text summarizing techniques. A text document is represented by features with different weights according to the importance of each sentence. To verify the new method, we constructed Korean news group data set and experiment our method using it. We found that our new method gale a significant improvement over a basis system for our data sets.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.381-382
• /
• 2015

Small devices such as MLCC, sample inspection on the processing is not easy. If you can proceed with the sample inspection, the production process will be able to maximize the MLCC production efficiency. In this study, to minimize the interference of operator, and to maximize the operating efficiency of the equipment. Use image processing techniques for its extracts the position and angle of the MLCC. Implements an automatic inspection system with the high productivity.It is possible to inspect the final six MLCC devices. And once we Pick-Up to 200 Chip to check the accuracy of 98.4%. Based on the results of various studies are in progress to be expected to be applicable to the automatic inspection equipment side development of a variety of small devices.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.235-237
• /
• 2022

Video content is divided into long-form video content and short-form video content according to the length. Long form video content is created with a length of 15 minutes or longer, and all frames of the captured video are included without editing. Short-form video content can be edited to a shorter length from 1 minute to 15 minutes, and only some frames from the frames of the captured video. Due to the recent growth of the single-person broadcasting market, the demand for short-form video content to increase viewers is increasing. Therefore, there is a need for research on content editing technology for editing and generating short-form video content. This study studies the technology to create short-form videos of main scenes by capturing images, voices, and motions. Short-form videos of key scenes use a pre-trained highlight extraction model through machine learning. An automatic video editing system and method for automatically generating a highlight video is a core technology of short-form video content. Machine learning-based automatic video editing method and system research will contribute to competitive content activities by reducing the effort and cost and time invested by single creators for video editing

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.2
• /
• pp.113-121
• /
• 2011

In this paper, we proposed the method automatically to match areal feature based on similarity using spatial information. For this, we extracted candidate matching pairs intersected between two different spatial datasets, and then measured a shape similarity, which is calculated by an weight sum method of each matching criterion automatically derived from CRITIC method. In this time, matching pairs were selected when similarity is more than a threshold determined by outliers detection of adjusted boxplot from training data. After applying this method to two distinct spatial datasets: a digital topographic map and street-name address base map, we conformed that buildings were matched, that shape is similar and a large area is overlaid in visual evaluation, and F-Measure is highly 0.932 in statistical evaluation.

• The Journal of the Korea Contents Association
• /
• v.13 no.1
• /
• pp.1-8
• /
• 2013

The accuracy of a real facial recognition system can be varied according to the accuracy of the eye detection algorithm when we design and implement a semi-automatic facial recognition algorithm depending on the eye position of a database. In this paper, a fully automatic facial recognition algorithm is proposed such that Gabor and LBP features are extracted from fiducial points of a face graph which was created by using fiducial points based on the eyes, nose, mouth and border lines of a face, fitted on the face image. In this algorithm, the recognition performance could be increased because a face graph can be fitted on a face image automatically and fiducial points based LPB features are implemented with the basic Gabor features. The simulation results show that the proposed algorithm can be used in real-time recognition for more than 1,000 faces and produce good recognition performance for each data set.

• Journal of Korea Multimedia Society
• /
• v.9 no.1
• /
• pp.127-137
• /
• 2006

In order to process video data effectively, it is required that the content information of video data is loaded in database and semantic- based retrieval method can be available for various query of users. Currently existent contents-based video retrieval systems search by single method such as annotation-based or feature-based retrieval, and show low search efficiency and requires many efforts of system administrator or annotator form less perfect automatic processing. In this paper, we propose semantic-based video retrieval system which support semantic retrieval of various users by feature-based retrieval and annotation-based retrieval of massive video data. By user's fundamental query and selection of image for key frame that extracted from query, the automatic indexing agent gives the detail shape for annotation of extracted key frame. Also, key frame selected by user become query image and searches the most similar key frame through feature based retrieval method that propose. Therefore, we propose the system that can heighten retrieval efficiency of video data through semantic-based retrieval.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11a
• /
• pp.697-699
• /
• 2005

본 논문에서는 실세계 조명 정보를 표현하는 HDR(High Dynamic Range) 영상으로부터 소수의 방향성 광원을 추정하는 기법을 제안한다. 광원 추정을 위해 노출 시간을 달리한 일련의 일반 영상으로부터 실세계의 조명 정보를 선형적으로 표현할 수 있는 HDR영상을 생성한다. HDR영상의 색상 및 명도 변화를 이용하며 영역을 분할하고, 분할된 영역으로부터 명도 평균과 가중치를 이용하여 방향성 광원의 파라미터를 추출하는 방법을 제안한다. 제안된 방법의 장정은 비반복적인 기법을 사용하여 일관된 결과를 산출하여 사용자의 입력없이 자동으로 계산하는 것이다. 추정된 광원은 그래픽 하드웨어를 사용한 실시간 렌더링에 적용 가능하다. 또한 실시간 렌더링이 중요한 가상현실이나 증강현실 분야에서 가상의 오브젝트를 렌더링할 때 IBL(Image Based Lighting)등의 전역조명 효과와 유사한 사실적인 영상을 얻을 수 있다.

• Annual Conference of KIPS
• /
• 2006.05a
• /
• pp.363-366
• /
• 2006

최근 전자 상거래가 증가하면서 인터넷 경매를 통하여 물품을 거래하는 경우가 확산되고 있다. 하나 기존 인터넷 경매 시스템들은 경매 물품의 경매 가격을 판매자의 결정에만 의존하고 있어서, 판매자가 물품의 경매 시작가격, 낙찰 예상가격, 즉시 구매가격 등을 정하는데 어려움을 가지고 있었다. 이를 해결하기 위하여 과거의 경매 기록을 데이터베이스로 구축하여 이를 통하여 판매자에게 경매 가격을 제시하는 방법이 제시되었다. 그러나 여기서는 경매 물품에 따라서 경매 가격에 중요한 영향을 미치는 속성 정보와 가중치 부여에 대한 기준이 제시되지 못하여 잘못된 정보 제공으로 경매 물품의 가격이 지나치게 낮게 결정되거나 높아서 유찰되는 경우가 발생한다. 본 논문에서는 이러한 문제점을 해결하고자, 과거의 경매 기록과 인터넷 전자상거래 사이트의 가격 정보로부터 경매 가격 결정 요인과 가중치를 추출하여, 사례 구조화 과정을 통하여 사례베이스로 구축하고, 이를 적용하여 적합한 경매 가격을 자동으로 생성하여 이를 판매자에게 추천하는 시스템을 구현한다.

• Annual Conference on Human and Language Technology
• /
• 2007.10a
• /
• pp.38-45
• /
• 2007

본 연구는 키워드 기반 통합 검색의 한계를 극복하고자, 시맨틱 웹 기술의 기반인 URI가 부여된 인스턴스를 등록하고 관리하는 URI 서버를 이용하여 개체 페이지를 구성하는 방식의 통합 검색 방안을 제안한다. 키워드로 구성된 사용자 질의어와 매칭된 URI 서버 내의 인스턴스를 분석하여 최적 개체를 선정하고 단위 서비스의 동시 작업 방식으로 개체 페이지를 구성한다. 또한, 논문으로부터 자동 추출된 주제 정보를 추론을 통해 인력, 기관, 위치 등으로 전파함으로써 주제 중심의 심층적 정보 제공이 가능하다. 해외에서 실 서비스되고 있는 Citeseer, Google Scholar와의 통합 검색 결과 비교 실험을 통해 본 연구의 효용성을 실증한다.