• Journal of Korean Institute of Industrial Engineers
• /
• v.20 no.1
• /
• pp.99-112
• /
• 1994

This paper describe the development of a systematic method of slicing solid parts based on a data structure called Sliced Profile Data Structure(SPDS). SPDS is an augmented polygon data structure that allows multiple layers of sliced profiles to be connected together. The method consists of five steps: (1) Selection of slicing directions, (2) Determination of slicing levels, (3) Creation of sliced profiles, (4) Connection of sliced profiles, and (5) Refinement. The presented method is aimed at enhancing the applicability of CSG for manufacturing by overcoming the problem of non-uniqueness and global nature. The SPDS-based method of feature extraction is suitable for recognizing broad scope of features with detailed information. The method is also suitable for identifying the global relationships among features and is capable of incorporating the context dependency of feature extraction.

• Journal of the Korean Society for Library and Information Science
• /
• v.39 no.3
• /
• pp.139-163
• /
• 2005

Various corpus-based approaches, rhetorical roles of discourse structure, and unifications of similar sentences were applied to construct the automatic Ext/Sums(extracts and summaries). Rhetorical roles of sentences like objective, method, background, result, conclusion, etc. for making elastic Ext/Sums were established and extraction engines according to respective role were prepared. The $90\%$ of Success rate in extracting the important sentences of sample articles was accomplished. Rearranging the selected sentences, it used unification of similar sentences using the cosine coefficient equation, deletion of unnecessary modification and insertion clauses, junction of short sentences, and connection of sentences able to link. They suggest the methods applying rhetorical roles of sentences, meaning and signature of noun and verb in clauses, and cue words and location will be researched to construct the more effective Ext/Sums.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.6
• /
• pp.127-136
• /
• 2008

A digitized image passes by encoding, storing or transmitting to show it to users. In this process, may be users would want to see a specific region of the image. And depending on the system features or in the case that the resolution of the image is large, it will take a huge time that the image show to the users. In this time, it will be resonable that the part users want to see shows earlier and afterward the other parts show. For this, JPEG2000 standards provide ROI. Although ROI extraction that users specify ROI arbitrarily is the best, people not always participate in doing all the images. There needs an automatic ROI extracting and storing in some images. JPEG2000 should extract and send an ROI automatically when the images is encoded without ROI. This study proposes a method that automatically extracts an ROI, makes the ROI masks, transfers the masked image preferentially and the background. And the study compares and experiments the proposed method and the method not having ROI.

• Spatial Information Research
• /
• v.16 no.2
• /
• pp.193-206
• /
• 2008

If stereo images is used for Digital Elevation Model (DEM) generation, a DEM is generally made by matching left image against right image from stereo images. In stereo matching, tie-points are used as initial match candidate points. The number and distribution of tie-points influence the matching result. DEM made from matching result has errors such as holes, peaks, etc. These errors are usually interpolated by neighbored pixel values. In this paper, we propose the DEM generation method combined with automatic tie-points extraction using existing DEM, image pyramid, and interpolating new DEM using existing DEM for more reliable DEM. For test, we used IKONOS, QuickBird, SPOT5 stereo images and a DTED level 2 data. The test results show that the proposed method automatically makes reliable DEMs. For DEM validation, we compared heights of DEM by proposed method with height of existing DTED level 2 data. In comparison result, RMSE was under than 15 m.

• International Journal of Knowledge Content Development & Technology
• /
• v.3 no.1
• /
• pp.81-95
• /
• 2013

Through a series of precise text handling processes, including automatic extraction of information from documents with knowledge from various fields, recognition of entity names, detection of core topics, analysis of the relations between the extracted information and topics, and automatic inference of new knowledge, the most efficient knowledge base of the relevant field is created, and plans to apply these to the information knowledge management and service are the core requirements necessary for intellectualization of information. In this paper, the knowledge base, which is a necessary core resource and comprehensive technology for intellectualization of science and technology information, is described and the usability of academic information services using it is evaluated. The knowledge base proposed in this article is an amalgamation of information expression and knowledge storage, composed of identifying code systems from terms to documents, by integrating terminologies, word intelligent networks, topic networks, classification systems, and authority data.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.464-466
• /
• 2003

생명과학 관련 문서에서 자동으로 이벤트를 추출하는 것은 관련 연구자들의 연구에 많은 도움을 줄 수 있다. 본 논문에서는 생명과학 관련 문서 중 특히 효모와 관련된 문서를 대상으로 간단한 자연언어 처리 기술을 적용하여 유의미한 정보를 추출한 결과를 제시하고자 한다. 실험은 효모 관련 문서에서 고빈도의 이벤트 표현 동사에 대한 패턴 정보를 조사한 후, 패턴 정보에 의거하여 이벤트를 추출하였다. 평가 결과, 비교적 간단한 자연언어 처리 기술 안으로도 유의미한 정보들을 추출할 수 있었다.

• Proceedings of the Korean Society for Information Management Conference
• /
• 1998.08a
• /
• pp.227-230
• /
• 1998

문헌정보학분야의 용어사전을 이용한 자동시소러스 구축을 위한 첫단계로$\ulcorner$문헌정보학 용어사전$\lrcorner$ MRD를 구성하고 이를 이용하여 상위어 자동 추출알고리즘을 개발하였다. MRD구성시 전처리과정을 통하여 상위어 추출에 불필요한 정보가 수록되는 것을 방지하였다. 상위어 추출을 위한 알고리즘 개발은 무작위 표본추출을 통하여 $\ulcorner$문헌정보학 용어사전$\lrcorner$에 기술된 문장의 구문적 특성을 분석한 후, 이 구문정보를 이용하여 수행하였다. 본 연구에서 제시된 알고리즘의 효율성 평가결과 89.4%의 정확도를 보였다.

• The Journal of Information Technology and Database
• /
• v.8 no.1
• /
• pp.117-128
• /
• 2001

Recently there are many researches of text mining to find interesting patterns or association rules from mass textual documents. However, the words extracted from informal documents are tend to be irregular and there are too many general words, so if we use pre-exist method, we would have difficulty in retrieving knowledge information effectively. In this paper, we propose a new feature extraction method to classify mass documents using association rule based on unsupervised learning technique. In experiment, we show the efficiency of suggested method by extracting features and classifying of documents.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.553-555
• /
• 2000

기존의 특징점 추출 알고리즘들은 입력 지문의 전처리, 이미지의 이진화, 세선화, 특징점 추출 등의 여러 처리 단계를 거쳐 이루어지므로 잡음등과 같은 외부적 요인과 여러 처리단계엣 발생하는 내부적 요인 등으로 왜곡 현상을 피하기 어렵고 전체 인증 시간이 길어 지는 등 성능 저해 요인이 많다. 본 논문에서는 복잡한 처리 과정을 거치지 않고 입려영상에서 집적 융선의 흐름을 추적하여 특징점들을 추출하고 매칭을 수행함으로써 이미지의 왜곡에서 오는 오류를 줄이고 처리 시간을 단축하여 기존의 시스템보다 빠른 시간에 지문을 인식하는 시스템을 설계 및 구현한다.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2001.08a
• /
• pp.181-184
• /
• 2001

본 논문에서는 적합한 색인어를 자동으로 추출해 내기 위해 잘 알려진 통계적 기법과 구문분석적 기법을 혼용하였다. 적용결과를 검색효율로 나타내지 않고 각 방법에 따라 추출된 단어들을 실증적으로 보여주어 성능에 대한 판단을 유도하였다. 빈도나 품사가 단독으로 사용된 것보다 동시에 적용된 것이 보다 좋은 결과를 가져왔다.