• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.544-546
• /
• 2001

이 논문은 OCR(Optical Character Reader)로 인식된 한글 문서에서의 오인식 경향을 분석하고, 이를 이용한 한글 단어 검색 방법을 제안한다. OCR로 인식된 많은 야의 한글 문서를 기반으로 자모별 인식 빈도수를 계산하고 이를 바탕으로 초성, 중성, 중성별 인식 혼동 행렬(confusion matrix)을 구성하였다. 또한 인식 정보를 적절히 이용하기 Bayes 정리를 이용하였다. 질의어에 대한 오인식 단어의 검색 방법을 제시하고 혼동 행렬과 이 검색 방법을 바탕으로 OCR 기반 단어 검색 시스템을 구축하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10a
• /
• pp.290-292
• /
• 2000

최근 국대 인터넷 발전과 더불어 검색엔진들의 수요가 많아지고 있어 크고 작은 검색엔진들이 많이 개발되고 있다. 기존의 디지털 라이브러리에 사용되고 있는 정보 검색 엔진인 한글 MG 시스템을 웹 문서 검색에 적용하는데는 어려움이 있었다. 본 논문은 한글 MG 시스템을 기반으로 웹 사이트의 내부 문서 검색이 가능한 소형검색엔진으로 확장하는데 필요한 웹 로봇에 의한 문서 수집, 수집된 문서의 가공, 메타 데이터의 데이터베이스와, 단락 대 문서 사상, 문서 검색을 위한 질의 루틴의 수정과 웹 검색 및 시스템 관리 인터페이스에 대한 방안들을 제안하여 확장 시스템을 설계하고 구현하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.109-118
• /
• 2011

Recently, electronic documents are deployed in many areas. However, trust concerns arise owing to the fact that detecting whether an electronic document is modified or not is not an easy process. To facilitate this process, many word processors provide digital signature capabilities on themselves. However, there were not much research on the security of digital signature function of various programs including Microsoft Word and Hancom Hangul. Therefore, in this paper, we analyze the security of Microsoft Word and Hancom Hangul, and propose improvements for their digital signature schemes.

• The KIPS Transactions:PartB
• /
• v.12B no.5 s.101
• /
• pp.521-526
• /
• 2005

In this Paper, we propose a keyword spotting system as an alternative to searching system for poor quality Korean document images and compare the Proposed system with an OCR-based document retrieval system. The system is composed of character segmentation, feature extraction for the query keyword, and word-to-word matching. In the character segmentation step, we propose an effective method to remove the connectivity between adjacent characters and a character segmentation method by making the variance of character widths minimum. In the query creation step, feature vector for the query is constructed by a combination of a character model by typeface. In the matching step, word-to-word matching is applied base on a character-to-character matching. We demonstrated that the proposed keyword spotting system is more efficient than the OCR-based one to search a keyword on the Korean document images, especially when the quality of documents is quite poor and point size is small.

• Journal of Korea Society of Industrial Information Systems
• /
• v.8 no.2
• /
• pp.14-20
• /
• 2003

This paper presents a text extraction method of camera based document image. It is more difficult to recognize camera based document image in comparison with scanner based image because of segmentation problem due to variable lighting condition and versatile fonts. Both document binarization and character extraction are important processes to recognize camera based document image. After converting color image into grey level image, gray level normalization is used to extract character region independent of lighting condition and background image. Local adaptive binarization method is then used to extract character from the background after the removal of noise. In this character extraction step, the information of the horizontal and vertical projection and the connected components is used to extract character line, word region and character region. To evaluate the proposed method, we have experimented with documents mixed Hangul, English, symbols and digits of the ETRI database. An encouraging binarization and character extraction results have been obtained.

• Journal of the Korea Society of Computer and Information
• /
• v.7 no.4
• /
• pp.108-114
• /
• 2002

After automatic translation system for hangul's romanization based on the World Wide Web converting korean-word, sentence, document to Transliteration letters by applying algorithm based phonological principles. even though a user do not know the basic principles of the usage of Korean-to-Romanization notations, It refers to corresponding character table that has been currently adopted the authority's standard proposition for Korean-to-Romanization notation rule concurrently, add to make possible to convert a machinized code as well. It provides font for toggling Korean-English mode, insert-edit mode by assigning ASCII codes and Unicode are hardly used to them. This program could be made in C++ progamming language and Unified Modeling Language to implement various font. font-expanding and condensing. alternative printing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.05a
• /
• pp.718-721
• /
• 2017

Natural language processing, which is the basis of text mining, differs depending on the type of language. Especially, Hangeul, which has relatively high freedom of expression compared to other languages, has various forms of words depending on the use of ending. The part that does not change in these various forms of words is called the stem. For effective text mining, it is essential to extract words and unify various types of words. Therefore, this paper proposes an extraction algorithm for Hangul word for effective text mining of Hangul document.

• Journal of the Korea Society of Computer and Information
• /
• v.6 no.4
• /
• pp.6-11
• /
• 2001

After automatic translation system for hangul's romanization based on the World Wide Web converting korean-word. sentence, document to Transliteration letters by applying algorithm based phonological principles. even though a user do not know the basic principles of the usage of Korean-to-Romanization notations. It refers to corresponding character table that has been currently adopted the authority's standard proposition for Korean-to-Romanization notation rule concurrently, add to make possible to convert a machinized code as well. It Provides font for toggling Korean-English mode, insert-edit mode by assigning ASCII codes are hardly used to them. This program could be made in C++ programming language and Unified Modeling Language to implement various font. font-expanding and condensing, alternative printing.

• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.132-136
• /
• 1989

본 논문에서는 한국과학기술원 전산학과 인공지능연구실에서 개발하고 있는 한글 문서 인식 시스템 SILNOON을 소개한다. 본 연구는 인쇄체 한글로 작성된 문서를 자동으로 인식하여 컴퓨터 화일로 저장하고, 인식된 문서를 편집 및 수정하여 레이저 프린터를 통하여 출력할 수 있는 실용적인 한글 문서 인식 시스템의 개발을 그 목적으로 하고 있다. SILNOON 시스템은 크게 전처리, 문자 인식, 후처리 등의 세 단계로 구성되어 있다. 본 논문에서는 SILNOON 시스템의 각 구성 단계에 대하여 설명하고 개인용 컴퓨터 상에서 구현되어 있는 시제품을 가지고서 실험한 결과를 발표한다.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2008.03a
• /
• pp.813-820
• /
• 2008

We have developed inventory database program which is available in the mobile PC. The mobile PC is convenient in terms of portability, data input, modification, practicality of various program and data confirmation in site. By utilizing the inventory database program in mobile PC, we are able to complete database in site. Then, database is converted into the Hangul document and Excel worksheet. Also, based on the above procedure, effective management and utilization of inventory on cut-slope can be achieved.