• ETRI Journal
• /
• 제32권5호
• /
• pp.729-739
• /
• 2010

Due to the rapid development of mobile devices equipped with cameras, instant translation of any text seen in any context is possible. Mobile devices can serve as a translation tool by recognizing the texts presented in the captured scenes. Images captured by cameras will embed more external or unwanted effects which need not to be considered in traditional optical character recognition (OCR). In this paper, we segment a text image captured by mobile devices into individual single characters to facilitate OCR kernel processing. Before proceeding with character segmentation, text detection and text line construction need to be performed in advance. A novel character segmentation method which integrates touched character filters is employed on text images captured by cameras. In addition, periphery features are extracted from the segmented images of touched characters and fed as inputs to support vector machines to calculate the confident values. In our experiment, the accuracy rate of the proposed character segmentation system is 94.90%, which demonstrates the effectiveness of the proposed method.

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 2007년도 춘계학술대회
• /
• pp.48-52
• /
• 2007

As huge amount of literature including biological data is being generated after post genome era, it becomes difficult for researcher to find useful knowledge from the biological databases. Bio-text mining and related natural language processing technique are the key issues in the intelligent knowledge retrieval from the biological databases. We propose a bio-text mining technique for the biologists who find Knowledge from the huge literature. At first, web robot is used to extract and transform related literature from remote databases. To improve retrieval speed, we generate an inverted file for keywords in the literature. Then, text mining system is used for extracting given knowledge patterns and keywords. Finally, we construct a grid computing environment to guarantee processing speed in the text mining even for huge literature databases. In the real experiment for 10,000 bio-literatures, the system shows 95% precision and 98% recall.

• 한국통신학회논문지
• /
• 제42권2호
• /
• pp.493-504
• /
• 2017

최근 뉴스, 블로그, 소셜미디어 등을 통해 방대한 양의 비정형 텍스트 데이터가 쏟아져 나오고 있다. 이러한 비정형 텍스트 데이터는 풍부한 정보 및 의견을 거의 실시간으로 반영하고 있다는 측면에서 그 활용도가 매우 높아, 학계는 물론 산업계에서도 분석 수요가 증가하고 있다. 하지만 텍스트 데이터의 유용성이 증가함과 동시에 이러한 텍스트 데이터를 왜곡하여 특정 목적을 달성하려는 시도도 늘어나고 있다. 이러한 스팸성 텍스트 데이터의 증가는 방대한 정보 가운데 필요한 정보를 획득하는 일을 더욱 어렵게 만드는 것은 물론, 정보 자체 및 정보 제공 매체에 대한 신뢰도를 떨어뜨리는 현상을 초래하게 된다. 따라서 원본 데이터로부터 스팸성 데이터를 식별하여 제거함으로써, 정보의 신뢰성 및 분석 결과의 품질을 제고하기 위한 노력이 반드시 필요하다. 이러한 목적으로 스팸을 식별하기 위한 연구가 오피니언 스팸 탐지, 스팸 이메일 검출, 웹 스팸 탐지 등의 분야에서 매우 활발하게 수행되었다. 본 연구에서는 스팸 식별을 위한 기존의 연구 동향을 자세히 소개하고, 블로그 정보의 신뢰성 향상을 위한 방안 중 하나로 블로그의 스팸 태그를 식별하기 위한 방안을 제안한다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2000년도 가을 학술발표논문집 Vol.27 No.2 (2)
• /
• pp.72-74
• /
• 2000

인터넷을 효과적으로 검색하기 위하여 검색엔진을 많이 이용하고 있다. 그런데 문서의 키워드를 추출할 적에 지금까지는 Anchor Text를 염두에 두지 않았었다. Anchor Text는 사람이 직접 요약한 것이고(요약성), 하이퍼링크를 포함하는 웹 문서에 반드시 존재하므로(보편성) 그 하이퍼링크가 가리키는 곳의 문서의 키워드를 추출에 적합한 용도가 될 수 있다. 웹 그래프는 이러한 Anchor Text를 이용하여 키워드를 추출함으로써 문서와 문서간, 단어와 단어간의 관계(연관성)까지도 나타내 줄 수 있게 한 검색 엔진 시스템이다. 그러나 Anchor Text 자체가 본문의 내용이 아니고, Anchor Text를 작성한 사람에 따라 다르게 작성되며, 본문의 내용과 무관한 내용도 작성할 수 있다. 따라서 Anchor Text 자체를 어떠한 여과 없이 문서의 키워드로 받아들이긴 힘들다. 본 논문에서는 TFIDF를 통해 좀 더 정확성이 있는 키워드를 추출하였다.

• 산업경영시스템학회지
• /
• 제41권4호
• /
• pp.131-137
• /
• 2018

People write reviews of numerous products or services on the Internet, in their blogs or community bulletin boards. These unstructured data contain important emotions and opinions about the author's product or service, which can provide important information for future product design or marketing. However, this text-based information cannot be evaluated quantitatively, and thus they are difficult to apply to mathematical models or optimization problems for product design and improvement. Therefore, this study proposes a method to quantitatively extract user's opinion or preference about a specific product or service by utilizing a lot of text-based information existing on the Internet or online. The extracted unstructured text information is decomposed into basic unit words, and positive rate is evaluated by using existing emotional dictionaries and additional lists proposed in this study. This can be a way to effectively utilize unstructured text data, which is being generated and stored in vast quantities, in product or service design. Finally, to verify the effectiveness of the proposed method, a case study was conducted using movie review data retrieved from a portal website. By comparing the positive rates calculated by the proposed framework with user ratings for movies, a guideline on text mining based evaluation of unstructured data is provided.

• Genomics & Informatics
• /
• 제16권3호
• /
• pp.75-77
• /
• 2018

Genomics & Informatics (NLM title abbreviation: Genomics Inform) is the official journal of the Korea Genome Organization. Text corpus for this journal annotated with various levels of linguistic information would be a valuable resource as the process of information extraction requires syntactic, semantic, and higher levels of natural language processing. In this study, we publish our new corpus called GNI Corpus version 1.0, extracted and annotated from full texts of Genomics & Informatics, with NLTK (Natural Language ToolKit)-based text mining script. The preliminary version of the corpus could be used as a training and testing set of a system that serves a variety of functions for future biomedical text mining.

• 한국통신학회논문지
• /
• 제22권3호
• /
• pp.410-422
• /
• 1997

In this paper, we descried a bottom-up document structure analysis method in bilingual Korean-English document. We proposed a character segmentation method based on the layout information of connected component of each character. In many researches, a document has been analyzed into text blocks and graphics. We analyzed a document into four parts: text, table, graphic, and separator. A text is recursively subdivided into text blocks, text lines, words, and characters. To extract the character in bilingual text, we proposed a new method of word of word separation of Korean or English. Futhermore, we used a character merging and segmentation method in accordance with the properties of Hangul on the Korean word blocks. Experimental results on the various documents show that the proposed method is very effectively operated on the document structure analysis and the character segmentation.

• 디지털콘텐츠학회 논문지
• /
• 제17권4호
• /
• pp.219-226
• /
• 2016

일반 생활 속에서 우리 인간의 눈으로 정보를 인식하고 그 정보를 이용하는 것에는 한계가 없을 만큼 다양하고 방대하다. 그러나 인공지능이 발달한 현재의 기술로도, 인간의 시각 처리 능력에 비하면 턱없이 능력이 부족하다. 그럼에도 불구하고 많은 연구자들은 실생활 속에서 정보를 얻고자 하고 있고, 특히 글자로 된 정보를 인식하는데 많은 노력을 기울이고 있다. 글자를 인식하는 분야에서 일반적인 문서에서 글자를 추출하는 것은 일부 정보처리 분야에서 이용되고 있지만, 실영상에서 문자를 추출하고 인식하는 부분은 아직도 많이 부족하다. 그 이유는 실영상에서는 색깔, 크기, 방향, 공통점 등에서 다양한 특징을 갖고 있기 때문이다. 본 논문에서는 이런 다양한 환경에서 문자 영역을 추출하기 위하여 적응적 에지 강화 기반의 MSER을 적용하여 장면 텍스트 추출을 시도하고, 비교적 좋은 방법임을 실험으로 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권1호
• /
• pp.269-281
• /
• 2014

Compared to hiding information into digital image, hiding information into digital text file requires less storage space and smaller bandwidth for data transmission, and it has obvious universality and extensiveness. However, text files have low redundancy, so it is more difficult to hide information in text files. To overcome this difficulty, Wang et al. proposed a reversible information hiding scheme using left-right and up-down representations of Chinese characters, but, when the scheme is implemented, it does not provide good visual steganographic effectiveness, and the embedding and extracting processes are too complicated to be done with reasonable effort and cost. We observed that a lot of traditional and simplified Chinese characters look somewhat the same (also called lookalike), so we utilize this feature to propose a novel information hiding scheme for hiding secret data in lookalike Chinese characters. Comparing to Wang et al.'s scheme, the proposed scheme simplifies the embedding and extracting procedures significantly and improves the effectiveness of visual steganographic images. The experimental results demonstrated the advantages of our proposed scheme.

• International Journal of Contents
• /
• 제6권2호
• /
• pp.1-5
• /
• 2010

The rapid growth in communication technology has led to the development of effective ways of sharing ideas and information in the form of speech and images. Understanding this information has become an important research issue and drawn the attention of many researchers. Text in a digital image contains much important information regarding the scene. Detecting and extracting this text is a difficult task and has many challenging issues. The main challenges in extracting text from natural scene images are the variation in the font size, alignment of text, font colors, illumination changes, and reflections in the images. In this paper, we propose a connected component based method to automatically detect the text region in natural images. Since text regions in mages contain mostly repetitions of vertical strokes, we try to find a pattern of closely packed vertical edges. Once the group of edges is found, the neighboring vertical edges are connected to each other. Connected regions whose geometric features lie outside of the valid specifications are considered as outliers and eliminated. The proposed method is more effective than the existing methods for slanted or curved characters. The experimental results are given for the validation of our approach.