• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.10
• /
• pp.2650-2662
• /
• 2012

Due to the semantic gap issue, the performance of automatic image annotation is still far from satisfactory. Active learning approaches provide a possible solution to cope with this problem by selecting most effective samples to ask users to label for training. One of the key research points in active learning is how to select the most effective samples. In this paper, we propose a novel active learning approach based on sparse graph. Comparing with the existing active learning approaches, the proposed method selects the samples based on two criteria: uncertainty and representativeness. The representativeness indicates the contribution of a sample's label propagating to the other samples, while the existing approaches did not take the representativeness into consideration. Extensive experiments show that bringing the representativeness criterion into the sample selection process can significantly improve the active learning effectiveness.

• Journal of the Korea Society of Computer and Information
• /
• v.5 no.3
• /
• pp.99-105
• /
• 2000

Video has become an important element of multimedia computing and communication environments, with applications as varied as broadcasting, education, publishing, and military intelligence. The necessity of the efficient methods for multimedia data retrieval is increasing more and more on account of various large scale multimedia applications. According1y, the retrieval and representation of video data becomes one of the main research issues in video database. As for the representation of the video data there have been mainly two approaches: (1) content-based video retrieval, and (2) annotation-based video retrieval This paper designs and implements a video retrieval system for using semantic-based annotation.

• The KIPS Transactions:PartB
• /
• v.13B no.1 s.104
• /
• pp.63-70
• /
• 2006

In general, a corpus contains lots of linguistic information and is widely used in the field of natural language processing and computational linguistics. The creation of such the corpus, however, is an expensive, labor-intensive and time-consuming work. To alleviate this problem, annotation tools to build corpora with much linguistic information is indispensable. In this paper, we design and implement an annotation tool for establishing a Korean dependency tree-tagged corpus. The most ideal way is to fully automatically create the corpus without annotators' interventions, but as a matter of fact, it is impossible. The proposed tool is semi-automatic like most other annotation tools and is designed to edit errors, which are generated by basic analyzers like part-of-speech tagger and (partial) parser. We also design it to avoid repetitive works while editing the errors and to use it easily and friendly. Using the proposed annotation tool, 10,000 Korean sentences containing over 20 words are annotated with dependency structures. For 2 months, eight annotators have worked every 4 hours a day. We are confident that we can have accurate and consistent annotations as well as reduced labor and time.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04a
• /
• pp.616-618
• /
• 2004

모바일 디바이스가 널리 사용됨에 따라 이를 통한 웹 컨텐츠의 이용이 증가하고 있다. 그러나 모바일 디바이스를 통하여 기존의 웹 컨텐츠를 이용하는 데에는 한계가 있다. 본 논문에서는 CC/PP 프로파일에 따라 웹 문서를 적절히 가공하여 전송하는 트랜스코딩 방법을 제안한다. 제안된 방법은 보다 정교한 수준의 맞춤형 서비스를 지원하기 위하여 원본 문서에 애노테이션(annotation)을 기술할 수 있는 방법을 지원한다. 제안된 애노테이션은 모바일 디바이스에서 표시할 수 없는 컨텐츠를 임의의 리소스로 대체할 수 있다. 또한 제안된 방법은 디바이스의 스크린 사이즈를 고려하여 컨텐츠를 적절한 크기로 나누어 보여주며, 문서의 구조를 효과적으로 전달하기 위한 내비게이션 맵을 제공한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2010.07a
• /
• pp.151-152
• /
• 2010

WWW images locate in structural, networking documents, so the importance of a word can be indicated by its location, frequency. There are two patterns for multi-cues ingegration annotation. The multi-cues integration algorithm shows initial promise as an indicator of semantic keyphrases of the web images. The latent semantic automatic keyphrase extraction that causes the improvement with the usage of multi-cues is expected to be preferable.

• Journal of Korean Medical classics
• /
• v.31 no.2
• /
• pp.17-47
• /
• 2018

Objectives: The three nations of far Northeastern Asia, namely China, Korea, and Japan, have developed a tradition of Asian medicine within a common cultural realm. Studying Japan's Yunqi not only helps our understanding of Japanese traditional medicine, but the course of development taken by the three nations' traditional Asian medicine as a whole. Methods: All books relating to Yunqi published in Japan were studied, with special focus on books that are especially more important. Results: It is assumed that Japan's first book on Yunqi is 吉田宗桂's Ungiileonjib. The Japanese mainstream study on Yunqi is the annotations and studies on Suwenrushiyungilunao, written by Liuwenshu. YunQiLunAoKouYiis the first annotation on Suwenrushiyungilunao and had the greatest impact. Yunqilunjujie is an annotation book written by a Confucian scholar, and Yunqilunaoshuchao an annotation book composed by a Confucian doctor who was a thorough expert on sinology and the annotations ranged greatly from medical books, Confucian books, historical books and hundred schools of books. Aotouyunqilun is the most slight in terms of annotations compared to other annotation books, and Yunqilunaoyanjie is special in that it writes with both Chinese characters and Japanese language in order to help easier understanding by the novice scholars. Conclusions: Suwenrushiyunqilunao includes astronomy, geography, delivery sound, calendar, the eight trigrams, the Twelve laws, Shier chen, Constellation of twenty eight, Thirty-six birds, and secret days, which is leading to further study in these fields. Suwenrushiyunqilunao also contains excerpts from Suwen Liujiecangxianglun to describe the algorithm of the operation of Sun and Moon, which is also leading a further study in the field.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.2
• /
• pp.49-59
• /
• 2007

This paper is about an system which can perform automatic semantic annotation to actualize "Semantic Web." Since it is impossible to tag numerous documents manually in the web, it is necessary to gather large Korean web documents as training data, and extract features by using natural language techniques and a thesaurus. After doing these, we constructed concept classifiers through the SVM (support vector machine) teaming algorithm. According to the characteristics of Korean language, morphological analysis and syntax analysis were used in this system to extract feature information. Based on these analyses, the concept code is mapped with Kadokawa thesaurus, which made it possible to map similar words and phrase to one concept code, to make training vectors. This contributed to rise the recall of our system. Results of the experiment show the system has a some possibility of semantic annotation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.8C
• /
• pp.1133-1141
• /
• 2004

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. 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 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. From experiment, the designed and implemented system showed high precision ratio in performance assessment more than 90 percents.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.361-363
• /
• 2005

본 연구에서는 온라인 다중 사용자 환경의 eBook 어노테이션 시스템 개발에서 데이터를 의미 기반으로 관리하고, 데이터에 대하여 상호 공통적인 이해를 표현하며, 그리고 데이터에 대한 무결성 검사 등을 지원하기 위해서 eBook 어노테이션 온톨로지를 구축하였다. eBook 어노테이션 테이터에 대한 상호 공통적인 이해의 표현을 위해서 한국 전자책 문서 표준인 EBKS(Electronic Book of Korea Standard)를 기반으로 구축 하였으며 구축된 온톨로지는 Conceptual Graph(CG)를 사용하여 표현하였다. 의미 기반의 처리를 위해서 본 온톨로지에서는 다국어(Multilingua) 관계를 고려하였으며 또한 오노테이션 데이터 생성 시 중요도를 표현하기 위해서 중요성 axiom을 고려했고, $NF^2$(Non-First Normal Form)에 입각하여 온톨로지를 설계함으로서 어노테이션 데이터의 검색에 활용도를 높였다. 제안된 온톨로지는 어노테이션 데이터의 재사용성을 높일 수 있고 의미 정보를 활용함으로써 eLearning, cyberclass과 같은 다중 사용자 환경에서 효과적인 협업을 가능하게 한다. 본 연구에서는 구현한 eBook annotation 시스템은 구축한 온톨로지를 사용함으로써 의미 기반의 데이터 관리가 가능하다. 또한 어노테이션 생성 시 온톨로지 구조를 모르더라도 어노테이션을 생성할 수 있는 인터페이스를 구현하였다.

• Journal of KIISE:Software and Applications
• /
• v.37 no.7
• /
• pp.548-557
• /
• 2010

In this paper, we propose a semi-automatic modeling approach of ontology to annotate VOD to realize the IPTV's intelligent searching. The ontology is made by combining partial tree that extracts hypernym, hyponym, and synonym of keywords related to a service domain from WordNet. Further, we add to the partial tree new keywords that are undefined in WordNet, such as foreign words and words written in Chinese characters. The ontology consists of two parts: generic hierarchy and specific hierarchy. The former is the semantic model of vocabularies such as keywords and contents of keywords. They are defined as classes including property restrictions in the ontology. The latter is generated using the reasoning technique by inferring contents of keywords based on the generic hierarchy. An annotation generates metadata (i.e., contents and genre) of VOD based on the specific hierarchy. The generic hierarchy can be applied to other domains, and the specific hierarchy helps modeling the ontology to fit the service domain. This approach is proved as good to generate metadata independent of any specific domain. As a result, the proposed method produced around 82% precision with 2,400 VOD annotation test data.