• Annual Conference on Human and Language Technology
• /
• 2001.10d
• /
• pp.115-122
• /
• 2001

정보추출 기법을 논의할 때 핵심 역할을 차지하는 것이 추출 패턴(규칙)을 표현하는 종류와 규칙을 만들어 내는 기계학습의 방법이다. 본 논문에서는 mDTD(modified Document Type Definition)라는 새로운 추출패턴을 제안한다. mDTD는 SGML에서 사용되는 DTD를 구문과 해석 방식을 변형하여 일반적인 HTML에서의 정보추출에 활용되도록 설계하였다. 이러한 개념은 DTD가 문서에 나타나는 객체를 지정하는 역할을 하는 것을 역으로 mDTD를 이용하여 문서에 나타는 객체를 식별하는데 사용하는 것이다. mDTD 규칙을 순차기계학습으로 확장시켜서 한국어와 영어로된 인터넷 쇼핑몰 중에서 AV(Audio and Visual product) 도메인에 적용하여 실험하였다 실험 결과로 정보추출의 평균 정확도은 한국어와 영어에 대해서 각각 91.3%와 81.9%를 얻었다.

• International Journal of Internet, Broadcasting and Communication
• /
• v.6 no.1
• /
• pp.1-4
• /
• 2014

In this paper, an augmented refrigerator is proposed that presents information to increase the awareness of electric power consumption of a household fridge. The key idea is to reflect wasteful behavior on the feedback to a user, rather than mere amount of consumption or duration of opening a door of a fridge.

• Proceedings of the IEEK Conference
• /
• 2007.07a
• /
• pp.487-488
• /
• 2007

This Paper provides perceptual metrics for video quality based on properties of human visual system, and audio quality based on human audition. All metrics work without reference signals, allowing non-intrusive, in-service measurements. A simple and easy-to-learn user interface displays the metrics and saves them in popular file formats like CSV.

• Speech Sciences
• /
• v.8 no.3
• /
• pp.123-132
• /
• 2001

In recent years research on HCI technology has been very active and speech recognition is being used as its typical method. Its recognition, however, is deteriorated with the increase of surrounding noise. To solve this problem, studies concerning the multimodal HCI are being briskly made. This paper describes automated lipreading for bimodal speech recognition on the basis of image- and speech information. It employs audio-visual DB containing 1,074 words from 70 voice and tri-viseme as a recognition unit, and state tied HMM as a recognition model. Performance of automated recognition of 22 to 1,000 words are evaluated to achieve word recognition of 60.5% in terms of 22word recognizer.

• Journal of Information Technology Applications and Management
• /
• v.28 no.1
• /
• pp.43-51
• /
• 2021

This article explores Kim Hye-soo's film acting from the perspective of performance, which means a socio-cultural action planned and intended for a certain purpose. Through the aspect of screen performance which the identity of the era that the performance study aims for is expressed through acting and reappeared in a system of verbal and non-verbal symbols, it was intended to enhance the academic value of Korean film acting. First, Kim Hye-soo's acting performance transforms by repeating genre acting. The sensuality and sexual attractiveness that evaluates Kim Hye-soo are repeated by the typical vision required by genre films, but the acting performance is not consumed or subordinated as a tool for visual pleasure. Second, Kim Hye-soo's body, face, emotion and audio are engraved with memories of the times, and the sociocultural identity of the performance is expressed through dynamic interaction between actions and reactions. Third, Kim Hye-soo's restored and recreated performance is sensitive to the changes of the times and is still in the process.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.7C
• /
• pp.598-603
• /
• 2010

In this paper, we work for Lipreading using visual information for ship environment. Lipreading is studied for using image information including lips of a speaker at the existing speech recognition system. This technique is a compensation method to increase recognition rate decreasing remarkably in noisy circumstances. Proposed way improved the rate of recognition improving methode of preprocessing using the Gabor Filter for Ship Environment. The experiment were carried out under changing of light with time in the ship environment with lip image. For Comparing with recognition, make a compare with between method of lip region of interest (ROI) before Gabor filtering and after Gabor filtering. In the case of using method of lip ROI before Gabor filtering, the result of the experiments applying to the proposed ways recognition resulting in 44% of recognition.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.8
• /
• pp.2287-2297
• /
• 2000

Video documents which have audio-visual and other semantics information have complex relationship among media. While user requests for topic retrieval or specific region retrieval increase, it is difficult to meet these requests with the existing design methodology, In order to support the systematic management and the various retrieval capabilities of video document, we must formulate structural and systematic model on metadata using semantics and structural informations which are abstracted automaticallv or manuallv. This paper suggests generic metadata model with which we analyze the characteristics of video document, supports various query types and serves as a generic framework for video applications, we propose the generic integrated management model(GIMM)for generic metadata,, design video documents management system(VDMS) and implement it using GIMM.

• The Research Journal of the Costume Culture
• /
• v.4 no.2
• /
• pp.173-185
• /
• 1996

The purpose of this study was to identify the relationship of clothing involvement and clothing buying behavior of women. A questionnaire was developed to measure clothing involvement, clothing purchasing motives, clothing purchasing criteria, fashion information sources, store selection criteria, and demographic characteristics. The questionnaire was administered to 430 female adults in Taegu. The data were analyzed using percentage, frequency, factor analysis, and t-test. The results of the study were s follows: 1. Subjects were divided into low clothing involved and high clothing involved groups. 2. Three dimensions of clothing purchasing motives were derived by factor analysis such as Aesthetic dependant, Impulsive, and Practical motive. Clothing purchasing criteria were factor analysed as Aesthetic, Qualitative, External, and Economical criterion. Fashion information sources were factor analysed as Printed & audio-visual oriented media, Marketer intensive search, Store search, Observation & Interpersonal search, and Experience. Store selection criteria were factor analyzed as Merchandise & Store atmosphere, Store convenience, and Brand & fashion. 3. There were significant differences between high involved and low involved consumers in clothing purchasing behavior. The high involved consumers showed more importance than low involved consumers about purchasing criteria expecially in aesthetic dependant. The high involved consumers put more importance to aesthetic, qualitative, and external criterion as clothing purchasing criteria. The high involved information sources. The high involved consumers were more concerned about merchandise & store atmosphere, and brand & fashion than low involved consumers in store selection criteria.

• Journal of the Korean Institute of Educational Facilities
• /
• v.9 no.3
• /
• pp.23-34
• /
• 2002

This paper is to analyse the major impact of the new era of information technology on the changes being made in physical environment of existing corporate training centers through the case of on- and off-line LG academies. By the analysis, some interesting features are to be found which can be a hint for the future planning and design of corporate training centers. Unlike the expectation in the early stage of changes, the rapid growth of on-line education forms a very strong partnership with the existing in-house training programs at all levels. Understanding of such key issues surrounding the use of facilities is specific to the formation of an effective environment for training programmes. After all aspects of the facility uses-not just the class rooms, but also the residential, dining, recreational, and support areas, as well as on-line type of educational services-are carefully examined, a design guideline is identified as considerations for guestrooms, classrooms, public facilities, the recreational areas, and the audio-visual provisions.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.921-926
• /
• 2009

After the scientific development of human history, numerous images have been developed and expanded in digital media as a communication tools. Image digital media make communication closer between sender and receptor. The image digital media which has been developed with the change of technology and media transformation have shortened visual information transportation and the time as well by combining the sense of visual and audio. Motion graphic field has been emerged as the type of image digital media development. The development of motion graphic make possible for the expressive effect and dynamic image technique which is impossible by the existing media type. Especially, it is applied to various field such as the title of movie, TV program, and advertise or music video etc. These image expression techniques are stimulating acceptor's emotion to take a role of emotion communication function also. This study aims to find the characteristics motion graphic of which how influence as an effective communication tool as important role to the receptors, and the examine the effect and application of motion graphic to the receptors as a emotion communication tool by case study.