• 대한인간공학회:학술대회논문집
• /
• 대한인간공학회 1995년도 추계학술대회논문집
• /
• pp.56-61
• /
• 1995

Multimedia systems present information by using various media, for example, video, sound, music, animation, movie, etc., in addition to the text which has long been used for conveying the information. Among many multimedia applications, the multimedia information retrieval systems commercialized in the form of multimedia encyclopedia CD-ROMs, benefit by using various media for their ability to present information in an efficient and complete way. But using various media may cause end users' confusion and furthermore, poor user-interface design often exacerbates the systems. For appropriate design of the user interface of multimedia information retrieval systems, we investigated the characteristics of the multimedia information retrieval systems and listed 35 variables that might affect the usability of the user interface. And we selected 10 variables through some procedures such as brainstorming, literature survey, expert opinion, relevance analysis and feasibility analysis, in order to perform a screening study which will remarkably reduce the cost and time in conducting subsequent human factors experiments.

• 한국정보처리학회논문지
• /
• 제7권2S호
• /
• pp.692-700
• /
• 2000

As the multimedia application services have been getting various in Internet, need of multimedia database management system which can manage various multimedia information effectively has been increased. The multimedia application generally needs the features to store, manage, retrieve the multimedia data. We need a database management system framework that may be easily integrated with these features. This paper proposes th database management system framework providing the easy integration with various multimedia information retrieval. The framework uses OQL as the retrieval interface, so that user can use it easily. It can be integrated dynamically and easily with various multimedia retrieval method as a loosely coupled system. In addition there is no performance degradation caused in a loosely coupled system.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1403-1417
• /
• 2019

With the rapid growth of multimedia data, research on cross-media feature learning has significance in many applications, such as multimedia search and recommendation. Existing methods are sensitive to noise and edge information in multimedia data. In this paper, we propose a semi-supervised method for cross-media feature learning by means of $L_{2,q}$ norm to improve the performance of cross-media retrieval, which is more robust and efficient than the previous ones. In our method, noise and edge information have less effect on the results of cross-media retrieval and the dynamic patch information of multimedia data is employed to increase the accuracy of cross-media retrieval. Our method can reduce the interference of noise and edge information and achieve fast convergence. Extensive experiments on the XMedia dataset illustrate that our method has better performance than the state-of-the-art methods.

• 한국정보처리학회논문지
• /
• 제7권2S호
• /
• pp.678-691
• /
• 2000

A variety of multimedia applications require multimedia database management systems to manage multimedia data, such as text, image, and video, as well as t support content-based image or video retrieval. In this paper we design and implement a content-based image retrieval system, BADA-IV/I$^2$R(Image Information Retrieval), which is developed based on BADA-IV multimedia database management system. In this system image databases can be efficiently constructed and retrieved with the visual features, such as color, shape, and texture, of image. we extend SQL statements to define image query based on both annotations and visual features of image together. A high-dimensional index structure, called CIR-tree, is also employed in the system to provide an efficient access method to image databases. We show that BADA-IV/I$^2$R provides a flexible way to define query for image retrieval and retrieves image data fast and effectively: the effectiveness and performance of image retrieval are shown by BEP(Bull's Eye Performance) that is used to measure the retrieval effectiveness in MPEG-7 and comparing the performance of CIR-tree with those of X-tree and TV-tree, respectively.

• 대한산업공학회지
• /
• 제22권2호
• /
• pp.265-276
• /
• 1996

Multimedia systems present information by various media, for example, video, sound, music, animation, movie, etc., in addition to the text which has long been used for conveying the information. Among many multimedia applications, the multimedia information retrieval systems commercialized in the forms of multimedia encyclopedia CD-ROMs, benefited from various media for their ability to present information in an efficient and complete way. But using several media, on the other hand, may cause end users' confusion and furthermore, poorly designed user interface often exacerbates the situation. In this study, the multimedia systems were studied from the standpoint of usability. The conceptual framework of the user interface of the multimedia system was newly defined. And 100 initial variables for user interface design of general multimedia systems were suggested through literature survey and expert opinions based upon the framework developed. Among various application areas, the multimedia information retrieval systems were chosen for investigation, and 36 variables particularly relevant to user interface of the multimedia information retrieval systems were selected. According to the sequential research strategy, the variables that were considered to be most important were finally selected through a screening stage. A part of selected variables were verified through a human factors experiment as the first step of sequential research. Based upon the result of the experiment, guidelines for user interface design were provided. For future study, the variables remained will be Investigated and the study will expand to another application areas.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2000년도 춘계종합학술대회
• /
• pp.325-330
• /
• 2000

최근 들어, 컴퓨터 및 관련 기술의 발전은 통신망, 정보 처리 형태 및 통신 서비스의 발전을 동반하여 정보화 사회로의 진입을 가속화시키고 있다. 특히 인터넷의 WWW 등장으로 인하여 전자 신문, 전자 컨퍼런스, 멀티미디어 문서 검색 등 헤아릴 수 없는 많은 서비스들이 손쉽게 개발되었고, 이는 일반인들의 정보 통신망의 수요를 더 한층 증가시키고 있으며 실제적인 정보화 시대를 앞당기고 있다. 최근 연구되고 있는 주요 기반 기술들로는 정보의 형태가 멀티미디어 화에 따른 내용 기반 정보검색 기술 연구가 활발히 진행되고 있고, 멀티미디어 정보가 방대함에 따라 기존의 하드디스크 대신에 3차 저장 장치를 하부 저장 시스템의 일부로 확장시키는 연구가 한창이다. 또한 정보 검색 분야 외에도 정보 구축 기술로, 정보들을 체계적으로 관리할 수 있도록 모델링 기법에 대해 기술한다.

• 한국멀티미디어학회논문지
• /
• 제19권8호
• /
• pp.1498-1504
• /
• 2016

The progress of mobile computing technology is bringing a large amount of multimedia contents such as image. Thus, we need an image retrieval system which searches semantically relevant image. In this paper, we propose a semantic image annotation and retrieval in mobile environments. Previous mobile-based annotation approaches cannot fully express the semantics of image due to the limitation of current form (i.e., keyword tagging). Our approach allows mobile devices to annotate the image automatically using the context-aware information such as temporal and spatial data. In addition, since we annotate the image using RDF(Resource Description Framework) model, we are able to query SPARQL for semantic image retrieval. Our system implemented in android environment shows that it can more fully represent the semantics of image and retrieve the images semantically comparing with other image annotation systems.

• Journal of Multimedia Information System
• /
• 제4권3호
• /
• pp.99-106
• /
• 2017

This study does a qualitative and quantitative analysis of how music by humming is being used by music educators in the classroom. Music by humming is part division of music information retrieval. In order to define what a music information retrieval system is first I need to define what it is. Berger and Lafferty (1999) define information retrieval as "someone doing a query to a retrieval system, a user begins with an information need. This need is an ideal document- perfect fit for the user, but almost certainly not present in the retrieval system's collection of documents. From this ideal document, the user selects a group of identifying terms. In the context of traditional IR, one could view this group of terms as akin to expanded query." Music Information Retrieval has its background in information systems, data mining, intelligent systems, library science, music history and music theory. Three rounds of surveys using question pro where completed. The study found that there were variances in knowledge, training and level of awareness of query by humming, music information retrieval systems. Those variance relationships where based on music specialty, level that they teach, and age of the respondents.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1996년도 Proceedings International Workshop on New Video Media Technology
• /
• pp.128-133
• /
• 1996

In this paper, we describe the design and implementation of a multimedia information system integrating hypermdia, information retrieval, and DBMS technologies. We browse the information space through hypermedia link navigation and also use ad hoc queries for direct retrieval of information from the database. Both the hypermedia and the information retrieval systems are integrated into a database management system (DMBS) so that concurrent edition, update, and retrieval of documents can have the ACID properties of atomicity, consistency, isolation, and durability. We will first explain the architecture of the system and then, describe how the hypermedia system is integrated with information retrieval capability, and finally integrated with DBMS capabilities.

• 인터넷정보학회논문지
• /
• 제8권5호
• /
• pp.67-79
• /
• 2007

최근 웹 기술의 발달과 유무선 네트워크 성능의 향상, 그리고 다양한 멀티미디어 서비스가 등장함에 따라 텍스트 문서나 이미지에 대한 검색뿐만 아니라 동영상을 포함한 멀티미디어 검색에 대한 요구가 크게 증가하고 있다. 그러나 기존의 멀티미디어 검색 방법은 멀티미디어 콘텐츠에 포함된 의미 개념들의 연관성을 효과적으로 이용하지 못하고 콘텐츠에 대한 메타데이터의 검색에 의존함에 따라 제한적인 검색 결과만을 제공한다. 본 논문에서는 도메인 온톨로지를 활용하여 멀티미디어 콘텐츠의 의미적 연관성에 기반을 둔 멀티미디어 검색 방법 및 시스템 구조를 제안한다. 사용자 검색어를 직접적으로 포함하지 않지만 의미적으로 연관성이 있는 개념들을 온톨로지에서 검색하고 이들에 대한 랭킹을 결정하기 위한 클래스 연관도 척도를 정의하고, 이를 효율적으로 계산하기 위한 알고리즘을 제시한다. 또 프로토타입 시스템 구현 및 실험을 통해 제안한 검색 방법 및 시스템의 효과를 보인다.