• Journal of KIISE:Software and Applications
• /
• v.27 no.5
• /
• pp.510-520
• /
• 2000

For content-based video indexing and retrieval, it is necessary to segment video data into video shots and then select key frames or representative frames for each shot. However, it is very difficult to select key frames automatically because the task of selecting meaningful frames is quite subjective. In this paper, we propose a new approach in selecting key frames based on visual contents such as region information and their temporal variations in the shot. First of all, we classify video shots into panning shots, zooming shots, tilting shots or no camera motion shots by detecting camera motion information in video shots. Then, in each category, we apply appropriate fuzzy rules to select key frames based on meaningful content in frame. Finally, we control the number of key frames in the selection process by adjusting the degree of detail in representing video shots.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.215-218
• /
• 2000

디지털 비디오 데이터를 효율적으로 브라우징 하는데 필요한 비디오 분할에 관한 연구가 활발하게 진행되고 있다. 본 연구에서는 비디오 데이터를 Shot단위로 분할하고, Shot내부에서 카메라 동작과 객체 움직임 분석을 이용한 sub-shot으로 분할하고자 한다. 연구 방법으로는 I-frame의 DC 영상을 이용하여 픽쳐그룹을 Shot(장면이 바뀐 경우), Move(카메라 동작,객체움직임), Static(영상의 변화가 거의 없는 경우)로 세분화하고 해당 픽쳐 그룹의 P, B-frame을 검사하여 정확한 컷 발생 위치, 디졸브, 카메라동작, 객체 움직임을 검출하게 된다. 픽쳐그룹 분류에서 정확성을 높이기 위해 계층적 신경망과 다중 특징을 이용한다. 정확한 컷 발생위치 검출하기 위해서 P, B프레임의 메크로블럭 타입을 이용한 통계적 방법을 이용하고, 디졸브, 카메라 동작, 객체 움직임을 검출하기 위해서 P, B-frame의 메크로블럭 타입과 움직임 벡터를 이용한 신경망으로 검출한다. 본 연구에서는 계층적 탐색을 이용하여 시간을 단축할 수 있고, 계층적 신경망과 다중 특징을 이용하여 픽쳐 그룹을 세분화 할 수 있고, 메크로 블록 타입과 통계적 방법을 이용하여 정확한 컷 검출을 할수 있고, 신경망을 이용하여 디졸브, 카메라 동작, 객체움직임을 검출 할 수 있음을 확인한다.

• Annual Conference on Human and Language Technology
• /
• 2007.10a
• /
• pp.179-182
• /
• 2007

우리가 현재 사용하고 있는 정보검색 시스템은 사용자의 질의와 연관있는 문서 집합만을 제공하므로 사용자가 원하는 정답을 찾기 위해서 사용자는 문서 집합을 브라우징하는 수고를 하여야 하며, 이러한 수고를 덜어주기 위해 개발되는 자동 질의응답시스템은 의미 분석 및 지식 추출 등의 기술적 한계로 사용자에게 만족할 만한 서비스를 제공하고 있지 못한 실정이다. 본 논문은 인터넷에 연결되어 있는 사람 중에 질의어에 대한 응답을 할 수 있는 지혜 제공자를 자동으로 검색 분류하여, 질의자와 실시간으로 연결하여 사용자와 지혜 제공자가 실시간 상호커뮤니케이션을 이용하여 지혜를 교류할 수 있는 인력기반 질의응답시스템인 알포도 시스템을 제안한다. 알포도 시스템은 질의응답모듈, 메티스 관리 모듈, 실시간 커뮤니케이션 모듈, 그리고 지식 추출 및 관리 모듈로 구성되며 현재 베타 서비스를 실시 중이다.

• The KIPS Transactions:PartD
• /
• v.10D no.1
• /
• pp.133-142
• /
• 2003

The major challenge for post-genomic study is to identify structural similarity and relationships of proteins. SCOP (Structural Classification of Proteins) is a typical database for this purpose, providing a derailed description of the structural and functional relationships of the proteins whose three-dimensional structures have been determined. Unfortunately, since the SCOP data is only available as a plain text format, it is cumbersome and error-prone to develop tools and resources to utilize the data more effectively. To meet these researchers to utilize the data more effectively. To meet these requirements, we have developed an XML representation for the SCOP site, users of the tool, named, SCOPBrowser, for effective search of SCOP database. In addition to the information available from the SCOP site, users of the tool can obtain various information such as viewing the tree hierarchy of structure classification of proteins, searching into whole protein domains, showing XML contents of a specific domain, and some useful statistics about protein structures.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.5
• /
• pp.441-446
• /
• 2009

This paper proposes an automatic indexing algorithm of golf video using audio information. In the proposed algorithm, the input audio stream is demultiplexed into the stream of video and audio. By means of Adaboost-cascade classifier, the continuous audio stream is classified into announcer's speech segment recorded in studio, music segment accompanied with players' names on TV screen, reaction segment of audience according to the play, reporter's speech segment with field background, filed noise segment like wind or waves. And golf swing sound including drive shot, iron shot, and putting shot is detected by the method of impulse onset detection and modulation spectrum verification. The detected swing and applause are used effectively to index action or highlight unit. Compared with video based semantic analysis, main advantage of the proposed system is its small computation requirement so that it facilitates to apply the technology to embedded consumer electronic devices for fast browsing.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.11a
• /
• pp.173-176
• /
• 2009

본 논문에서는 영상 정보와 오디오 정보 분석을 이용하여 TV 골프 방송 프로그램에서 중요 이벤트 구간을 검출하고 요약 하는 알고리즘을 제안한다. 제안하는 알고리즘에서는 입력되는 TV 골프 동영상을 영상 신호와 오디오 신호로 분리한 후에, 연속적인 오디오 스트림을 내용 기반의 오디오 구간으로 분류한 뒤 오디오 이벤트 구간을 검출하고, 이와 병렬적으로 영상정보에서 선수들의 플레이 장면을 검출한다. 플레이 장면 검출에 있어서는 방송 환경이나 날씨 등의 변화하는 다양한 조건에 대해 플레이 장면에 대한 오프라인 모델과 함께 경기 내에서 발생한 온라인 모델에 대한 학습을 혼합 적용함으로써 검출 성능을 높였다. 오디오 신호로부터 관중들의 박수소리와 스윙 사운드를 통해 검출된 오디오 이벤트와 플레이 장면은 이벤트 장면 검출 및 요약본 생성을 위해 사용된다. 제안된 알고리즘은 멀티 모달 정보를 이용하여 이벤트 구간 검출을 수행함으로써 중요 이벤트 구간 검출의 정확도를 높일 수 있었고, 검출된 이벤트 구간에 대한 요약본 생성을 통해 골프 경기를 시청하는 사용자가 원하는 부분을 빠르게 브라우징하여 시청하는 것이 가능하여 높은 사용자 만족도를 얻을 수 있었다.

• Journal of Broadcast Engineering
• /
• v.11 no.1 s.30
• /
• pp.15-27
• /
• 2006

In this paper, a novel approach is addressed to facilitate the browsing of large collection of digital photos associated with specified person(s) in the photos. The goal of the proposed method is to exploit additional person-identity features as incorporating facial regions and peripheral clothes region associated with them. For more effective incorporation of the clothes and facial features, situation-based photo clustering is also proposed. To evaluate the efficacy of the proposed method experiment was performed with 1120 generic home photos. The experiment results showed that the proposed method outperformed the conventional method us El.g only face feature as showing the average performance of about 92% contrary to the average performance of about 70% in the conventional method.

• The Journal of Society for e-Business Studies
• /
• v.14 no.4
• /
• pp.59-73
• /
• 2009

Keyword extraction is an important and essential technique for text mining applications such as information retrieval, text categorization, summarization and topic detection. A set of keywords extracted from a large-scale electronic document data are used for significant features for text mining algorithms and they contribute to improve the performance of document browsing, topic detection, and automated text classification. This paper presents a keyword extraction technique that can be used to detect topics for each news domain from a large document collection of internet news portal sites. Basically, we have used six variants of traditional TF-IDF weighting model. On top of the TF-IDF model, we propose a word filtering technique called 'cross-domain comparison filtering'. To prove effectiveness of our method, we have analyzed usefulness of keywords extracted from Korean news articles and have presented changes of the keywords over time of each news domain.

• Journal of KIISE:Software and Applications
• /
• v.34 no.9
• /
• pp.828-847
• /
• 2007

In this paper we propose a formal data model of an object-based thesaurus system supporting multi-dimensional facets. According to facets reflecting on respective user perspectives, it supports systematic construction, browsing, navigating and referencing of thesauri. Unlike other faceted thesaurus systems, it systematically manages its complexity by appropriately ing sophisticated conceptual structure through visualized browsing and navigation as well as construction. The browsing and navigation is performed by dynamically generating multi-dimensional virtual thesaurus hierarchies called "faceted thesaurus hierarchies." The hierarchies are automatically constructed by combining facets, each representing a dimension of view. Such automatic construction may make it possible the flexible extension of thesauri for they can be easily upgraded by pure insertion or deletion of facets. With a well defined set of self-referential queries, the thesauri can also be effectively referenced from multiple view points since they are structured by appropriately interpreting the semantics of instances based on facets. In this paper, we first formalize the underlying model and then implement its prototype to demonstrate its feasibility.

• Journal of KIISE:Software and Applications
• /
• v.31 no.5
• /
• pp.586-594
• /
• 2004

Because web documents become creation and disappearance rapidly, users require the recommend system that offers users to browse the web document conveniently and correctly. One largely untapped source of knowledge about large data collections is contained in the cumulative experiences of individuals finding useful information in the collection. Recommendation systems attempt to extract such useful information by capturing and mining one or more measures of the usefulness of the data. The existing Information Filtering system has the shortcoming that it must have user's profile. And Collaborative Filtering system has the shortcoming that users have to rate each web document first and in high-quantity, low-quality environments, users may cover only a tiny percentage of documents available. And dynamic recommendation system using the user browsing pattern also provides users with unrelated web documents. This paper classifies these web documents using the similarity between the web documents under the web document type and extracts the user browsing sequential pattern DB using the users' session information based on the web server log file. When user approaches the web document, the proposed Dynamic recommendation system recommends Top N-associated web documents set that has high similarity between current web document and other web documents and recommends set that has sequential specificity using the extracted informations and users' session information.