• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06d
• /
• pp.350-355
• /
• 2007

본 연구에서는 점점 보편화되고 있는 대용량 휴대용 멀티미디어 단말에서 동영상, 사진, 음악 등과 같은 멀티미디어 컨텐츠를 메타 정보를 이용하여 쉽고 빠르게 검색할 수 있게 하는 시스템을 설계 및 구현하였다. 멀티미디어 컨텐츠에서 메타 정보는 사용자가 필요로 하는 중요한 정보들을 포함하고 있으며, 이를 이용한 검색은 디렉토리와 파일명에 의존하던 기존의 제한적인 컨텐츠 관리방식을 내용 기반의 자동 분류 방식으로 개선할 수 있게 한다. 또한 모든 컨텐츠에 대한 정보를 색인화한 뒤, 색인되어 있는 메타 정보데이터베이스에서 원하는 정보를 찾아내는 방법을 사용하여, 기존 시스템에서 파일명 검색만 가능했던 한계와 디스크 기반 검색으로 인한 느린 속도의 문제점을 해결할 수 있을 것으로 기대된다.

• The KIPS Transactions:PartA
• /
• v.10A no.6
• /
• pp.737-748
• /
• 2003

With the popularity of digital music contents, querying and retrieving music contents efficiently from database has become essential. In this paper, we propose a Fast Melody Finder (FMF) that can retrieve melodies fast and efficiently from music database using frequently queried tunes. This scheme is based on the observation that users have a tendency to memorize and query a small number of melody segments, and indexing such segments enables fast retrieval. To handle those tunes, FMF transcribes all the acoustic and common music notational inputs into a specific string such as UDR and LSR. We have implemented a prototype system and showed on its performance through various experiments.

• Journal of Broadcast Engineering
• /
• v.9 no.1
• /
• pp.2-7
• /
• 2004

In this paper, we proposed the content-based music information retrieval technique using some MPEG-7 low-level descriptors. Especially, pitch information and timbral features can be applied in music genre classification, music retrieval, or QBH(Query By Humming) because these can be modeling the stochasticpattern or timbral information of music signal. In this work, we restricted the music domain as O.S.T of movie or soap opera to apply broadcasting system. That is, the user can retrievalthe information of the unknown music using only an audio clip with a few seconds extracted from video content when background music sound greeted user's ear. We proposed the audio feature set organized by MPEG-7 descriptors and distance function by vector distance or ratio computation. Thus, we observed that the feature set organized by pitch information is superior to timbral spectral feature set and IFCR(Intra-Feature Component Ratio) is better than ED(Euclidean Distance) as a vector distance function. To evaluate music recognition, k-NN is used as a classifier

• The Journal of Korean Association of Computer Education
• /
• v.8 no.5
• /
• pp.109-118
• /
• 2005

In this paper, we present a music retrieval system that compares the geometric structure of a melody specified by a user with those in a music database. The system finds matches between a query melody and melodies in the database by analyzing both structural and contextual features. The retrieval method is based on the geometric hashing algorithm which consists of two steps; the preprocessing step and the recognition step. During the preprocessing step, we divide a melody into several fragments and analyze the pitch and duration of each note of the fragments to find a structural feature. To find a contextual feature, we find a main chord for each fragment. During the recognition step, we divide the query melody specified by a user into several fragments and search through all fragments in the database that are structurally and contextually similar to the melody. A vote is cast for each of the fragments and the music whose total votes are the maximum is the music that contains a matching melody against the query melody. Using our approach, we can find similar melodies in a music database quickly. We can also apply the method to detect plagiarism in music.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.139-141
• /
• 2007

최근 멀티미디어를 검색하기 위해 메타데이터 기반의 검색 방법에서 컨텐츠 자체를 검색 하려는 연구들이 활발히 진행되고 있다. 특히 음악 검색의 경우 허밍 입력으로 검색을 하려는 QBH(Query By Humming)가 많은 관심을 끌고 있다. 하지만 허밍 데이터는 개인마다 음높이나 박자 정보들이 모두 다르고 숨소리 등의 내재된 오류 정보들이 많아 정확한 검색 결과를 얻기가 쉽지 않다. 허밍 검색의 정확도 향상을 위해서는 음 데이터 추출이나 허밍의 오류 보정, 유사도 측정과 관련된 연구들이 선행되어야 한다. 본 논문에서는 효과적인 멜로디 표현방법에 대해 다양한 실험을 통해 최적의 모델을 제시하려 한다. 방법으로 UDR을 다양한 범위로 나누고 가중치를 달리하는 방법으로 실험을 한 결과 허밍을 그룹으로 분류하는 방법이 정확도를 향상 시키는 것을 확인 하였다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.10 no.3
• /
• pp.15-20
• /
• 2005

Since the invention of Web, it became part of our daily life replacing the routine information search and effecting many activities which otherwise could have been done off-line without it. It was a natural evolution of the web technology, which had started out as a simple test based pattern matching, to be based on the optimized match process for its multi-media Web environment, like still images, music and movies that we are to face today. In this paper, we proposed and implemented the model which the multimedia resources can be efficiently shared in semantic web. After converting multimedia resource information(metadata) into RDF, for efficient management, the model separate and allotment actual multimedia resource and corresponding metadata changed to RDF to each server. The proposed model could be applied in all multimedia resources. For easy explanation and implementation, however, we applied it to the digital photograph in example.