초록

Abstract

Our limited understanding of real-life music information queries is an impediment to developing music information retrieval (MIR) systems that meet the needs of real users. This study aims to contribute to developing a theorized understanding of how people seek music information by an empirical investigation of real-life queries, in particular, focusing on the accuracy of user-provided information and users' uncertainty expressions. This study found that much of users' information is inaccurate; users made various syntactic and semantic errors in providing this information. Despite these inaccuracies and uncertainties, many queries were successful in eliciting correct answers. A theory from pragmatics is suggested as a partial explanation for the unexpected success of inaccurate queries.

초록

본 연구에서는 비디오의 의미를 잘 표현하고 있는 키프레임들을 추출하는 알고리즘을 설계하고 평가하였다. 구체적으로 영상 초록의 키프레임 선정을 위한 이론 체계를 수립하기 위해서 선행 연구와 이용자들의 키프레임 인식 패턴을 조사하여 분석해 보았다. 그런 다음 이러한 이론 체계를 기초로 하여 하이브리드 방식으로 비디오에서 키프레임을 추출하는 알고리즘을 설계한 후 실험을 통해서 그 효율성을 평가해 보았다. 끝으로 이러한 실험 결과를 디지털 도서관과 인터넷 환경의 비디오 검색과 브라우징에 활용할 수 있는 방안을 제안하였다.

Abstract

The purposes of the study are to design a key-frame extraction algorithm for constructing the virtual storyboard surrogates and to evaluate the efficiency of the proposed algorithm. To do this, first, the theoretical framework was built by conducting two tasks. One is to investigate the previous studies on relevance and image recognition and classification. Second is to conduct an experiment in order to identify their frames recognition pattern of 20 participants. As a result, the key-frame extraction algorithm was constructed. Then the efficiency of proposed algorithm(hybrid method) was evaluated by conducting an experiment using 42 participants. In the experiment, the proposed algorithm was compared to the random method where key-frames were extracted simply at an interval of few seconds(or minutes) in terms of accuracy in summarizing or indexing a video. Finally, ways to utilize the proposed algorithm in digital libraries and Internet environment were suggested.