• Title/Summary/Keyword: 실험영화

Search Result 471, Processing Time 0.027 seconds

A Study on the Content-Based Video Information Indexing and Retrieval Using Closed Caption and Speech Recognition (캡션정보 및 음성인식을 이용한 내용기반 비디오 정보 색인 및 검색에 관한 연구)

  • 손종목;김진웅;배건성
    • Proceedings of the Korean Society of Broadcast Engineers Conference
    • /
    • 1999.11b
    • /
    • pp.141-145
    • /
    • 1999
  • 뉴스나 드라마, 영화 등의 비디오에 대한 검색 시 일반 사용자의 요구에 가장 잘 부합되는 결과를 얻기 위해 비디오 데이터의 의미적 분석과 색인을 만드는 것이 필요하다. 일반적으로 음성신호가 비디오 데이터의 내용을 잘 나타내고 비디오와 동기가 이루어져 있으므로, 내용기반 검색을 위한 비디오 데이터 분할에 효율적으로 이용될 수 있다 본 논문에서는 캡션 정보가 주어지는 방송뉴스 프로그램을 대상으로 효율적인 검색, 색인을 위한 비디오 데이터의 분할에 음성인식기술을 적용하는 방법을 제안하고 그에 따른 실험결과를 제시한다.

  • PDF

Construction of Dialog Engagement Model using MovieDic Corpus (MovieDic 말뭉치를 이용한 대화 참여 모델의 구성)

  • Koo, Sangjun;Yu, Hwanjo;Lee, Gary Geunbae
    • 한국어정보학회:학술대회논문집
    • /
    • 2016.10a
    • /
    • pp.249-251
    • /
    • 2016
  • 다중 화자 대화 시스템에서, 시스템의 입장에서 어느 시점에 참여해야하는지를 아는 것은 중요하다. 이러한 참여 모델을 구축함에 있어서 본 연구에서는 다수의 화자가 대화에 참여하는 영화 대본으로 구축된 MovieDic 말뭉치를 사용하였다. 구축에 필요한 자질로써 의문사, 호칭, 명사, 어휘 등을 사용하였고, 훈련 알고리즘으로는 Maximum Entropy Classifier를 사용하였다. 실험 결과 53.34%의 정확도를 기록하였으며, 맥락 자질의 추가로 정확도 개선을 기대할 수 있다.

  • PDF

Dual-Mode Type Stop-and-Go Adaptive Blind Equalization Algorithm (이중모드 형태의 Stop-and-Go 적응 블라인드 등화 알고리즘)

  • 정영화;진용옥
    • The Journal of the Acoustical Society of Korea
    • /
    • v.17 no.2
    • /
    • pp.11-17
    • /
    • 1998
  • 본 논문에서는 빠른 수렴 속도를 가지면서 정상 상태에서 작은 오차 레벨을 유지하 는 이중모드 형태의 Stop-and-Go 알고리즘을 제안한다. 제안된 알고리즘은 특별한 결정 영 역을 설정하여 등화기 출력 레벨이 어느 영역에 속하느냐에 따라 MCMA와 판정지향 알고 리즘을 결합한 변형된 Stop-and-Go 알고리즘과 기존의 Stop-and-Go 알고리즘의 동작을 자동 전환한다. 컴퓨터 모의실험 결과, 제안한 알고리즘이 CMA, MCMA 및 Stop-and-Go 알고리즘등과 같은 기존의 적응 블라인드 등화 알고리즘들에 비해 잔류 심볼간 간섭과 정상 상태로의 수렵 속도면에서 모두 우수한 성능을 가짐을 확인하였다.

  • PDF

Recommendation Reflecting User Preferences on Genres (유저의 장르 선호도를 반영한 추천)

  • Lee, Ho-Jong;Hwang, Won-Seok;Kim, Sang-Wook
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2011.04a
    • /
    • pp.1285-1286
    • /
    • 2011
  • MovieLens를 대상으로 하는 추천 시스템에 대한 연구 중 k-NN 추천 방법은 정확도가 비교적 높지만 평점을 예측할 수 없는 상황이 발생할 수 있다. 본 논문에서는 기존 방법의 문제점을 해결한 장르기반 추천 방법 제안하고, 실험을 통하여 제안하는 방법이 모든 영화에 대한 평점의 예측이 가능함을 검증한다.

Linear Scratch Detection and Removal Technique for Old Film Sequences Using Wavelet Shrinkage and Interpolation (고전 영화 복원을 위한 웨이블릿 계수축소와 보간법을 이용한 선형 스크래치 검출 및 제거 기술)

  • Kang, Won-Seok;Lee, Eun-Sung;Kim, Sang-Jin;Paik, Joon-Ki
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.48 no.5
    • /
    • pp.1-9
    • /
    • 2011
  • This paper presents a novel scratch detection and removal approach for old film images in wavelet-domain. Various scratch detection and removal algorithms have been proposed for past decades. However, accurate scratch detection and removal with a moderate amount of computing effort is still a problem because of trade off between the quality of the film and computational load. For overcoming this problem, we first decompose an input image using a 3-level wavelet transform, and then remove the scratch by shrinking wavelet coefficients using linear interpolation. Experimental results show that the proposed algorithm can efficiently detect and remove the scratch in damaged films, and also be incorporated into old film restoration systems.

Development of Emotion Contents Recommender System for Improvement of Sentimental Status (감정 및 정서상태 전이를 위한 감성 컨텐츠 추천 시스템 개발)

  • Park, Myon-Woong;Ha, Sung-Do;Jeong, Do-Un;Lyoo, In-Kyoon;Ahn, Seong-Min
    • Science of Emotion and Sensibility
    • /
    • v.10 no.1
    • /
    • pp.1-11
    • /
    • 2007
  • An Infotainment Service intended to enhance the human emotion is introduced in this paper. The service is to be installed on the robot helping elderly persons to live comfortable and enjoyable life. The research started with defining the undesirable status of emotion in everyday life, and the psychological skills to cope with the status were sought about. Then, a methodology for providing emotion contents reflecting the coping skill has been suggested. Based on the Cognitive Behavior Therapy, the coping skill is used to edit animation clips. A movie recommendation system to utilize the edited animation clips has been being developed. A series of process for developing the system is described, where the emotion elements are taken into consideration in addition to the user preference as the criterion for recommendation.

  • PDF

Stereoscopic Contents Production Workflow Based on Nonlinear Editing (비선형 편집기반의 입체영상 제작 흐름에 관한 연구)

  • Kim, Chul-Hyun;Paik, Joon-Ki
    • Journal of Broadcast Engineering
    • /
    • v.15 no.3
    • /
    • pp.391-406
    • /
    • 2010
  • Digital cinema based on digital master distribution increases with stereoscopic film as the center. DCI specification V1.0 announced at 2004, it considerates stereoscopic film screening. And now, the Society of Motion Picture and Television Engineers is establishing a task force to define the standards of a stereoscopic contents viewed in the home. Today, most Hollywood commercial stereoscopic film features animation using computer graphic. However, considering film making characteristic, stereoscopic digital cinema is required shooting in real world and editing, screening. This paper presents possibility of stereoscopic examination at NLE in the stereoscopic workflow. And we will propose new stereoscopic digital cinema workflow to apply the stereoscopic examination. Based on experimental results, the 3D ready television using 120Hz has some obstacles for contents editing, but most domestic stereoscopic monitor using circular polarization is possible for successful editing.

Performance Improvement of a Movie Recommendation System using Genre-wise Collaborative Filtering (장르별 협업필터링을 이용한 영화 추천 시스템의 성능 향상)

  • Lee, Jae-Sik;Park, Seog-Du
    • Journal of Intelligence and Information Systems
    • /
    • v.13 no.4
    • /
    • pp.65-78
    • /
    • 2007
  • This paper proposes a new method of weighted template matching for machine-printed numeral recognition. The proposed weighted template matching, which emphasizes the feature of a pattern using adaptive Hamming distance on local feature areas, improves the recognition rate while template matching processes an input image as one global feature. Template matching is vulnerable to random noises that generate ragged outlines of a pattern when it is binarized. This paper offers a method of chain code trimming in order to remove ragged outlines. The method corrects specific chain codes within the chain codes of the inner and the outer contour of a pattern. The experiment compares confusion matrices of both the template matching and the proposed weighted template matching with chain code trimming. The result shows that the proposed method improves fairly the recognition rate of the machine-printed numerals.

  • PDF

Contingent Interactivity of New Media Contents: Film Re-cut and Game Modding (뉴미디어 콘텐츠의 우연적 상호작용성: 영화 리컷과 게임 모딩)

  • Kim, Mookyu
    • The Journal of the Korea Contents Association
    • /
    • v.19 no.6
    • /
    • pp.481-490
    • /
    • 2019
  • The purpose of this paper is to recognize and embody the implications of the concept of interactivity. Among the many types of interactivity already proposed, this paper sheds light especially on the so-called contingent interactivity. The contingency means a condition in which a particular performance or selection of a subject is considered neither necessary nor conclusive, and also the potential for various activities of this subject. The contingent interaction comes into being when the involvements of users in dealing with a message or content are experimental or creative. The interaction does not orient toward the completion of content or the immersion to a particular reality. Rather, the results of a user's contingent performance are not the finalized content and have characteristics that lead to the continuous modification. In order to embody this meaning of contingent interactivity, the paper examined the two example, the film re-cut and game modding. In both cases, it is comprehensive that the user of these two new media activities lies in the contingent situation.

Multicriteria Movie Recommendation Model Combining Aspect-based Sentiment Classification Using BERT

  • Lee, Yurin;Ahn, Hyunchul
    • Journal of the Korea Society of Computer and Information
    • /
    • v.27 no.3
    • /
    • pp.201-207
    • /
    • 2022
  • In this paper, we propose a movie recommendation model that uses the users' ratings as well as their reviews. To understand the user's preference from multicriteria perspectives, the proposed model is designed to apply attribute-based sentiment analysis to the reviews. For doing this, it divides the reviews left by customers into multicriteria components according to its implicit attributes, and applies BERT-based sentiment analysis to each of them. After that, our model selectively combines the attributes that each user considers important to CF to generate recommendation results. To validate usefulness of the proposed model, we applied it to the real-world movie recommendation case. Experimental results showed that the accuracy of the proposed model was improved compared to the traditional CF. This study has academic and practical significance since it presents a new approach to select and use models in consideration of individual characteristics, and to derive various attributes from a review instead of evaluating each of them.