簡易檢索 / 詳目顯示
| 研究生： |
吳文博 |
|---|---|
| 論文名稱： |
基於自動建置的社群網路之電影中的人臉分群研究 Face Clustering in Movies Using Automatically Constructed Social Networks |
| 指導教授： | 葉梅珍 |
| 學位類別： |
碩士 Master |
| 系所名稱： |
資訊工程學系 Department of Computer Science and Information Engineering |
| 論文出版年： | 2012 |
| 畢業學年度： | 100 |
| 語文別： | 中文 |
| 論文頁數： | 45 |
| 中文關鍵詞： | 人臉分群 、社群網路 |
| 英文關鍵詞： | Face Clustering, Social Network |
| 論文種類： | 學術論文 |
| 相關次數： | 點閱：94 下載：10 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
傳統基於視覺的低階臉部特徵（Low-Level Face Descriptor）用於人臉分群（Face Clustering）的研究已有局限，主要的困難在於人臉在拍攝角度或亮度有差異的情況下，如何適當地衡量它們之間的相似程度，以避免在執行人臉分群的工作時，將同一個人的人臉影像分至不同人的人臉群集之中。為了解決角度亮度及人臉分群的問題，直覺的做法是需要人力的介入去檢視所有的人臉群集，並手動將相同的人臉群集合併在一起。在本篇論文中，我們提出藉由聯想預測模型（Associate-Predict Model）的方法與社群網路的特徵來解決這兩個問題。我們提出自動的方法，從電影中建立角色間的社群網路，再者，我們獲取社群網路內在所蘊含有意義的社群資訊，將這些資訊用於人臉分群的工作上以提升其準確率。我們實驗證明藉由角色間的社群關係確實可以增進人臉分群及社群網路建置的效能。
This paper describes a technique for clustering faces in movies. Traditional methods are based on low-level visual features; such approaches have limited performance because of large intra-personal variations. We propose a new approach that revises the similarity of two face clusters by the use of an associate-predict model and social relationships, which are automatically discovered from movies. Experimental results validate the effectiveness of the proposed method. In addition, our approach can be used to construct social networks between characters that describe their social relationships.
[01] Peng Wu and Dan Tretter, “Close & Closer: Social Cluster and Closeness form Photo Collections,” Proc. ACM Multimedia, 2009.
[02] Peng Wu and Feng Tang, “Improving Face Clustering Using Social Context,” Proc. ACM Multimedia, 2010.
[03] Jae Young Choi, Wesley De Neve, Konstantinos N. Plataniotis, and Yong Man Ro, “Collaborative Face Recognition for Improved Face Annotation in Personal Photo Collections Shared on Online Social Networks,” IEEE Transactions on Multimedia, vol. 13, no.1, Feb. 2011.
[04] Chung-Yi Weng, Wei-Ta Chu, and Ja-Ling Wu, “Movie analysis based on roles’ social network,” Proc. IEEE ICME, Beijing, China, 2007.
[05] Chung-Yi Weng, Wei-Ta Chu, and Ja-Ling Wu, “RoleNet: Treat a Movie as a small society,” Proc. ACM MIR, pp.51-60, 2007.
[06] Chung-Yi Weng, Wei-Ta Chu, and Ja-Ling Wu, “RoleNet: Movie analysis from the perspective of social network,” IEEE Transactions on Multimedia, vol.11, no. 2, pp.256-271, Feb. 2009.
[07] Yi-Fan Zhang, Changsheng Xu, Hanqing Lu, and Yeh-Min Huang, “Character Identification in Feature-Length Films Using Global Face-Name Matching,” IEEE Transactions on Multimedia, vol.11, no. 7, Nov. 2009.
[08] Andrew C. Gallagher and Tsuhan Chen, “Using Group Prior to Identify People in Consumer Images,” IEEE Conference on Computer Vision and Pattern Recognition, 2007.
[09] Qi Yin, Xiaoou Tang, and Jian Sun, “An associate-predict model for face recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
[10] Open Source Computer Vision Library http://www.intel.com/technology/computing/opencv
[11] Yong Ma and Xiaoqing Ding, “Robust real-time face detection based on cost-sensitive AdaBoost method,” International Conference on Multimedia and Expo, 2003. ICME '03. Proceedings. 2003.
[12] T.Ahonen, A. Hadid and M. Pietikainen, “Face Recognition with Local Binary Patterns,” ECCV, 2004.
[13] Gross R., Matthews I., Cohn J., Kanade T., and Baker S., “Multi-PIE,” IEEE International Conference on Automatic Face & Gesture Recognition, 2008.
[14] Brendan J. Frey and Delbert Dueck, “Clustering by Passing Messages Between Data Points,” Science, pp. 972-976, Feb. 2007.
[15] Mei-Chen Yeh, Ming-Chi Tseng and Wen-Po Wu, "Automatic Social Network Construction from Movies Using Film-Editing Cues", 1st International Workshop on Social Media Computing, 2012.
[16] T. J. Smith, “An Attentional Theory of Continuity Editing,” PhD thesis, University of Edinburgh, 2005.
