Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/65506Full metadata record
| ???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
|---|---|---|
| dc.contributor.advisor | 歐陽明(Ming Ouhyoung) | |
| dc.contributor.author | Yi-Ting Wu | en |
| dc.contributor.author | 吳宜庭 | zh_TW |
| dc.date.accessioned | 2021-06-16T23:47:11Z | - |
| dc.date.available | 2012-08-09 | |
| dc.date.copyright | 2012-08-09 | |
| dc.date.issued | 2012 | |
| dc.date.submitted | 2012-07-23 | |
| dc.identifier.citation | [1] J.-x. Chai, J. Xiao, and J. Hodgins. Vision-based control of 3d facial animation. In Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation, SCA ’03, pages 193–206, Aire-la-Ville, Switzerland, Switzerland, 2003. Eurographics Association.
[2] J. Chen, M. K. Leung, and Y. Gao. Noisy logo recognition using line segment hausdorff distance. Pattern Recognition, 36(4):943 – 955, 2003. [3] C.-Y. Chiu, S.-P. Chao, M.-Y. Wu, S.-N. Yang, and H.-C. Lin. Content-based retrieval for human motion data. J. Vis. Comun. Image Represent., 15(3):446–466, Sept. 2004. [4] Y. Gao and M. K. Leung. Line segment hausdorff distance on face matching. Pattern Recognition, 35(2):361 – 371, 2002. [5] B. Gong, Y. Wang, J. Liu, and X. Tang. Automatic facial expression recognition on a single 3d face by exploring shape deformation. In Proceedings of the 17th ACM international conference on Multimedia, MM ’09, pages 569–572, New York, NY, USA, 2009. ACM. [6] E. Keogh. Exact indexing of dynamic time warping. In Proceedings of the 28th international conference on Very Large Data Bases, VLDB ’02, pages 406–417. VLDB Endowment, 2002. [7] E. Keogh, T. Palpanas, V. B. Zordan, D. Gunopulos, and M. Cardle. Indexing large human-motion databases. In Proceedings of the Thirtieth international conference 41 on Very large data bases - Volume 30, VLDB ’04, pages 780–791. VLDB Endowment, 2004. [8] L. Kovar and M. Gleicher. Automated extraction and parameterization of motions in large data sets. In ACM SIGGRAPH 2004 Papers, SIGGRAPH ’04, pages 559–568, New York, NY, USA, 2004. ACM. [9] F. Li, M. Leung, and X. Yu. A two-level matching scheme for speedy and accurate palmprint identification. In Advances in Multimedia Modeling, pages 323–332. Springer Berlin / Heidelberg, 2006. [10] X. Li, Q. Ruan, and Y. Ming. 3d facial expression recognition based on basic geometric features. In Signal Processing (ICSP), 2010 IEEE 10th International Conference on, pages 1366 –1369, oct. 2010. [11] A. Maalej, B. B. Amor, M. Daoudi, A. Srivastava, and S. Berretti. Shape analysis of local facial patches for 3d facial expression recognition. Pattern Recognition, 44(8):1581 – 1589, 2011. [12] A. Maalej, B. Ben Amor, M. Daoudi, A. Srivastava, and S. Berretti. Local 3d shape analysis for facial expression recognition. In Pattern Recognition (ICPR), 2010 20th International Conference on, pages 4129 –4132, aug. 2010. [13] M. M‥uller, T. R‥oder, and M. Clausen. Efficient content-based retrieval of motion capture data. ACM Trans. Graph., 24(3):677–685, July 2005. [14] S. Pal, P. Biswas, and A. Abraham. Face recognition using interpolated bezier curve based representation. In Information Technology: Coding and Computing, 2004. Proceedings. ITCC 2004. International Conference on, volume 1, pages 45 – 49 Vol.1, april 2004. [15] V. F. Pamplona, E. B. Passos, J. Zizka, M. M. Oliveira, E. Lawson, E. Clua, and R. Raskar. Catra: interactive measuring and modeling of cataracts. In ACM SIGGRAPH 2011 papers, SIGGRAPH ’11, pages 47:1–47:8, New York, NY, USA, 2011. ACM. [16] Y. Sakamoto, S. Kuriyama, and T. Kaneko. Motion map: image-based retrieval and segmentation of motion data. In Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation, SCA ’04, pages 259–266, Aire-la-Ville, Switzerland, Switzerland, 2004. Eurographics Association. [17] Y. Seol, J. Seo, P. H. Kim, J. P. Lewis, and J. Noh. Artist friendly facial animation retargeting. ACM Trans. Graph., 30(6):162:1–162:10, Dec. 2011. [18] H. Soyel and H. Demirel. Facial expression recognition using 3d facial feature distances. In ICIAR, pages 831–838, 2007. [19] Y. Sun and L. Yin. Facial expression recognition based on 3d dynamic range model sequences. In Proceedings of the 10th European Conference on Computer Vision: Part II, ECCV ’08, pages 58–71, Berlin, Heidelberg, 2008. Springer-Verlag. [20] H. Tang and T. Huang. 3d facial expression recognition based on automatically selected features. In Computer Vision and Pattern Recognition Workshops, 2008. CVPRW ’08. IEEE Computer Society Conference on, pages 1 –8, june 2008. [21] S. Villagrasa and A. Susin. Face! 3d facial animation system based on facs. In O. Rodr’ıguez, F. Ser’on, R. Joan-Arinyo, and E. C. J. Madeiras, J. Rodr’ıguez, editors, Proceedings of the IV Iberoamerican Symposium in Computer Graphics. Sociedad Venezolana de Computaci’on Gr’afica, DJ Editores, C.A., June 2009. [22] J. Wang, L. Yin, X. Wei, and Y. Sun. 3d facial expression recognition based on primitive surface feature distribution. In in Proc. Conf. Computer Vision and Pattern Recognition, pages 1399–1406, 2006. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/65506 | - |
| dc.description.abstract | 隨著動畫電影和電玩的興起以及電腦繪圖技術的成熟，人臉動畫需
求量越來越多。但是對動畫師來說，製作一段人臉動畫是非常辛苦而 且費時的工作。不但需要調整數十個到數百個控制器才能生成一個表 情還需要掌握表情變化的節奏才能讓動畫角色的演出栩栩如生。而且 比起肢體動畫的製作，臉部動畫更為細緻且難以調整。所以，我們提 出一個互動式人臉動畫生成系統，可以利用一些之前動畫師已經做好 的臉部動畫重新生成新的動畫。除了能輔助新手動畫師可以較快生成 品質不錯的人臉動畫之外，也能作為動畫師與動畫導演之間的溝通工 具。動畫師可以快速生成大致的動畫給導演看而省去重覆討論並生成 新的動畫的時間。為了能幫助動畫師快速在資料庫中找到想要的動畫 片段，我們提出一個新的3D人臉動畫搜尋方法。與一般人臉表情辨識 方法較為不同的是我們把動畫角色臉部的深度影像當成輸入資訊並從 中抓取深度特徵以及曲線特徵作為比較表情相似度的根據。由於我們 只取深度資訊所以系統不會限定動畫角色綁定系統的格式，因此可以 較廣泛被應用。最後，我們也對結果做了詳細的分析和比較。 | zh_TW |
| dc.description.abstract | Making facial animation of 3D characters is a difficult and time consuming
work since there are over hundreds of controllers for facial expressions, and even slight differences may create different emotions. We present an interactive facial animation creation system reusing high quality animations. This system can not only assist novices to produce facial animations more quickly, moreover, it can be used as a communication tool between artists and directors for shooting scripts without repeatedly editing. To help an artist to efficiently find the animation needed in our system, we propose a novel method employing retrieval approaches for 3D facial expressions. Different from usual face expression recognition methods, we use depth maps of character face as our input data, and extract depth features and curve features. The system doesn’t require a special rigging system, and the result is stable. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T23:47:11Z (GMT). No. of bitstreams: 1 ntu-101-R99944020-1.pdf: 15730527 bytes, checksum: d628c86ad271d05baa4cf39e2eec793e (MD5) Previous issue date: 2012 | en |
| dc.description.tableofcontents | 口試委員會審定書 i
致謝 iii 中文摘要 v Abstract vii 1 Introduction 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Problem Analysis . . . . . . . . . . . . . . . . . . . 2 1.3 Thesis Organization . . . . . . . . . . . . . . . . . .3 2 Related Works 5 2.1 Facial Animation System . . . . . . . . . . . . . . . .5 2.2 Expression Recognition . . . . . . . . . . . . . . . . 6 2.3 Animation Retrieval . . . . . . . . . . . . . . . . . .7 3 System Overview 11 3.1 System Flow Chart . . . . . . . . . . . . . . . . . . 11 3.2 System Modules . . . . . . . . . . . . . . . . . . . .13 3.2.1 Preprocessing . . . . . . . . . . . . . . . . . . . 13 3.2.2 Feature Extraction . . . . . . . . . . . . . . . . .13 3.2.3 Retrieval Method . . . . . . . . . . . . . . . . . .13 3.3 Implementation . . . . . . . . . . . . . . . . . . . .14 3.3.1 Maya Depth Camera . . . . . . . . . . . . . . . . . 14 3.3.2 Input and Output . . . . . . . . . . . . . . . . . .14 4 Method 15 4.1 Preprocessing . . . . . . . . . . . . . . . . . . . . 15 4.1.1 Histogram equalization . . . . . . . . . . . . . . .15 4.1.2 Canny Edge Detector . . . . . . . . . . . . . . . . 16 4.2 Feature Extraction . . . . . . . . . . . . . . . . . .19 4.2.1 Controller Feature . . . . . . . . . . . . . . . . .19 4.2.2 Feature-based Method . . . . . . . . . . . . . . . .19 4.2.3 Depth Feature . . . . . . . . . . . . . . . . . . . 20 4.2.4 Curve Feature . . . . . . . . . . . . . . . . . . . 20 4.3 Similarity Measures . . . . . . . . . . . . . . . . . 23 4.3.1 Keyframe Distance . . . . . . . . . . . . . . . . . 23 4.3.2 Dynamic Time Warping . . . . . . . . . . . . . . . .26 4.4 Search Method . . . . . . . . . . . . . . . . . . . . 28 4.4.1 Native Search Method . . . . . . . . . . . . . . . .28 4.4.2 Two-Stage Retrieval . . . . . . . . . . . . . . . . 29 5 Results 31 5.1 Dataset and key frames . . . . . . . . . . . . . . . .31 5.2 Retrieval Quality . . . . . . . . . . . . . . . . . . 31 5.3 User Interface . . . . . . . . . . . . . . . . . . . .36 5.4 Computation Time . . . . . . . . . . . . . . . . . . .37 6 Conclusions 39 6.1 Discussion . . . . . . . . . . . . . . . . . . . . . .39 6.2 Future Works . . . . . . . . . . . . . . . . . . . . .40 Bibliography 41 Appendix 44 Resume 49 | |
| dc.language.iso | en | |
| dc.subject | 深度資訊 | zh_TW |
| dc.subject | 動畫內容檢索 | zh_TW |
| dc.subject | 三維人臉動畫 | zh_TW |
| dc.subject | 3D Facial Animation | en |
| dc.subject | Content-based Retrieval | en |
| dc.subject | Depth map | en |
| dc.title | 基於範例為基礎的互動式人臉動畫系統 | zh_TW |
| dc.title | Example-based Interactive Facial Animation System | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 100-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 葉正聖(Jeng-Sheng Yeh),林奕成(I-Chen Lin),李明穗(Ming-Sui Lee),葉耀輝(Yao-Hui Yeh) | |
| dc.subject.keyword | 三維人臉動畫,動畫內容檢索,深度資訊, | zh_TW |
| dc.subject.keyword | 3D Facial Animation,Content-based Retrieval,Depth map, | en |
| dc.relation.page | 49 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2012-07-24 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 資訊網路與多媒體研究所 | zh_TW |
| Appears in Collections: | 資訊網路與多媒體研究所 | |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| ntu-101-1.pdf Restricted Access | 15.36 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.