臺灣博碩士論文加值系統

NPR(Non-photorealistic Rendering)主要目的是透過不同的演算法，由電腦自動產生各種不同繪畫風格的影像，目前的NPR系統礙於演算法的計算速度，多數都僅針對靜止的單一圖片進行處理，故本研究試圖對二維空間中已發展的NPR演算法做延伸，在空間領域以及MPEG壓縮領域上分別提出不同的加速效能方式。在空間方面針對不同的範圍套用NPR演算法，如臉部、膚色區塊等有意義的部份；而在MPEG壓縮格式上，透過MPEG中的I,P,B-frame不同的特性，視影像中的差異度做不同的套用方式，以求改進NPR演算法效能，達到即時產生NPR特效的影片或動畫，進一步應用於多媒體娛樂以及人機互動機制。

Recently, various non-photorealistic rendering (NPR) techniques have been developed for computers to generate images of different artistic styles automatically. Due to the complexity of the algorithms, however, most NPR methods are limited to the processing of static images. It is the objective of this thesis to extend and improve existing NPR techniques to enable near real-time processing of video.

The enhancement can be achieved in both spatial and compressed domains. In the spatial domain, computational complexity is reduced by applying NPR only to selective regions in the images, e.g., face or skin area. In the MPEG compressed domain, by exploiting the relationship among I, P, and B frames, different strategies can be developed to increase the efficiency of the NPR algorithm. Experimental results have demonstrated the efficacy of the proposed methods and validated the near real-time creation of NPR video effects.

第一章 緒論
1.1 研究動機
1.2 NPR（Non-photorealistic Rendering）簡介
1.3 研究目標
1.4 研究架構
1.5 論文章節架構

第二章 相關研究
2.1 NPR研究議題
2.2 NPR效果
2.2.1模擬水彩畫NPR
2.2.2分層處理(Multi-layer,Hierarchical,Coarse-to-fine
Processing)
2.2.3 分割處理(segmentation)
2.3 NPR動畫
2.3.1二維NPR動畫
2.3.2局部區塊NPR
2.4 Real-time NPR動畫

第三章 加速空間領域上的NPR演算法
3.1 整張影像(Full frame)
3.2 部分影像
3.2.1邊緣影像
3.2.2 移動區塊
3.2.3 背景
3.2.4 隨機存取
3.3 偵測區塊
3.3.1 臉部區塊
3.3.2 膚色區塊
3.4 統計與分析

第四章 加速壓縮領域上的NPR演算法
4.1 MPEG壓縮原理
4.2 在壓縮領域套用NPR演算法方式
4.3 於DCT domain的特效
4.3.1改變DC係數
4.3.2 AC Frequency Filter
4.4將I,P,B-frame轉回空間域套用NPR演算法
4.4.1 I-frame套用NPR演算法
4.4.2對P,B-frame 套上NPR演算法
4.5統計分析

第五章 結論與未來方向
5.1結論
5.2 未來方向

參考文獻

[1] Sony EyeToy, URL: <http://www.eyetoy.com/>
[2] Apple ToySight, URL: <http://toysight.com/>
[3] DDplayCam, URL: <http://www.ddplaycam.tv/>
[4] Stuart Green, Introduction to non-photorealistic rendering,
SIGGRAPH 1999 Non-Photorealistic Rendering Course Notes,
15-18, Aug 1999.
[5] Amy Gooch, Bruce Gooch, Peter Shirley, Elaine Cohen, A
non-photorealistic lighting model for automatic technical
illustration. Proceedings of the 25th annual conference on
Computer graphics and interactive techniques, 447-452, 1998.
[6] Cassidy J. Curtis, Sean E. Anderson, Joshua E. Seims, Kurt W.
Fleischery, David H. Salesin, Computer-Generated Watercolor,
Proceedings of the 24th annual conference on Computer
graphics and interactive techniques, 421-430, August 1997.
[7] Aaron Hertzmann, Painterly Rendering with Curved Brush
Strokes of Multiple Sizes, Proceedings of the 25th annual
conference on Computer graphics and interactive
techniques,453-460, 1998.
[8] Youngsup Parky and Kyunghyun Yoonz, Adaptive Brush Stroke
Generation for Painterly Rendering, Proceedings of
Eurographics 2004, 65-68, August, 2004.
[9] Daniel Sperl, Realtime Painterly Rendering for Animation,
Proceedings of SIGGRAPH 96,477- 484, 1996.
[10] L. Markosian, M. Kowalski, S. Trychin, and J. Hughes,
Real-Time Non-Photorealistic Rendering, Proceeding of
SIGGRAPH 97, August 1997.
[11] Barbara J. Meier, Painterly Rendering for Animation,
Proceedings of the 23rd annual conference on Computer
graphics and interactive techniques, 477-484, 1996.
[12] Jue Wang, Yingqing Xu, Heung-Yeung Shum and Michael F.
Cohen, Video Tooning, ACM Transactions on Graphics, Volume
23, Issue 3, August 2004.
[13] Peter Litwinowicz, Processing Images and Video for An
Impressionist Effect, Proceedings of SIGGRAPH 97, 407-414,
August 1997.
[14] Aaron Hertzmann Ken Perlin, Painterly Rendering for Video
and Interaction, First International Symposium on
NonPhotorealistic Animation and Rendering, 7-12, June 2000.
[15] J. P. Collomosse1, D. Rowntree2 and P. M.
Hall1.2003.Cartoon-style Rendering of Motion from Video.
Vision, Video and Graphics,117-124, July 2003.
[16] Byungmoon Kim and Irfan Essa, Video-based Nonphotorealistic
and Expressive Illustration of Motion, CGI (Computer
Graphics International) 2005.
[17] Nelson S.-H. Chu Chiew-Lan Tai, Real-Time Ink Dispersion in
Absorbent Paper, ACM Transactions on Graphics (SIGGRAPH 2005
issue), Vol. 24, No. 3, August 2005.
[18] Michael Haller and Daniel Sperl.2004.Real-Time Painterly
Rendering for MR Applications. Proceedings of the 2nd
international conference on Computer graphics and
interactive techniques in Australasia and Southe East Asia,
30-38, 2004.
[19] NPR Examples：
URL:<http://ise.stanford.edu/class/ee368a_proj00/project18/index.html>
[20] Intel Open Source Computer Vision Library
URL:<http://www.intel.com/research/mrl/research/opencv/>
[21] Demo video WebSite
URL:<http://140.119.164.91/liang/NPR.htm>
[22] P. Viola and M. Jones.2001.Rapid object detection using a
boosted cascade of simple features. Proceedings of IEEE
Computer Society Conference on Computer Vision and Pattern
Recognition, December, 2001.
[23] JPEG Tutorial,
URL:<http://www.imaging.org/resources/jpegtutorial/index.cfm>
[24] Dali library,
URL:<http://www.cs.cornell.edu/dali/>
[25] MPEG Technology Overview,
URL:<http://www.hongik.edu/~sjpark/mpeg.htm>