臺灣博碩士論文加值系統

將一張影像的顏色風格套用到視訊上是一個極具前瞻性與實用性的技術。通常在視訊的處理中，我們可以將視訊視為一串影像連結而成的串列，然後以單張影像的色彩轉換演算法對每一張影格進行處理。然而因為提供色彩的影像與視訊影格場景內容的差異，此種方法所得到的視訊品質通常不佳，而且缺乏平順感與協調感。雖然我們可以應用『區塊指定（swatch mechanism）』的方式來改善色彩轉換的品質，但是這種方式用在視訊上所需耗的人力相當可觀。為了解決這個問題，我們提出一個『可調適性影格傳遞（Adaptive Frame Pass）』的方法來解決這個問題。我們的方法是將視訊影格的變化也參考進色彩轉換參數中，所以對於每一個影格，我們都可以套用一個相對應較佳的色彩轉換參數。此外，我們也探討以目前數位影像／視訊常用的色彩空間—YCbCr，應用於色彩轉換上所發生的問題與解決方案。根據我們的實驗與測試，大多數的測試者認為經由我們的方法產生的視訊比用單張影像轉換方法來得平順、協調與自然，而我們所提出的平順度評估曲線亦輔以證實這個結果。

Applying one image’s color style to a video is a promising technology for video applications. One simple solution is treating a video as a sequence of image frames and then applying the image-based color transfer algorithm on every frame. However, the transferred quality as a whole usually lacks of smoothness and harmony in color style, because the scene of the destination frame varies and is gradually different from that of the color source image (for example, during a video with panning or zooming operation). Although manually specifying the similar regions before transferring (the swatch mechansim) can get better quality, it is not suitable for our video case due to the high cost of manpower involved. To solve the visual defects and ease the cost, we propose an Adaptive Frame Pass (AFP) algorithm that is based on ιαβ color space to adaptively consider the processing parameters from not only the color source image, but the destination frame. Besides, we also discuss the problem when we apply color transfer mechanism to YCbCr color space, the working color space of JPEG and MPEG. We propose an objective “evaluation sequence” measurement to evaluate the smoothness quality of processed video shot. The experimental result shows that our approach produces perceptually more coherent, smooth, natural color style in video than the image-based approach does.

論文摘要 I
Abstract II
Contents III
List of Figure V
List of Table VII

Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Related work 4
1.3 Report Organization 5
Chapter 2 Background 6
2.1 Color Space 6
2.2 Image Based Color Transform 8
Chapter 3 Algorithm for Color Transfer on Video 13
3.1 Basic Framework for Video Color Transfer 13
3.2 Direct Video Transfer (Extension Of Reinhard’s algorithm (EOR)) 14
3.3 Frame Pass Algorithm 16
3.4 Adaptive Frame Pass algorithm 19
Chapter 4 Quality Evaluation 25
4.1 Subjective evaluation mechanism 25
4.2 Objective evaluation mechanism 26
Chapter 5 System Implementation 30
5.1 Image Color Transfer 30
5.2 Color Space Analysis 31
5.3 Video Color Transfer 33
5.4 Video Evaluation 34
Chapter 6 Experimental Results and Discussion 36
6.1 Color Transfer in Different Color Spaces 36
Chapter 7 Conclusion and Future Work 49
7.1 Conclusion 49
7.2 Future Work 49
Reference 50
Color Transfer 50
Image/Color Processing 50
Color Space 51
System Implementation 51
Quality Evaluation 51

Color Transfer
[CSN2003]Chang, Y., Saito, S., and Nakajima, M. “A framework for transfer colors based on the basic color categories” Computer Graphics International, 2003, pp.176-183
[CUS2004]Youngha Chang, Keiji Uchikawa, Suguru Saito. “Example-Based Color Stylization Based on Categorical Perception”, Proceedings of the 1st Symposium on Applied perception in graphics and visualization, ACM, August 2004. pp. 91-98.
[DJJ2004]Daniel Sýkora, Jan Buriánek, Jiří Žára. “Animation: Unsupervised colorization of black-and-white cartoons”, Proceedings of the 3rd international symposium on Non-photorealistic animation and rendering, ACM, June 2004, pp. 121-127.
[GD2003]Gary R. Greenfield, Donald H. House. “Image Recoloring Induced by Palette Color Associations”, Journal of WSCG, 2003.
[PDZ2004]Zhigeng Pan, Zhaohua Dong, Mingmin Zhang. “A New Algorithm for Adding Color to Video or Animation Clips” Journal of WSCG, 2004, Vol.12, No.1-3, pp. 515-520.
[RAGS2001] Reinhard, E., Ashikhmin, M., Gooch, B., Shirley, P. "Color Transfer Between Images" IEEE Computer Graphics and Applications, 2001, v. 21, no. 5 (special issue on Applied Perception), pp. 34-41.
[T2005]Toet, Alexander. “Colorizing single band intensified nightvision images” Displays, January 2005, Vol. 26, Issue 1, pp. 15-21.
[WAM2002]Welsh,T., Ashikhmin, M., Mueller, K. "Transferring Color to Grayscale Images" TOG special issue on ACM SIGGRAPH 2002, v.20. no. 3, pp. 277-280.
[WH2004]Chung-Ming Wang, Yao-Hsien Huang. “A Novel Color Transfer Algorithm for Image Sequence” Journal of Information Science and engineering, 2004, Vol.20, No.6, pp. 1039-1056
Image/Color Processing
[LL2003]Jia-Bin Liou, Chi-Fang Lin. “A Sequence of Images Enhancing Method Using Dichotomy Histogram Equalization and Color Transfer Techniques”, Master Thesis, Yuan-Ze University, 2003.
[JJ2004]Jianfeng Yin, Jeremy R. Cooperstock. “Color Correction Methods with Applications to Digital Projection Environments” Journal of WSCG, 2004, Vol. 12, No. 1-3, pp. 499-506.
Color Space
[DTC98]Daniel L. Ruderman, Thomas W. Cronin, Chuan-Chin Chiao. “Statistics of cone responses to natural images: Implications for visual coding.” J. Optical Soc. of America, 1998, v. 15, no. 8, pp. 2036-2045.

System Implementation
[WCC2003]Chin-chia Wu. TMyAVI_Example(AVI module for Borland C++ Builder) http://delphi.ktop.com.tw/topic.asp?topic_id=41765
Quality Evaluation
[Nicolls]Fred Nicolls. “The human visual system.” http://www.dip.ee.uct.ac.za/~nicolls/lectures/eee401f/hvs.pdf
[DDML2002]Delaigle, J.F. Devleeschouwer, C. Macq, B. Langendijk, L. Lab.”human Visual System Features Enabling Watermarking”, Belgium; Multimedia and Expo, 2002. ICME '02. Proceedings. 2002 IEEE International Conference on Volume 2, August, 2002 pp. 489-492.
[Z98]Zhou Wang, "Blind Measurement of Blocking Artifacts in Images-Literature survey", Video Processing, EE381K-14 Multidimensional Digital Signal Processing - Fall 1998 Projects
[EF95]Eskicioglu, A.M. Fisher, P.S. "Image quality measures and their performance", Communications, IEEE Transactions, December, 1995, Volume: 43, Issue: 12, pp. 2959-2965