臺灣博碩士論文加值系統

本文主要以影像分割為基礎，藉由參考彩色影像上的色彩來對灰階影像自動作著色。有別於傳統以像素為比對單位，為了使著色後色彩可達到空間上的一致性，首先分別對彩色影像與灰階影像作平均值位移的區域分割，以取得著色的基本單位。為了決定灰階影像像素參考的來源，利用區域內像素分群方法計算每一區域多個主要亮度的平均值，並透過單向郝思多夫距離的多數值比對，以增加區域比對的正確性。最後，依據區域內像素紋理的配對，賦予灰階影像適切的色彩以完成上色的目標。本文著重於一個全自動化的著色過程，期間包括影像分割、區塊匹配、比對著色等一連串的動作，除了可減少使用者介入的時間與人力外，並能自然呈現著色後的視覺感受。

The main objective of this thesis is to colorize grayscale images automatically by reference to the color information in another color image. Unlike using the traditional pixel-by-pixel matching algorithm, the mean-shift image segmentation is firstly adopted in color image and grayscale image respectively to separate into semantic regions as a basic unit in colorization. Since all pixels inside one region have similar color and texture features, the colorization can achieve the spatial coherence. In order to determine the referring source of grayscale image, use the clustering method in each region to find the main multi-luminances, and match these luminances by the one-way Hausdorff distance to increase the correctness of region matching. Finally, according to the texture feature in a local region, give every pixel in grayscale image an appropriate color to finish the coloring goal. This proposed method is a fully automatic coloring process, including image segmentation, region matching, matching colorization, and a series of actions. Such an approach not only can reduce human intervention and computational time, but also can display a natural colorization fit as human visual experience.

章節目錄
摘要II
AbstractIII
目錄IV
圖目錄VI
表目錄IX
第1章 簡介1
第2章 相關技術研究3
2.1 以彩色參考影像為基礎的著色演算法3
2.1.1 彩色影像間的色彩轉換3
2.1.2 灰階影像的著色演算法5
2.1.3 藉由影像遮罩的著色演算法6
2.1.4 快速著色演算法7
2.2 以使用者塗繪為基礎的著色演算法8
2.2.1 使用最佳化的著色演算法9
2.2.2 使用色彩混合的快速影像與視訊著色演算法10
2.3 以影像分割為基礎的著色演算法11
第3章 基於影像分割之自動著色方法14
3.1 影像分割15
3.1.1 k-means影像分割法16
3.1.2 平均值位移影像分割法18
3.2 影像匹配20
3.3 灰階影像比對著色21
3.3.1 非影像分割之點對點著色方法22
3.3.2 非影像分割之遮罩比對著色方法23
3.3.3 影像分割之遮罩統計著色方法24
3.3.4 影像分割之區域統計著色方法25
第4章 實驗結果29
4.1 影像分割測試29
4.2 影像匹配測試36
4.3 影像著色測試38
4.3.1 Levin顏色擴散法實驗38
4.3.2 點對點與遮罩對遮罩著色法實驗39
4.3.3 遮罩資訊統計著色與區域內k-means資訊統計著色實驗41
第5章 結論48
參考文獻49
圖目錄
圖一、彩色影像間的色彩轉換4
圖二、lαβ色彩空間4
圖三、灰階影像著色6
圖四、Chen著色演算法(花朵)6
圖五、Chen著色演算法(人臉)7
圖六、Levin著色演算法9
圖七、Yatziv著色演算法(蔬果)11
圖八、Yatziv著色演算法(河岸)11
圖九、Irony的著色演算法比較圖13
圖十、著色演算法流程圖15
圖十一、k-means資料分群17
圖十二、k-means影像分割17
圖十三、平均值位移18
圖十四、彩色影像分割19
圖十五、灰階影像分割20
圖十六、簡單的影像著色法21
圖十七、非影像分割之點對點比對著色23
圖十八、非影像分割之遮罩比對著色24
圖十九、影像分割之遮罩資訊統計著色25
圖二十、階層式比對著色27
圖二十一、區域內k-means資訊統計著色28
圖二十二、場景單純之彩色影像分割結果29
圖二十三、場景單純之灰階影像分割結果30
圖二十四、場景複雜之彩色影像分割結果30
圖二十五、場景複雜之灰階影像分割結果31
圖二十六、彩色影像分割結果31
圖二十七、彩色影像取出獨立的區域(n = 2)32
圖二十八、彩色影像取出獨立的區域(n = 3)32
圖二十九、彩色影像取出獨立的區域(n = 4)32
圖三十、灰階影像分割結果33
圖三十一、灰階影像取出獨立的區域(n = 2)33
圖三十二、灰階影像取出獨立的區域(n = 3)33
圖三十三、灰階影像取出獨立的區域(n = 4)34
圖三十四、彩色影像分割(n = 2)34
圖三十五、彩色影像分割(n = 3)34
圖三十六、彩色影像分割(n = 4)35
圖三十七、灰階影像分割(n = 2)35
圖三十八、灰階影像分割(n = 3)35
圖三十九、灰階影像分割(n = 4)36
圖四十、影像分割區域比較36
圖四十一、影像分割結果37
圖四十二、灰階影像分割區塊圖37
圖四十三、彩色影像分割區塊圖37
圖四十四、k-means影像匹配結果38
圖四十五、Levin著色演算法39
圖四十六、Levin著色法塗繪區域多寡比較39
圖四十七、點對點的比對著色法40
圖四十八、遮罩對遮罩的比對著色法40
圖四十九、遮罩對遮罩的比對著色法41
圖五十、使用平均值位移分割法41
圖五十一、使用遮罩統計鄰域資料比對著色結果42
圖五十二、使用平均值位移分割法42
圖五十三、使用遮罩統計鄰域資料比對著色結果42
圖五十四、k-means資訊統計比對著色結果43
圖五十五、k-means資訊統計比對著色結果43
圖五十六、k-means資訊統計比對著色結果44
圖五十七、使用平均值位移分割法44
圖五十八、k-means資訊統計比對著色結果45
圖五十九、灰階目標影像與彩色參考影像45
圖六十、k-means資訊統計比對著色結果46
圖六十一、k-means影像分割法與平均值位移影像分割法著色後比較47
表目錄
表一、執行時間比較8

一、中文部份
[1]王友俊，以影像處理方法分割相互接觸之近似橢圓，台灣大學生物產業機電工程學研究所博士學位論文，民國95年。
[2]王宗銘、游世安、黃明隆、洪國綸、李佳豐，有效基於模糊分割技術的中國水墨著色演算法，全國計算機會議，民國94年。
二、英文部份
[1]A. Hertzmann, C. E. Jacobs, N. Oliver, B. Curless and D. H. Salesin, “Image Analogies,” Proceedings of SIGGRAPH, pp. 327-340, Los Angeles, August 12-16, 2001.
[2]A. Levin, D. Lischinski and Y. Weiss, “Colorization using Optimization,”Proceedings of SIGGRAPH, July 2004.
[3]Anjin Park, Jungwhan Kim, Seungki Min, Sungju Yun, and Keechul Jung, “Graph Cuts-Based Automatic Color Image Segmentation,” Proceedings of DICTA, 2008.
[4]B. A. Attea and A. D. Aboud, “Evolutionary Colorization of Grayscale Images,” Proceedings of IEEE International Conference on Computer Systems and Applications, pp. 786-791, March 2006.
[5]C. Christoudias, B. Georgescu and P. Meer, “Synergism in Low-Level Vision,” 16th International Conference on Pattern Recognition, vol. 4, pp. 150-155, Canada, August 2002.
[6]D. Comaniciu and P. Meer, “Mean Shift: A Robust Approach toward Feature Space Analysis,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 24, no. 5, pp. 603-619, May 2002.
[7]D. L. Ruderman, T. W. Kalvin and C. C. Chiao, “Statistics of Cone Responses to Natural Images: Implications for Visual Coding,” Journal of the Optical Society of America A, vol. 15, no. 8, pp. 2036-2045, 1998.
[8]D. Sýkora, J. Buri?nek and J. Z?ra, “Unsupervised Colorization of Black-and-White Cartoons,” Proceedings of 3rd Int. Symp. NPAR, Annecy, France, pp. 121-127, June 2004.
[9]D.E. Ilea and P.F. Whelan, “CTex-An Adaptive Unsupervised Segmentation Algorithm Based on Color-Texture Coherence,” IEEE Transactions on Image Processing, vol. 17, no. 10, pp. 1926-1939, October 2008.
[10]Dongdong Nie, Qinyong Ma, Lizhuang Ma and Shuangjiu Xiao, “Optimization based Grayscale Image Colorization,” Pattern Recognition Letters, vol. 28, no. 12, pp. 1445-1451, September 2007.
[11]E. Reinhard, M. Ashikhmin, B. Gooch and P. Shirley, “Color Transfer between Images,”IEEE Computer Graphics and Applications, vol. 21, no. 5, pp. 34-40, 2001.
[12]G. Di Blasi and D. Reforgiato, “Fast Colorization of Gray Images,” Proceedings of Eurographics, 2003.
[13]Huachun Tan and Yu-Jin Zhang, “Computing Eigenface from Edge Images for Face Recognition Based on Hausdorff Distance,” Fourth International Conference on Image and Graphics, pp. 639-664, August 2007.
[14]K. Y. Ni, B. W. Hong, S. Soatto and T. F. Chan, “Unsupervised multiphase segmentation: A recursive approach,” Computer Vision and Image Understanding, vol. 113, no. 4, pp. 502-510, April 2009.
[15]Liron Yatziv and Guillermo Sapiro, “Fast Image and Video Colorization Using Chrominance Blending,” IEEE Transactions on Image Processing, vol. 15, no.5, pp. 1120-1129, May 2006.
[16]M. ?zden and E. Polat, “Image Segmentation using Color and Texture Features,” Proceedings of EUSIPCO, September 2005.
[17]M. G. Ross and L. P. Kaelbling, “Segmentation According to Natural Examples: Learning Static Segmentation from Motion Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 4, pp. 661-676, April 2009.
[18]P. Meer and B. Georgescu, “Edge Detection with Embedded Confidence,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 12, pp. 1351-1365, 2001.
[19]R. Irony, D. Cohen-Or and D. Lischinski, “Colorization by Example,” Proceedings of Eurographics Symposium on Rendering, 2005.
[20]Simon Premože and William B. Thompson, “Automated Coloring of Panchromatic Orthoimagery,” Proceedings of the ICA Mountain Cartography Workshop, May 2002.
[21]T. Horiuchi and S. Hirano, “Colorization Algorithm for Grayscale Image by Propagating Seed Pixels,” Proceedings of the IEEE Int. Conf. Pattern Recognition, pp. 457-460, 2003.
[22]T. Welsh, M. Ashikhmin and K. Mueller, “Transferring Color to Greyscale Images,”Proceedings of SIGGRAPH, July 2002.
[23]Tongbo Chen, Yan Wang, Volker Schillings and Christoph Meinel, “Grayscale Image Matting And Colorization,” Proceedings of ACCV, 2004.
[24]U. Lipowezky, “Grayscale Aerial and Space Image Colorization Using Texture Classification,” Pattern Recognition Letters, vol. 27, no. 4, pp. 275-286, 2006.
[25]Yung-Yu Chuang, Brian Curless, David H. Salesin and Richard Szeliski, “A Bayesian Approach to Digital Matting,” Proceedings of IEEE Computer Vision and Pattern Recognition, 2001.