近年來，由於影像處理與電腦繪圖技術的高速發展，越來越多的影像科技被應用於日常生活中，紋理生成是其中一項應用廣泛的影像科技。由於數位印花、建材磁磚、陶瓷業等產業對於大面積圖紋的需求日益漸增，然而大面積的自然紋理難以取得，因而需要利用小面積的紋理影像樣本，透過智慧運算方式產生紋理結構相似、但又不完全相同的高解析紋理影像。
因此，本研究基於紋理變置概念設計一套圖紋生成演算法，並據此開發軟體系統。此技術對於自然紋理影像如石紋、木紋進行紋理變置，產生與原圖紋理元素相似，但細節分布相異的新紋理影像。該演算法含底圖、裂紋、細紋、及合成四大處理程序：底圖利用影像修補(Image In-painting)技術來填補被挖除的裂紋區域；裂紋透過K平均法對裂紋分群，為了使變置的裂紋分布均勻，對不同的裂紋排佈組合評估其均勻度，選擇較佳的組合進行影像合成；影像細紋透過高通濾波萃取；最後合成所有圖層生成新的紋理影像。測試結果顯示，本研究設計與優化的演算法確實能夠生成與樣本影像相似的石紋與木紋。然而，生成的影像是否理想？目前仍缺乏客觀的量化評估指標。

With rapid development of computer graphics and image processing technologies, texture synthesis technology is widely used in our daily life. Due to the increasing demand of large format digital printing for building materials tiles, ceramics, carpets and textile, large amount of natural texture images are needed. However, they are difficult to be obtained. Therefore, there is a need to use small texture image samples to generate large coherent and non-repetitive material images through intelligent operations.
In this study, texture generation algorithms for irregular patterns based on texture rearrangement were proposed, which transform the texture of natural image samples such as stone grain and wood grain to generate new texture images which are similar but different to the original image in appearance. The workflow of the proposed algorithms is divided into four parts: background image, crack, fine lines and image synthesis. The cracked areas of the background image are repaired using in-painting technologies. Through k-means clustering, cracks are sub-divided and randomly distributed. The uniformity of the cracks of the new image is optimized. Image details are extracted from the sample image by a high-pass filter. Finally, all the image layers are combined to transform the texture into a new form. A practical software system was developed based on the algorithms. Testing results showed that the proposed methods could generate texture images with similar visual appearance compared to the input image samples.

[1]J. R.Bergen , M. S.Landy, "Computational Modeling of Visual Texture Segregation ", Comput. Model. Vis. Process., pp. 253-271, 1991.
[2]Y. Rubner, C. Tomasi, Texture metric, IEEE Conference: Systems, Man, and Cybernetics, 1998.
[3]C. Archibaid, Emil Petriu, Advances in Machine Vision: Strategies and Applications, World Scientific Publishing, pp.197, 1992
[4]W. C.Lin, J.Hays, C.Wu, V.Kwatra, Y.Liu, ‘A comparison study of four texture synthesis algorithms on near-regular textures’, ACM SIGGRAPH 2004 Posters, SIGGRAPH 2004, p. 16, 2004.
[5]R. M.Haralick, I.Dinstein, and K.Shanmugam, ‘Textural Features for Image Classification’, IEEE Trans. Syst. Man Cybern., vol. SMC-3, no. 6, pp. 610–621, 1973.
[6]C. G.Eichkitz, J.Davies, J.Amtmann, M. G.Schreilechner, and P.deGroot, ‘Grey level co-ocurrence matrix and its application to seismic data’, First Break, vol. 33, no. March, pp. 71–77, 2015.
[7]M. M. Galloway, Texture classification using gray Level Length, Computer Graphics and Image Processing, 4, pp. 172-179, 1975.
[8]章毓晉,"圖像工程",清華大學出版社有限公司, 第九章p221-224頁, 2005.
[9]R.W. Conners, C.A. Harlow, Toward a structural textureal analyzer based on statistical methods, Computer Graphics and Image Processing, Vol.12, pp 224-256, 1980.
[10]T. Randen, J.H. Husoy, Filtering for texture classification: A comparative study, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, pp 291-310 ,1999.
[11]P. J.Burt and E. H.Adelson, ‘The Laplacian Pyramid as a Compact Image Code’, in Fundamental Papers in Wavelet Theory, vol. 31, no. 4, Princeton: IEEE Transactions on Communications, 1983, pp. 532–540
[12]G.R. Cross, A.K. Jain, Markov random field texture model, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 5, no. 1, pp 25-39 , 1983.
[13]A P. Pentland, Fractal based description of natural scenes, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 6, no. 6, pp. 661-674 , 1984.
[14]Alexei A. Efros and Thomas K. Leung, Texture synthesis by non-parametric sampling, IEEE International Conference on Computer Vision , 1999.
[15]L. Liang, C. Liu, Y. Q.Xu, B. Guo, H. Y.Shum ,Real-time texture synthesis by patch-based sampling, ACM Transactions on Graphics, Vol. 20, no. 3, pp 127-150 , 2001.
[16]Andrew Nealen and Marc Alexa, Hybrid texture synthesis, Eurographics Symposium on Rendering , 2003.
[17]R. Szeliski, Computer Vision: Algorithms and Applications, Springer, pp.93 (2011).
[18]A. A.Efros, W. T.Freeman, ‘Image quilting for texture synthesis and transfer’, Proc. 28th Annu. Conf. Comput. Graph. Interact. Tech. SIGGRAPH 2001, pp. 341-346, 2001.
[19]T. Briand, et al., The Heeger-Bergen pyramid-based texture synthesis algorithm, Image Processing On Line, 4, pp. 276-299 , 2014.
[20]H.C. Hsin, T. Y .Sung, Y. S .Shieh, and Cattani, A new texture synthesis algorithm based on wavelet packet tree, Mathematical Problems in Engineering, 2012.
[21]L.Y. Wei and M. Levoy, Fast texture synthesis using tree-structured vector quantization, SIGGRAPH 2000 Conference Proceedings, pp 479-488, 2000.
[22]M. Ashikhmin, Synthesizing natural texture, ACM Symposium on Interactive 3D Graphics, pp.217-226 , 2001.
[23]L.A. Gatys, A.S. Ecker, Matthias Bethge, Texture Synthesis Using Convolutional Neural Networks, NIPS'15 Proceedings of the 28th International Conference on Neural Information Processing Systems, pp. 262-270, 2015.
[24]R. Szeliski, Computer Vision: Algorithms and Applications, Springer, pp.93, 2011.
[25]A. A.Efros and W. T. Freeman, ‘Image quilting for texture synthesis and transfer’, Proc. 28th Annu. Conf. Comput. Graph. Interact. Tech. SIGGRAPH 2001, pp. 341-346, 2001.
[26]M. Sezgin and B. Sankur Survey over image thresholding techniques and quantitative performance evaluation, Journal of Electronic Imaging, Vol. 13, no. 1, pp.146-165, 2004.
[27]S. Esedoglu and J. Shen, Digital inpainting based on the Mumford–Shah–Euler image model, Euro. Jnl of Applied Mathematics, vol. 13, no. 1, pp. 353-370 , 2002.
[28]R. Szeliski, Computer Vision: Algorithms and Applications, Springer, pp. 93 ,2011.
[29]D. Ruprecht, Heinrich Muller, Image Warping with Scattered Data Interpolation, IEEE Computer Graphics and Applications, pp.37-43 , 1995.
[30]P. Drineas, A. Frieze, R. Kannan, S. Vempala and V. Vinay, Clustering large graphs via the singular value decomposition, Machine Learning, 56, pp. 9-33 , 2004.
[31]R. Haralick and L. Shapiro Computer and Robot Vision, Vol. 1, Addison-Wesley Publishing Company, pp.346-351 , 1992.
[32]魏碩廷, 陳鴻興, 徐明景, 李文淵, 謝翠如, 吳瑞卿, 孫沛立. "色彩新論 -從心理設計到科學應用", 五南圖書, pp.178-223 , 2018.
[33]胡國瑞, 孫沛立, 徐道義, 陳鴻興, 黃日鋒, 詹文鑫, 羅梅君. "顯示色彩工程學", 全華圖書, pp.130-156 , 2013.
[34]M. P.Sampat, Z.Wang, S.Gupta, A. C.Bovik, and M. K.Markey, ‘Complex wavelet structural similarity: A new image similarity index’, IEEE Trans. Image Process., vol. 18, no. 11, pp. 2385–2401, 2009.