基于梯度的块尺寸自适应Wang Tiles纹理合成算法

基于Wang Tiles纹理合成算法原理, 研究纹理图像梯度结构信息、纹理块自适应尺寸以及Tiles集合制作方法对纹理合成质量及合成时间的影响。在判断两纹理块相似程度时, 将纹理块的颜色误差和梯度信息同时作为纹理块相似程度的度量标准, 其合成效果优于只考虑颜色误差的传统纹理合成算法。同时, 使用优化后的纹理块尺寸进行纹理合成, 能缩短纹理合成时间。另外, 采用改进后的Tiles集合能取得比传统方法更好的合成效果。实验证明, 与基于Wang Tiles的传统算法相比, 改进算法在取得较好合成质量的同时, 能提高纹理合成的速度。

Abstract

Based on the Wang Tiles texture synthesis algorithm, the effects of texture gradient structure information, texture blocks with adaptive size, and Tile set generation method on the texture synthesis quality and time are studied. The color error and gradient information of the texture blocks are both used as the standard to measure the similarity of two blocks in the texture synthesis algorithm. It is better than the traditional texture synthesis algorithm, which only considers the color error to determine the similarity of two texture blocks. Meanwhile, using the optimized block size for texture synthesis, the texture synthesis time is reduced. In addition, using the improved Tile set to achieve texture synthesis, we can achieve better results than those of the traditional methods. Experimental results show that this algorithm can improve both the quality and the speed of texture synthesis, compared with the traditional Wang Tile-based algorithm.

参考文献

[1] Cohen M F, Shade J, Hiller S, et al. Wang Tiles for image and texture generation［C］. Annual Symposium of the ACM SIGGRAPH, San Diego, CA, USA, 2003: 287-294.

[2] Ng T Y, Wen C, Tan T S, et al. Generating an ω-tile set for texture synthesis［C］. Proceedings of Computer Graphics International Conference, 2005: 177-184.

[3] Kwatra V, Schoedl A, Essa I, et al. Graphcut textures: image and video synthesis using graph cuts［C］. Proceedings of ACM Transactions on Graphics, SIGGRAPH 2003, San Diego, CA, USA, 2003: 277-286.

[4] Xue F, Zhang Y S, Jiang J L, et al. Real-time texture synthesis using s-tile set［J］. Journal of Computer Science and Technology, 2007, 22(4): 590-596.

[5] 刘骥, 朱庆生, 曾令秋, 等. 基于PSO的Wang Tiles纹理合成［J］. 计算机工程与应用, 2010, 46(30): 159-162.

Liu Ji, Zhu Qingsheng, Zeng Lingqiu, et al. PSO based Wang Tiles texture synthesis［J］. Computer Engineering and Applications, 2010, 46(30): 159-162.

[6] 王继东, 庞明勇, 赵瑞斌. 旋转的Wang Tiles 纹理合成算法［J］. 中国图象图形学报, 2013, 18(1): 49-54.

Wang Jidong, Pang Mingyong, Zhao Ruibin. Texture synthesis using rotational Wang Tiles［J］. Journal of Image and Graphics, 2013, 18(1): 49-54.

[7] Zu Y R, Duan H C. Texture synthesis using diagonal quilting Wang Tiles［C］. Proceedings of the 2013 9th International Conference on Computational Intelligence and Security, 2013: 836-840.

[8] Wang H. Proving theorems by pattern recognition-II［J］. Bell Labs Technical Journal, 1961, 40(1): 1- 41.

[9] Efros A A, Freeman W T. Image quilting for texture synthesis and transfer［C］. Proceeding of the 28th Annual Conference on Computer Graphics and Interactive Techniques, New York, USA, 2001: 341-346.

[10] 刘大礼, 王允, 邱丽荣, 等. 差动共焦显微边缘轮廓检测与定位方法［J］. 中国激光, 2014, 41(10): 1008001.

Liu Dali, Wang Yun, Qiu Lirong, et al. Differential confocal microscopy for edge contour detection and location［J］. Chinese J Lasers, 2014, 41(10): 1008001.

[11] 谭永前, 曾凡菊, 岳莉, 等. 一种改进的纹理图像合成算法［J］. 激光与光电子学进展, 2016, 53(12): 121001.

Tan Yongqian, Zeng Fanju, Yue Li, et al. An improved texture image synthesis algorithm［J］. Laser and Optoelectronics Progress, 2016, 53(12): 121001.

[12] 余临倩, 覃亚丽, 张晓帅. 基于字典学习的梯度重权非局部平均的强噪声图像去噪［J］. 激光与光电子学进展, 2016, 53(11): 111002.

Yu Linqian, Qin Yali, Zhang Xiaoshuai. Denoising of strong noisy image via gradient reweighted non-local averaging over learned dictionaries［J］. Laser & Optoelectronics Progress, 2016, 53(11): 111002.

[13] 陈志明. 基于多阶环形结构量子算法的图像纹理检测研究［J］. 激光与光电子学进展, 2016, 53(11): 111101.

Chen Zhiming. Image texture detection based on multi-order ring structure quantum algorithms［J］. Laser & Optoelectronics Progress, 2016, 53(11): 111101.

[14] 聂俊岚, 王艳芬. 块纹理合成中纹理块尺寸自适应算法［J］. 计算机辅助设计与图形学学报, 2008, 20(10): 1353-1357.

Nie Junlan, Wang Yanfen. An algorithm for adaptively selecting the size of the candidate patches in patch based texture synthesis［J］. Journal of Computer-Aided Design and Computer Graphics, 2008, 20(10): 1353-1357.

[15] Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification［J］. IEEE Transections on Systems, Man and Cybernetics, 1973, SMC-3(6): 610-621.

[16] Chen H H, Hu W G, Lai D J, et al. Nonemptiness problems of Wang Tiles with three colors［J］. Theoretical Computer Science, 2014, 547: 34-45.

[17] Jeandel E, Rolin N. Fixed parameter undecidability for Wang Tile sets［C］. Proceedings 18th International Workshop on Cellular Automata and Discrete Complex Systems and 3rd International Symposium Journees Automates Cellulaires, 2012, EPTCS 90, 69-85.

[18] 孙劲光, 刘双九. 块尺寸自适应的Tile纹理合成算法［J］. 计算机工程与应用, 2016, 52(11): 164-168.

Sun Jinguang, Liu shuangjiu. Algorithm of texture synthesis for adaptively selecting size of patches based on Tile［J］. Computer Engineering and Applications, 2016, 52(11): 164-168.

谭永前, 曾凡菊. 基于梯度的块尺寸自适应Wang Tiles纹理合成算法[J]. 激光与光电子学进展, 2017, 54(5): 051001. Tan Yongqian, Zeng Fanju. Gradient-Based Wang Tiles Texture Synthesis Algorithm with Adaptive Block Size[J]. Laser & Optoelectronics Progress, 2017, 54(5): 051001.

基于梯度的块尺寸自适应Wang Tiles纹理合成算法

关于本站 Cookie 的使用提示

全站搜索

基于梯度的块尺寸自适应Wang Tiles纹理合成算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索