面向纹理合成的块尺寸自动选择算法

doi:10.11772/j.issn.1001-9081.2014.10.2982

计算机应用 ›› 2014, Vol. 34 ›› Issue (10): 2982-2984.DOI: 10.11772/j.issn.1001-9081.2014.10.2982

面向纹理合成的块尺寸自动选择算法

江巨浪¹,李飞²,朱柱¹,詹文法¹

1. 安庆师范学院物理与电气工程学院，安徽安庆 246133
2. 安庆师范学院数学与计算科学学院，安徽安庆 246133

收稿日期:2014-04-24 修回日期:2014-06-17 出版日期:2014-10-01 发布日期:2014-10-30
通讯作者: 江巨浪
作者简介:江巨浪(1967-)，男，安徽潜山人，教授，博士，主要研究方向：计算机图形学、图像处理；
李飞（1987-），男，河南信阳人，硕士研究生，主要研究方向：数字图形处理；
朱柱（1983-），男，安徽淮南人，博士，主要研究方向：数字图形与视频信号处理；
詹文法（1978-），男，安徽怀宁人，教授，博士，主要研究方向：数字信号处理。
基金资助:
国家自然科学基金资助项目

Automatic selection algorithm of patch size for texture synthesis

JIANG Julang¹,LI Fei²,ZHU Zhu¹,ZHAN Wenfa¹

1. School of Physics and Electrical Engineering, Anqing Teachers College, Anqing Anhui 246133, China;
2. School of Mathematics and Computational Science, Anqing Teachers College, Anqing Anhui 246133, China

Received:2014-04-24 Revised:2014-06-17 Online:2014-10-01 Published:2014-10-30
Contact: JIANG Julang

摘要/Abstract

摘要：

在现有的基于块的纹理合成算法中，针对块尺寸需要人工选择从而导致纹理合成质量不确定的问题，提出一种纹理合成中的块尺寸自动选择算法。在纹理样本上按扫描线顺序滑动子块直到遍历所有位置，对子块与纹理样本的直方图进行归一化与均值滤波预处理，然后计算二者直方图的交；在不同子块位置的上述计算结果中，取其最大值作为子块与样本的颜色相似度。针对颜色相似度与块尺寸的近似单调递增关系，采用二分法计算相似度阈值点所对应的横坐标，将其作为纹理合成的块尺寸。多种类型纹理的实验结果表明，该方法自动选择的块尺寸与最佳经验取值范围相吻合。所提方法不仅适用于结构性纹理的合成，而且适用于随机性纹理的合成，能够获得理想的合成结果。

Abstract:

In previous patch-based texture synthesis algorithm, the size of patch requires artificial choice which leads to an uncertainty quality of texture synthesis, so an automatic selection algorithm of patch size for texture synthesis was presented. When the patch was slid on the examplar in scan-line order until getting through all the plane, the histograms of the patch and the examplar were both pretreated by normalization and mean filtering, then the intersection of the two histograms was calculated. Among all the calculation results for different position, the maximum value was selected as the measurement of the color similarity between patches and examplar. Due to approximate monotone increasing relation between color similarity and patchs size, bisection method was adopted to calculate the abscissa for the color similarity threshold point, and the abscissa was used as the patchs size for texture synthesis. The experimental results of various types of textures show that the size of patch automatically selected by this method coincides with the range of best empirical value. Compared with the other automatic selection methods of patchs size, this method not only applies to structured texture synthesis, but also applies to stochastic texture synthesis, and obtains suitable results of texture synthesis.

中图分类号:

TP391.41

江巨浪李飞朱柱詹文法. 面向纹理合成的块尺寸自动选择算法[J]. 计算机应用, 2014, 34(10): 2982-2984.

JIANG Julang LI Fei ZHU Zhu ZHAN Wenfa. Automatic selection algorithm of patch size for texture synthesis[J]. Journal of Computer Applications, 2014, 34(10): 2982-2984.

参考文献

［1］EFROS A A, LEUNG T K. Texture synthesis by nonparametric sampling ［C］// Proceedings of the IEEE International Conference on Computer Vision. Piscataway: IEEE Press, 1999:1033-1038.
［2］WEI L Y, LEVOY M. Fast texture synthesis using tree structured vector quantization ［C］// Proceedings of the 2000 ACM SIGGRAPH. New York: ACM, 2000:479-488.
［3］KWATRA V, ESSA I A, BOBICK A F, et al.Texture optimization for example-based synthesis ［J］. ACM Transactions on Graphics—Proceedings of ACM SIGGRAPH 2005, 2005,24(3):795-802.
［4］LEFEBVRE S, HOPPE H. Appearance-space texture synthesis ［C］// Proceedings of the 2006 ACM SIGGRAPH. New York: ACM, 2006:541-548.
［5］XIAO C, HUANG Z, NIE Y, et al.Global texture optimization incorporating with image detail ［J］. Chinese Journal of Computers, 2009,32(6):1196-1205.(肖春霞,黄志勇,聂勇伟,等.结合图像细节特征的全局优化纹理合成［J］.计算机学报,2009,32(6):1196-1205.)
［6］EFROS A A, FREEMAN W T. Image quilting for texture synthesis and transfer ［C］// Proceedings of the 2001 ACM SIGGFAPH. New York: ACM, 2001:341-346.
［7］KWATRA V, SCHDL A, ESSA I A, et al.Graphcut textures: image and video synthesis using graph cuts ［J］. ACM Transactions on Graphics, 2003,22(3):277-286.
［8］WANG X, TAO J, SONG C. Task scheduling for regular patch-based texture synthesis in the parallel wavefront pattern ［J］. Journal of Computer-Aided Design and Computer Graphics, 2013,25(2):248-257.(王相海,陶兢喆,宋传鸣.并行波峰模式的规则块拼接纹理合成调度［J］.计算机辅助设计与图形学学报,2013,25(2):248-257.)
［9］COHEN M F, SHADE J, HILLER S, et al.Wang tiles for image and texture generation ［J］. ACM Transactions on Graphics, 2003,22(3):287-294.
［10］WANG J, PANG M, ZHAO R. Texture synthesis using rotational Wang Tiles ［J］. Journal of Image and Graphics, 2013,18(1):49-54.(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.)
［11］NIE J, WANG Y. 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.(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.)
［12］CHEN X, WANG W. Real-time synthesis of large textures ［J］. Journal of Software, 2009,20(zk):193-201.(陈昕,王文成.大尺寸纹理的实时合成［J］.软件学报,2009,20(zk):193-201.)
［13］ZHANG W, HE K, MENG C. Texture synthesis method by adaptive selecting size of patches ［J］. Computer Engineering and Applications, 2012,48(17):170-173. (张伟伟,何凯,孟春芝.自适应选取样本块大小的纹理合成方法［J］.计算机工程与应用,2012,48(17):170-173.)

[1]	杨鼎康黄帅王顺利翟鹏李一丹张立华. 基于对抗生成网络和网络集成的面部表情识别方法EE-GAN[J]. 计算机应用, 0, (): 0-0.
[2]	秦庭威赵鹏程秦品乐曾建朝柴锐黄永琦. 基于残差注意力机制的点云配准算法[J]. 计算机应用, 0, (): 0-0.
[3]	裴仪瑶, 郭会明, 张丹普, 陈文博. 基于定位不确定性的鲁棒3D目标检测方法[J]. 计算机应用, 2021, 41(10): 2979-2984.
[4]	许学斌, 张佳达, 刘伟, 路龙宾, 赵雨晴. 融合空间和通道特征的高精度乳腺癌分类方法[J]. 计算机应用, 2021, 41(10): 3025-3032.
[5]	汪虹余, 张彧, 杨恒, 穆楠. 基于蚁群优化算法的弱光图像显著性目标检测[J]. 计算机应用, 2021, 41(10): 2970-2978.
[6]	魏淳武, 赵涓涓, 唐笑先, 强彦. 基于多时期蒸馏网络的随访数据知识提取方法[J]. 计算机应用, 2021, 41(10): 2871-2878.
[7]	李自强, 王正勇, 陈洪刚, 李林怡, 何小海. 基于外观和动作特征双预测模型的视频异常行为检测[J]. 计算机应用, 2021, 41(10): 2997-3003.
[8]	张怡孙永荣赵科东李华曾庆化. 空中加油场景下的目标联合检测跟踪算法[J]. 计算机应用, 0, (): 0-0.
[9]	马峻姚震徐翠锋陈寿宏. 基于改进PP-YOLO和Deep-SORT的多无人机实时跟踪算法[J]. 计算机应用, 0, (): 0-0.
[10]	贺怀清闫建青惠康华. 基于深度残差网络的轻量级人脸识别方法[J]. 计算机应用, 0, (): 0-0.
[11]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[12]	张笑非, 杨阳, 黄佳进, 钟宁. 基于度中心性的认知特征选择方法[J]. 计算机应用, 2021, 41(9): 2767-2772.
[13]	姬张建, 任兴旺. 带旋转与尺度估计的全卷积孪生网络目标跟踪算法[J]. 计算机应用, 2021, 41(9): 2705-2711.
[14]	闫钧华侯平张寅吕向阳马越王高飞. 基于多尺度多分类器卷积神经网络的混合失真类型判定方法 [J]. 计算机应用, 0, (): 0-0.
[15]	李福海蒋慕蓉杨磊谌俊毅. 基于生成对抗网络的梯度引导太阳斑点图像去模糊方法[J]. 计算机应用, 0, (): 0-0.

面向纹理合成的块尺寸自动选择算法

Automatic selection algorithm of patch size for texture synthesis

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics