基于接缝一致性准则的结构纹理图像快速合成算法

计算机科学 ›› 2022, Vol. 49 ›› Issue (6): 262-268.doi: 10.11896/jsjkx.210400039

• 计算机图形学&多媒体 • 上一篇下一篇

基于接缝一致性准则的结构纹理图像快速合成算法

靳利贞, 李庆忠

中国海洋大学工程学院山东青岛 266100

收稿日期:2021-04-02 修回日期:2021-09-06 出版日期:2022-06-15 发布日期:2022-06-08
通讯作者: 李庆忠(liqingzhong@ouc.edu.cn)
作者简介:(jinlizhen@stu.ouc.edu.cn)
基金资助:
国家重点研发计划项目(2017YFC1405202);海洋公益性行业科研专项(2016050021)

Fast Structural Texture Image Synthesis Algorithm Based on Seam ConsistencyCriterion

JIN Li-zhen, LI Qing-zhong

School of Engineering,Ocean University of China,Qingdao,Shandong 266100,China

Received:2021-04-02 Revised:2021-09-06 Online:2022-06-15 Published:2022-06-08
About author:JIN Li-zhen,born in 1998,postgra-duate.Her main research interests include image processing and so on.
LI Qing-zhong,born in 1963,Ph.D,professor,postgraduate supervisor.His main research interests include image processing,signal processing and pattern recognition.
Supported by:
National Key Research and Development Program of China(2017YFC1405202) and Ocean Public Welfare Scientific Research Project(2016050021)

摘要/Abstract

摘要： 基于块的结构纹理图像合成算法存在诸多问题,如结构不连续、边界扭曲、接缝不齐以及合成速度慢等,对此提出了一种新的基于双接缝一致性准则的纹理图像非重叠拼接快速合成算法,该算法有效提高了结构纹理图像的合成质量与速度。首先基于更符合人眼视觉特性的HSI颜色空间建立了同时考虑色调、饱和度、亮度和边缘特征的接缝线一致性判别准则;然后提出并实现了基于双接缝线一致性准则的子块搜索策略和非重叠拼接算法。实验结果表明,与传统算法相比,所提算法能够显著提高结构纹理图像的合成质量和速度。

关键词: HIS颜色空间, 非重叠拼接, 接缝线一致性, 结构信息, 纹理合成

Abstract: Aiming at the problems of patch-based synthesis algorithm of structured texture images,such as discontinuity of structure,distortion of boundary,seam misalignment,and low synthesis speed,a new fast non-overlapping synthesis algorithm of texture images is proposed based on the consistency criterion of double-seam lines,thereby effectively improving the synthesis quality and speed of structured texture images.Firstly,the seamline consistency criterion considering hue,saturation,brightness and edge characteristics simultaneously is established in HSI color space that is more consistent with human visual characteristic.Then,a sub-block search strategy and a new non-overlapping splicing algorithm based on the consistency criterion of double-seam line are proposed and implemented.The experiment results show that the proposed algorithm can significantly improve the synthesis quality and speed of structured texture images in comparison with the traditional algorithms.

Key words: HSI color space, Non-overlapping splicing, Seam line consistency, Structure information, Texture synthesis

中图分类号:

TP391

靳利贞, 李庆忠. 基于接缝一致性准则的结构纹理图像快速合成算法[J]. 计算机科学, 2022, 49(6): 262-268. https://doi.org/10.11896/jsjkx.210400039

JIN Li-zhen, LI Qing-zhong. Fast Structural Texture Image Synthesis Algorithm Based on Seam ConsistencyCriterion[J]. Computer Science, 2022, 49(6): 262-268. https://doi.org/10.11896/jsjkx.210400039

参考文献

[1] LEE J,KIM D,KIM Y,et al.A Training Method for Image Compression Networks to Improve Perceptual Quality of Reconstructions[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop(CVPRW).IEEE,2020:585-589.
[2] YAO S,YAN J,WUM,et al.Texture synthesis based thyroid nodule detection from medical ultrasound images:interpreting and suppressing the adversarial effect of in-place manual annotation[J].Frontiers in Bioengineering and Biotechnology,2020,8(3):599-610.
[3] GUTIERREZ J,RABIN J,GALERNE B,et al.Ondemand solid texture synthesis using deep 3D networks[J].Computer Gra-phics Forum,2019,39(4):511-530.
[4] JIA R,WANG F,YUAN H W,et al.Research on Fuzzy Adaptive Fusion Algorithm for Ultraviolet Polarization Image of Latent Fingerprint[J].Computer Engineering,2020,46(11):267-272,278.
[5] CHEN Q,LI G,XIE L,et al.Structure guided image completion using texture synthesis and region segmentation[J].Optik,2019,185(7):896-909.
[6] RAAD L,DESOLNEUX A,MOREL J M.A Conditional Multiscale Locally Gaussian Texture Synthesis Algorithm[J].Journal of Mathematical Imaging & Vision,2016,56(2):260-279.
[7] PORTILLA J,SIMONCELLI E P.A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients[J].International Journal of Computer Vision,2000,40(7):49-70.
[8] HEEGER D J,BERGEN J R.Pyramid-based texture analysis/synthesis[C]//Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques.ACM,1995:229-238.
[9] GALERNE J M.Random Phase Textures:Theory and Synthesis[J].IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society,2011,20(1):257-267.
[10] BARNES C,ZHANG F L.A survey of the state-of-the-art in patch-based synthesis[J].Computational Visual Media,2017,4(1):3-20.
[11] EFROS A A,FREEMAN W T.Image quilting for texture synthesis and transfer[C]//The 28th International Conference on Computer Graphics and Interactive Techniques Conference(SIGGRAPH’01).ACM,2001:341-346.
[12] ZHU R C,QIAN W H,PU Y Y,et al.Texture Synthesis Base On Self-similarity Matching[J].Computer Science,2018,45(S1):228-232.
[13] PU Y Y,XU D,QIAN W H,et al.An improved texture synthesis algorithm[J].Transactions on Edutainment XI,Lecture Notes in Computer Science,2015,8971(1):103-113.
[14] RAAD L,GALERNE B.Efros and Freeman Image Quilting Algorithm for Texture Synthesis[J].Image Processing on Line,2017,7(6):1-22.
[15] SHEN J W,WANG S Z.Structural matching in texture synthesis based on image quilting[J].Journal of Shanghai University(Natural science),2010,16(1):10-14.
[16] TANG Y,LIN Q F,XIAO T Z,et al.GPU-based texture synthesis with preserved structures[J].Computer Science,2016,43(4):299-302,312.
[17] RAFI M,MUKHOPADHYAY S.Image Quilting for Texture Synthesis of Grayscale Images Using Gray-Level Co-occurrence Matrix and Restricted Cross-Correlation[J].Progress in Advanced Computing and Intelligent Engineering,Advances in Intelligent Systems and Computing,2019,713(8):37-47.
[18] CHEN B,ZHANG X,WANG R T,et al.Detect concrete cracks based on OTSU algorithm with differential image[J].The Journal of Engineering,2019,23:9088-9091.
[19] AKL A,YAACOUB C,DONIAS M,et al.A survey of exemplar-based texture synthesis methods[J].Computer Vision and Image Understanding,2018,172(5):12-24.
[20] HU Z J,LIU G H,SU Y.Application of Local Autocorrelation Function in Content-based Image Retrieval[J].Computer Science,2018,45(S2):259-262.
[21] KULLBACK S,LEIBLER R A.On Information and Sufficiency[J].Annals of Mathematical Statistics,1951,22(1):79-86.

相关文章 15

[1]	蒋宗礼, 李苗苗, 张津丽. 基于融合元路径图卷积的异质网络表示学习 Graph Convolution of Fusion Meta-path Based Heterogeneous Network Representation Learning 计算机科学, 2020, 47(7): 231-235. https://doi.org/10.11896/jsjkx.190600085
[2]	付健,孔芳. 融入结构信息的指代消解 Coreference Resolution Incorporating Structural Information 计算机科学, 2020, 47(3): 231-236. https://doi.org/10.11896/jsjkx.190100108
[3]	吴汉瑜, 严江, 黄少滨, 李熔盛, 姜梦奇. 用于文本分类的CNN_BiLSTM_Attention混合模型 CNN_BiLSTM_Attention Hybrid Model for Text Classification 计算机科学, 2020, 47(11A): 24-27. https://doi.org/10.11896/jsjkx.200400116
[4]	郭小英, 李亮, 耿海军. 合成纹理图像的视觉相似性眼动分析 Eye-movement Analysis of Visual Similarity Perception on Synthesized Texture Images 计算机科学, 2018, 45(8): 223-228. https://doi.org/10.11896/j.issn.1002-137X.2018.08.040
[5]	朱瑞超,钱文华,普园媛,徐丹. 自相似性匹配的纹理合成 Texture Synthesis Based on Self-similarity Matching 计算机科学, 2018, 45(6A): 215-219.
[6]	汤颖,林琦峰,肖廷哲,范菁. 基于GPU加速的保结构纹理合成 GPU-based Texture Synthesis with Preserved Structures 计算机科学, 2016, 43(4): 299-302. https://doi.org/10.11896/j.issn.1002-137X.2016.04.061
[7]	杜小坤,李国徽,李艳红. 模式匹配中的结构差异识别及消解 Structural Difference Recognition and Dispelling in Schema Matching 计算机科学, 2015, 42(2): 185-190. https://doi.org/10.11896/j.issn.1002-137X.2015.02.040
[8]	孙劲光,刘双九. 基于人工蜂群的D-Tile纹理合成算法 D-Tile for Texture Synthesis Based on Artificial Bee Colony 计算机科学, 2015, 42(2): 287-291. https://doi.org/10.11896/j.issn.1002-137X.2015.02.061
[9]	郑秀清,何坤,张健. 基于结构信息的RPCA图像去噪 Image Denoising by Principal Component Analysis with Structural Information 计算机科学, 2014, 41(8): 301-305. https://doi.org/10.11896/j.issn.1002-137X.2014.08.064
[10]	汤颖,肖廷哲,范菁. 基于GPU加速的快速图像相似区域查找 GPU-based Fast Search of Similar Patches in Images 计算机科学, 2014, 41(2): 290-296.
[11]	牛璐璐,陈松灿,俞璐. 线性判别分析中两种空间信息嵌入方法之比较 Comparison between Two Approaches of Embedding Spatial Information into Linear Discriminant Analysis 计算机科学, 2014, 41(2): 49-54.
[12]	杜常青,钱文华. 二维纹理合成算法优化研究 Optimization Technique of 2D Texture Synthesis 计算机科学, 2013, 40(4): 314-323.
[13]	刘春英,房庆云,胡维华. 基于区别缺损对象的视频序列修复方法 Restoration Method for Video Sequences Based on Distinguishing Damaged Objects 计算机科学, 2012, 39(7): 267-269.
[14]	黄承慧,印鉴,侯昉. 一种基于主谓宾结构的文本检索算法 Improved Text Retrieve Algorithm Based on Subject-verb-object Structure 计算机科学, 2010, 37(9): 173-176.
[15]	邹昆,韩国强,沃焱,张见威. 纹理合成中基于非标量距离度量的Graph Cut方法 Graph Cut Method Based on Non-scalar Distance Metric for Texture Synthesis 计算机科学, 2010, 37(2): 277-281.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed