Computer Science ›› 2022, Vol. 49 ›› Issue (6): 262-268.doi: 10.11896/jsjkx.210400039

• Computer Graphics & Multimedia • Previous Articles     Next Articles

Fast Structural Texture Image Synthesis Algorithm Based on Seam ConsistencyCriterion

JIN Li-zhen, LI Qing-zhong   

  1. 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)

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

CLC Number: 

  • TP391
[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.
[1] JIANG Zong-li, LI Miao-miao, ZHANG Jin-li. Graph Convolution of Fusion Meta-path Based Heterogeneous Network Representation Learning [J]. Computer Science, 2020, 47(7): 231-235.
[2] WU Han-yu, YAN Jiang, HUANG Shao-bin, LI Rong-sheng, JIANG Meng-qi. CNN_BiLSTM_Attention Hybrid Model for Text Classification [J]. Computer Science, 2020, 47(11A): 24-27.
[3] HE Xiao-jun, XU Ai-gong, LI Yu. Color Morphology Image Processing Method Using Similarity in HSI Space [J]. Computer Science, 2019, 46(4): 285-292.
[4] GUO Xiao-ying, LI Liang, GENG Hai-jun. Eye-movement Analysis of Visual Similarity Perception on Synthesized Texture Images [J]. Computer Science, 2018, 45(8): 223-228.
[5] ZHU Rui-chao,QIAN Wen-hua,PU Yuan-yuan, XU Dan. Texture Synthesis Based on Self-similarity Matching [J]. Computer Science, 2018, 45(6A): 215-219.
[6] TANG Ying, LIN Qi-feng, XIAO Ting-zhe and FAN Jing. GPU-based Texture Synthesis with Preserved Structures [J]. Computer Science, 2016, 43(4): 299-302.
[7] SUN Jin-guang and LIU Shuang-jiu. D-Tile for Texture Synthesis Based on Artificial Bee Colony [J]. Computer Science, 2015, 42(2): 287-291.
[8] TANG Ying,XIAO Ting-zhe and FAN Jing. GPU-based Fast Search of Similar Patches in Images [J]. Computer Science, 2014, 41(2): 290-296.
[9] NIU Lu-lu,CHEN Song-can and YU Lu. Comparison between Two Approaches of Embedding Spatial Information into Linear Discriminant Analysis [J]. Computer Science, 2014, 41(2): 49-54.
[10] DU Chang-qing and QIAN Wen-hua. Optimization Technique of 2D Texture Synthesis [J]. Computer Science, 2013, 40(4): 314-323.
[11] HUANG Cheng-hui,YIN Jian,HOU Fang. Improved Text Retrieve Algorithm Based on Subject-verb-object Structure [J]. Computer Science, 2010, 37(9): 173-176.
[12] ZOU Kun,HAN Guo-qiang,WO Yan,ZHANG Jian-wei. Graph Cut Method Based on Non-scalar Distance Metric for Texture Synthesis [J]. Computer Science, 2010, 37(2): 277-281.
[13] QU Zhong,LI Nan. Algorithm of Texture Synthesis Based on Chaos Particle Swarm Optimization [J]. Computer Science, 2010, 37(10): 275-278.
[14] . [J]. Computer Science, 2009, 36(6): 114-118.
[15] . [J]. Computer Science, 2008, 35(6): 251-254.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!