Inpainting of metallographic image based on improved PatchMatch algorithm

doi:10.13251/j.issn.0254-6051.2021.03.039

Abstract

Abstract: Combining the DCT pyramid compression algorithm and the multi-patch optimal matching mechanism to improve the traditional PatchMatch image repair algorithm, using different algorithms to repair and compare the metallographic images with pollution characteristics. The results show that the improved PatchMatch algorithm greatly improves the repair speed and repair quality. The repaired images are more effective than other image repair algorithms, the internal texture details of the metallographic images are restored more accurately and delicately, and metallurgical images repair can solve the problems that conventional metallurgical image segmentation can not eliminate the big noise.

Key words: metallographic image, PatchMatch algorithm, image inpainting, big noise processing

CLC Number:

TG115.21⁺1.3

Li Songtao, Li Weigang, Shi Jingrui, Gan Ping. Inpainting of metallographic image based on improved PatchMatch algorithm[J]. Heat Treatment of Metals, 2021, 46(3): 196-205.

References

[1] Tasan C C,Diehl M,Yan D,et al.An overview of dual-phase steels:Advances in microstructure-oriented processing and micromechanically guided design[J].Annual Review of Materials Research,2015,45(1):391-431.
[2] Billur E,Cetin B,Gurleyik M.New generation advanced high strength steels:Developments,trends and constraints[J].International Journal of Sciemtific and Technological Research,2016(2):50-62.
[3] Peihua Qiu.Statistical analysis of microstructures in materials science[J].Technometrics,2002,44(1):86.
[4] Bhadeshia H,Honeycombe R.Steels:Microstructure and properties[J].Metallurgy &Materials Science,2006,194(4260):55-56.
[5] 朱雪峰,余日成,黄艳华,等.热处理对TA19钛合金组织和力学性能的影响[J].金属热处理,2015,40(2):103-106.
Zhu Xuefeng,Yu Richeng,Huang Yanhua,et al.Effects of heat treatment on microstructure and mechanical properties of TA19 titanium alloy[J].Heat Treatment of Metals,2015,40(2):103-106.
[6] 李杰,付冬梅.金相图像均衡化和多尺度模板二值降噪方法研究[J].铸造技术,2018,39(11):2433-2439.
Li Jie,Fu Dongmei.The equilibrium of metallographic image and the research of multiscale template binary noise reduction[J].Foundry Technology,2018,39(11):2433-2439.
[7] Gong Shengrong,Liu Chunping,Ji Yi,et al.Advanced Image and Video Processing Using MATLAB[M].Springer,2019:209-232.
[8] Barnes C,Shechtman E,Finkelstein A,et al.PatchMatch:A randomized correspondence algorithm for structural image editing[J].ACM Transaction Graphics,2009:doi.org/10.1145/1576246.1531330.
[9] Criminisi A,Perez P,Toyama K.Region filling and object removal by exemplar-based image inpainting[J].IEEE Transactions on Image Processing,2004,13(9):1200-1212.
[10] Barnes C,Shechtman E,Goldman D B,et al.The generalized PatchMatch correspondence algorithm[C]//European Conference on Computer Vision.Springer,2010:29-43.
[11] Chen X,Ye F,Zhu F,et al.Real-time affine invariant patch matching using DCT descriptor and affine space quantization[C]//International Conference on Image Processing.2011:2993-2996.
[12] Wang H X,Li J,Liang R H,et al.Exemplar-based image inpainting using structure consistent Patch Matching[C]//International Conference on Intelligent Science and Big Data Engineering.2015:401-410.
[13] Liu H M,Bi X H,Lu G M,et al.Screen window propagating for image inpainting[J].IEEE Access,2018(6):61761-61772.
[14] Liu H M,Bi X H,Lu G M.Exemplar-based image inpainting with multi-resolution information and the graph cut technique[J].IEEE Access,2019(7):101641-101657.
[15] Tran A,Tran H.Data-driven high-fidelity 2D microstructure reconstruction via non-local patch-based image inpainting[J].Acta Materialia,2019(178):207-218.
[16] 倪康,吴一全,韩斌.基于改进CV模型的金相图像分割[J].工程科学学报,2017,39(12):1866-1872.
Ni Kang,Wu Yiquan,Han Bin.Segmentation of metallographic images based on improved CV model[J].Chinese Journal of Engineering,2017,39(12):1866-1872.
[17] 李新城,赵从光,朱伟兴,等.基于水域生长的超细晶钢金相图像复原方法[J].材料热处理学报,2013,34(9):69-73.
Li Xincheng,Zhao Congguang,Zhu Weixing,et al.Restoring method of metallographic image of ultra-fine grain steel based on water-growing[J].Transactions of Materials and Heat Treatment,2013,34(9):69-73.
[18] Watson A B.DCT quantization matrices visually optimized for individual images[C]//Proceedings of SPIE-The International Society for Optical Engineering.1993:1913-1914.
[19] Alain Horé,Ziou D.Image quality metrics:PSNR vs.SSIM[C]//20th International Conference on Pattern Recognition,ICPR 2010.IEEE Computer Society,2010:23-26.
[20] Liu S Y,Ng T,Sunkavalli K,et al.PatchMatch-based automatic lattice detection for near-regular textures[C]//IEEE International Conference on Computer Vision.IEEE,2015:181-189.
[21] Yang X Y,Gousseau Y,Maitre H,et al.A fast algorithm for occlusion detection and removal[C]//25th IEEE International Conference on Image Processing (ICIP).IEEE,2018:2905-2909.
[22] Ignacio Ramrez Paulino,Ignacio Hounie.Image inpainting using Patch Consensus and DCT Priors[J].Image Processing Online,2021,11:1-17.
[23] Paulino I R,Hounie I.Paco and Paco-Dct:Patch consensus andits application to inpainting[C]//2020 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP).IEEE,2020:5775-5779.