Blind Reconstruction Method of AFM Image Based on Conditional Generative Adversarial Network
HU Jia-cheng1,YAN Di-xin1,CAO Cong2,SHI Yu-shu3,ZHANG Shu3,LI Dong-sheng1
1. University of China Jiliang, Hangzhou,Zhejiang 310018,China
2. Shandong Institute of Metrology,Jinan,Shandong 250014,China
3. National Institute of Metrology,Beijing 100029,China
Abstract：To solve the problem caused by the tip broadening effect in the imaging process of atomic force microscope(AFM), a blind reconstruction method of AFM image based on the condition generating adversarial network (CGAN) is proposed.First, on the basis of pix2pixHD network, the simulation sample data are trained by global generation network, and AFM measurement data are trained by local lifting network. Finally, feature matching loss function is used to improve the lateral resolution of grid edge.The experimental results show that when performing the blind reconstruction for the measurement image of the one-dimensional rectangular grid with line width being 8μm under AFM, the standard deviation of the reconstructed image is 0.33×0.45μm, which has a high imaging resolution and is conducive to improving the accuracy of the measurement of the AFM image one-dimensional grid.
［1］Chai X, Ba Q, Yang G. Characterizing robustness and sensitivity of convolutional neural networks for quantita-tive analysis of mitochondrial morphology ［J］. Quan-titative Biology, 2018, 6 (4): 344-358.
［2］林启敬, 吴昊, 张福政, 等. Cu/Ti纳米薄膜表面形貌的分形表征研究 ［J］. 计量学报, 2018, 39 (5): 593-597.
Lin Q J,Wu H,Zhang F Z, et al. Research on Fractal Characterization of the Surface Morphology of Cu/Ti Nano Thin Film ［J］. Acta Metrologica Sinica, 2018, 39 (5): 593-597.
［3］Villarrubia J S. Morphological estimation of tip geometry for scanned probe microscopy ［J］. Surface science, 1994, 321 (3): 287-300.
［4］Wang W L, Whitehouse D J. Application of neural net-works to the reconstruction of scanning probe microscope images distorted by finite-size tips ［J］. Nanotechnology, 1995, 6 (2): 45-51.
［5］王春梅. 基于AFM的纳米结构精确测量的方法学和标准化研究 ［D］. 上海:上海交通大学, 2009.
［6］袁帅, 董再励, 缪磊, 等. 基于数学形态学方法的AFM探针建模研究 ［J］. 仪器仪表学报, 2010, 31 (5): 1102-1107.
Yuan S, Dong Z L, Miao L, et al. AFM Tip Estima-tion Based on Mathematical Morphology ［J］. Chinese Journal of Scientific Instrument, 2010, 31 (5):1102-1107.
［7］Bakucz P, Yacoot A, Dziomba T, et al. Neural network approximation of tip-abrasion effects in AFM imaging ［J］. Measurement Science and Technology, 2008, 19 (6): 065101.
［8］施玉书, 连笑怡, 王艺瑄, 等. AFM 扫描过程的模拟及针尖形状反求 ［J］. 计量学报, 2019, 40 (2): 177-182.
Shi Y S, Lian X Y, Wang Y X, et al. Simiulation of AFM Scanning Process and Tip Shape Estimation ［J］. Acta Metrologica Sinica, 2019, 40 (2): 1000-1158.
［9］Isola P, Zhu J Y, Zhou T, et al. Image-to-image trans-lation with conditional adversarial networks ［C］// Proc of CVPR, Honolulu, America, 2017: 1125-1134.
［10］Wang T C, Liu M Y, Zhu J Y, et al. High-Resolution Image Synthesis and Semantic Manipulation with Condi-tional GANs ［C］//Proc of CVPR, Salt Lake City, America, 2018: 8798-8807.
［11］Modarres M H, Aversa R, Cozzini S, et al. Neural Net-work for Nanoscience Scanning Electron Microscope Im-age Recognition ［J］. Entific Reports, 2017, 7 (1): 13282.
［12］Goodfellow I, Pouget-Abadie J, Mirza M, et al. Gener-ative adversarial nets ［C］// Proc of NIPS, Montreal, Canada, 2014: 2672-2680.
［13］王坤峰, 苟超, 段艳杰, 等. 生成式对抗网络GAN的研究进展与展望 ［J］. 自动化学报, 2017, 43 (3): 321-332.
Wang K F, Gou C, Duan Y J, et al. Generative Adversarial Networks: The State of the Art and Beyond ［J］. Acta Automatica Sinica, 2017, 43 (3):321-332.
［14］胡明霞, 马艳. 一维矩形光栅AFM图像盲探针表面重建模拟研究 ［J］. 光学仪器, 2018, 40 (3): 52-59.
Hu M X, Ma Y. Simulation of surface reconstruction of the one-dimensional rectangle grating AFM images by blind reconstructed tip ［J］. Optical Instruments, 2018, 40 (3): 52-59.
［15］王心哲. 基于卷积神经网络的图像盲复原方法研究 ［D］. 秦皇岛:燕山大学, 2018.
［16］Wu Y, Fang Y, Ren X, et al. Back propagation neural networks based hysteresis modeling and compensation for a piezoelectric scanner ［C］// Proc of 3M NANO, Chongqing, China, 2016: 119-124.
［17］Villarrubia J S. Algorithms for scanned probe micro-scope image simulation, surface reconstruction, and tip estimation ［J］. Journal of research of the National Institute of Standards and Technology, 1997, 102 (4): 425-454.
［18］刘俭, 谷康, 李梦周, 等. 扫描探针显微镜下微纳结构深度测量的校准方法 ［J］. 计量学报, 2019, 40 (4): 549-556.
Liu J, Gu K, Li M Z, et al. Calibration Method for Depth Measurement of Nano/microstructure in Scanning Probe Microscopy ［J］. Acta Metrologica Sinica, 2019, 40 (4): 549-556.
2021, Vol. 42 
