Volume 17 Issue 2
Mar.  2024
Turn off MathJax
Article Contents
LIU Xin-liang, ZHANG Long-quan, LENG Sheng, WANG Jing-qiu, WANG Xiao-lei. An autofocus algorithm for fusing global and local information in ferrographic images[J]. Chinese Optics, 2024, 17(2): 423-434. doi: 10.37188/CO.2023-0124
Citation: LIU Xin-liang, ZHANG Long-quan, LENG Sheng, WANG Jing-qiu, WANG Xiao-lei. An autofocus algorithm for fusing global and local information in ferrographic images[J]. Chinese Optics, 2024, 17(2): 423-434. doi: 10.37188/CO.2023-0124

An autofocus algorithm for fusing global and local information in ferrographic images

doi: 10.37188/CO.2023-0124
Funds:  Supported by National Key Laboratory of Science and Technology on Helicopter Transmission (No. HTL-A-21G03)
More Information
  • Corresponding author: meejqwang@nuaa.edu.cn
  • Received Date: 26 Jul 2023
  • Rev Recd Date: 24 Aug 2023
  • Available Online: 08 Nov 2023
  • To address the issues of large error and slow speed of manual focusing in ferrographic image acquisition, we propose an autofocus method for fusing global and local information in ferrographic images. This method includes two stages. In the first stage, the global autofocus stage, the feature vectors of the whole image is extracted by Convolutional Neural Networks (CNN) , and the features extracted in the focus process is fused by the Gate Recurrent Unit (GRU) to predict global defocusing distance, which serves as coarse focusing. In the local autofocus stage, the feature vector of the wear particle is extracted and the current features is fused with those extracted in the previous focusing process by GRU. The current defocusing distance is predicted by the resulting fused data based on the information of the thickest particle, which facilitates fine focusing. Moreover, we propose a determination method for autofocus direction using Laplacian gradient function to improve autofocus accuracy. Experimental results indicate an autofocus error of 2.51 μm on the test set and a focusing accuracy of 80.1% with a microscope depth of field of 2.0 μm. The average autofocus time is 0.771 s. The automatic ferrographic image acquisition system exhibits excellent performance and offers a practical approach for its implementation.


  • loading
  • [1]
    ROYLANCE B J. Ferrography—then and now[J]. Tribology International, 2005, 38(10): 857-862. doi: 10.1016/j.triboint.2005.03.006
    WANG J Q, WANG X L. The segmentation of ferrography images: a brief survey[J]. Materials Science Forum, 2013, 770: 427-432. doi: 10.4028/www.scientific.net/MSF.770.427
    卿华, 王新军. 飞机油液监控技术[M]. 北京: 航空工业出版社, 2011.

    QING H, WANG X J. Aircraft oil Monitoring Technology[M]. Beijing: Aviation Industry Press, 2011. (in Chinese).
    叶一青, 易定容, 张勇贞, 等. 基于倾斜摄像头的显微自动对焦方法[J]. 光学学报,2019,39(12):1218001. doi: 10.3788/AOS201939.1218001

    YE Y Q, YI D R, ZHANG Y ZH, et al. Microscopy autofocus method using tilt camera[J]. Acta Optica Sinica, 2019, 39(12): 1218001. (in Chinese). doi: 10.3788/AOS201939.1218001
    BATHE-PETERS M, ANNIBALE P, LOHSE M J. All-optical microscope autofocus based on an electrically tunable lens and a totally internally reflected IR laser[J]. Optics Express, 2018, 26(3): 2359-2368. doi: 10.1364/OE.26.002359
    ZHANG X, ZENG F, LI Y, et al. Improvement in focusing accuracy of DNA sequencing microscope with multi-position laser differential confocal autofocus method[J]. Optics Express, 2018, 26(2): 895-904.
    唐凌宇, 葛明锋, 董文飞. 全自动推扫式高光谱显微成像系统设计与研究[J]. 中国光学,2021,14(6):1486-1494. doi: 10.37188/CO.2021-0040

    TANG L Y, GE M F, DONG W F. Design and research of fully automatic push-broom hyperspectral microscopic imaging system[J]. Chinese Optics, 2021, 14(6): 1486-1494. (in Chinese). doi: 10.37188/CO.2021-0040
    JANG J, YOO Y, KIM J, et al. Sensor-based auto-focusing system using multi-scale feature extraction and phase correlation matching[J]. Sensors, 2015, 15(3): 5747-5762. doi: 10.3390/s150305747
    GUO K K, LIAO J, BIAN Z CH, et al. InstantScope: a low-cost whole slide imaging system with instant focal plane detection[J]. Biomedical Optics Express, 2015, 6(9): 3210-3216. doi: 10.1364/BOE.6.003210
    GAN Y H, YE Z T, HAN Y B, et al. Single-shot autofocusing in light sheet fluorescence microscopy with multiplexed structured illumination and deep learning[J]. Optics and Lasers in Engineering, 2023, 168: 107663. doi: 10.1016/j.optlaseng.2023.107663
    HOU S B, ZHANG H Y, MA B L, et al. Extended autofocusing in dual-wavelength digital holography[J]. Applied Optics, 2023, 62(22): 5959-5968. doi: 10.1364/AO.494696
    郭立强, 刘恋. 结合斜变换与方差的图像聚焦测度[J]. 光学 精密工程,2021,29(7):1731-1739. doi: 10.37188/OPE.2020.0555

    GUO L Q, LIU L. Image focus measure based on slant transform and variance[J]. Optics and Precision Engineering, 2021, 29(7): 1731-1739. (in Chinese). doi: 10.37188/OPE.2020.0555
    LIAO Y, XIONG Y H, YANG Y H. An auto-focus method of microscope for the surface structure of transparent materials under transmission illumination[J]. Sensors, 2021, 21(7): 2487. doi: 10.3390/s21072487
    NOEK R, KNOERNSCHILD C, MIGACZ J, et al. Multiscale optics for enhanced light collection from a point source[J]. Optics Letters, 2010, 35(14): 2460-2462. doi: 10.1364/OL.35.002460
    SHAJKOFCI A, LIEBLING M. Semi-blind spatially-variant deconvolution in optical microscopy with local point spread function estimation by use of convolutional neural networks[C]. Proceedings of 25th IEEE International Conference on Image Processing, IEEE, 2018.
    FARNES S A R, TSAI D M, CHIU W Y. Autofocus measurement for electronic components using deep regression[J]. IEEE Transactions on Components, Packaging and Manufacturing Technology, 2021, 11(4): 697-707. doi: 10.1109/TCPMT.2021.3060809
    GE Y H, LI B, ZHAO Y ZH, et al. HH-Net: image driven microscope fast auto-focus with deep neural network[C]. Proceedings of the 9th International Conference on Biomedical Engineering and Technology, Association for Computing Machinery, 2019: 180-185.
    XIANG Y, HE ZH J, LIU Q, et al. Autofocus of whole slide imaging based on convolution and recurrent neural networks[J]. Ultramicroscopy, 2021, 220: 113146. doi: 10.1016/j.ultramic.2020.113146
    REDMON J, FARHADI A. YOLOv3: an incremental improvement[J/OL]. arXiv: 1804.02767, 2018.
    HE K M, ZHANG X Y, REN SH Q, et al. Deep residual learning for image recognition[C]. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2016.
  • 加载中


    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(12)  / Tables(3)

    Article views(170) PDF downloads(71) Cited by()
    Proportional views


    DownLoad:  Full-Size Img  PowerPoint