留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码
邹鸿博, 章彪, 王子川, 陈可, 王立强, 袁波. 365彩票官网老虎机[J]. 365赌球. doi: 10.37188/CO.2023-0059
引用本文: 邹鸿博, 章彪, 王子川, 陈可, 王立强, 袁波. 365彩票官网老虎机[J]. 365赌球. doi: 10.37188/CO.2023-0059
ZOU Hong-bo, ZHANG Biao, WANG Zi-chuan, CHEN Ke, WANG Li-qiang, YUAN Bo. 365赌球注册开户[J]. Chinese Optics. doi: 10.37188/CO.2023-0059
Citation: ZOU Hong-bo, ZHANG Biao, WANG Zi-chuan, CHEN Ke, WANG Li-qiang, YUAN Bo. 365赌球注册开户[J]. Chinese Optics. doi: 10.37188/CO.2023-0059

365彩票官网老虎机

doi: 10.37188/CO.2023-0059
基金项目:国家重点研发计划项目(No. 2021YFC2400103);之江实验室科研项目(No. 2019MC0AD02;2022MG0AL01)
详细信息
    作者简介:

    邹鸿博(2000—),男,四川内江人,硕士在读,2021年6月于天津大学获得学士学位,2021年9月进入浙江大学光电学院学习。主要从事内窥成像、医学图像处理等方面研究。E-mail:[email protected]

    袁 波(1978—),男,江西萍乡人,副教授,硕士生导师,1999年于上海交通大学获得学士学位,2005年于上海交通大学获得博士学位,主要从事光电成像技术及内窥镜方面的研究。E-mail:[email protected]

  • 中图分类号:TN29;TP391.4

365赌球注册开户

Funds:Supported by the National Key Research and Development Program of China (No. 2021YFC2400103); Key Research Project of Zhejiang Lab (No. 2019MC0AD02; No. 2022MG0AL01)
More Information
  • 摘要:

    细胞内镜需实现最大倍率约500倍的连续放大成像,受光纤照明及杂散光影响,其图像存在不均匀光照,且光照分布会随放大倍率而变化,这会影响医生对病灶的观察及判断。为此,本文提出一种基于细胞内镜光照模型的图像不均匀光照校正算法。根据图像信息由光照分量和反射分量组成的原理,该算法通过卷积神经网络学习图像的光照分量,并基于二维Gamma函数实现不均匀光照校正。实验表明,经本文方法进行不均匀光照校正后,图像的光照分量平均梯度和离散熵分别为0.22和7.89,优于自适应直方图均衡化、同态滤波和单尺度Retinex等传统方法以及基于深度学习的WSI-FCN算法。

  • 图 1 常规成像模式下的照明光路

    Figure 1. Optical path in conventional imaging mode

    图 2 显微成像模式下的杂散光产生过程

    Figure 2. The process of stray light generation in microscopic imaging mode

    图 3 光照提取网络结构图

    Figure 3. Structure diagram of illumination extraction network

    图 4 空间金字塔模块示意图

    Figure 4. Schematic diagram of spatial pyramid module

    图 5 图像不均匀光照校正算法流程图

    Figure 5. Flow chart of non-uniform illumination correction algorithm

    图 6 细胞内镜不均匀光照数据集展示

    Figure 6. Image of non-uniform illumination dataset under cytoendoscope

    图 7 图像采集装置

    Figure 7. Image acquisition device

    图 8 不同方法的图像校正结果

    Figure 8. Image correction results using different correction methods

    表  1 不同方法的定量结果对比

    Table  1. Comparison of quantitative results of different correction methods

    AGIC DE
    AHE 0.40 5.58
    HF 0.26 7.68
    SSR 0.34 7.54
    WSI-FCN 0.29 7.23
    Ours 0.22 7.89
    下载: 导出CSV

    表  2 不同方法的速度对比

    Table  2. Speed comparison of different correction methods

    耗时(GPU)/ms 耗时(CPU)/ms
    AHE / 5260
    HF / 120
    SSR / 1340
    WSI-FCN 185 1190
    Ours 6 50
    下载: 导出CSV
  • [1] GOETZ M, MALEK N P, KIESSLICH R. Microscopic imaging in endoscopy: endomicroscopy and endocytoscopy[J]. Nature Reviews Gastroenterology & Hepatology, 2014, 11(1): 11-18.
    [2] 霍嘉燚, 李冕豪, 王子川, 等. 全景内窥成像技术及应用[J]. 中国光学(中英文),2023,16(1):44-60. doi: 10.37188/CO.2022-0074

    HUO J Y, LI M H, WANG Z CH, et al. Panoramic endoscopic imaging technology and it’s applications[J]. Chinese Optics, 2023, 16(1): 44-60. doi: 10.37188/CO.2022-0074
    [3] 王子川, 张伟, 郭飞, 等. 跨尺度光学内窥成像技术[J]. 中国光学(中英文),2022,15(6):1287-1301. doi: 10.37188/CO.2022-0078

    WANG Z CH, ZHANG W, GUO F, et al. Trans-scale optical endoscopy imaging technology[J]. Chinese Optics, 2022, 15(6): 1287-1301. doi: 10.37188/CO.2022-0078
    [4] 张伟, 牛春阳, 游兴海, 等. 高倍率大视场细胞内镜成像系统研究[J]. 光学学报,2021,41(17):1717001. doi: 10.3788/AOS202141.1717001

    ZHANG W, NIU CH Y, YOU X H, et al. Endocytoscopic imaging system with high magnification and large field of view[J]. Acta Optica Sinica, 2021, 41(17): 1717001. (in Chinese) doi: 10.3788/AOS202141.1717001
    [5] PIZER S M, AMBURN E P, AUSTIN J D, et al. Adaptive histogram equalization and its variations[J]. Computer Vision, Graphics, and Image Processing, 1987, 39(3): 355-368. doi: 10.1016/S0734-189X(87)80186-X
    [6] XIE X D, LAM K M. Face recognition under varying illumination based on a 2D face shape model[J]. Pattern Recognition, 2005, 38(2): 221-230. doi: 10.1016/S0031-3203(04)00275-4
    [7] LEE P H, WU S W, HUNG Y P. Illumination compensation using oriented local histogram equalization and its application to face recognition[J]. IEEE Transactions on Image Processing, 2012, 21(9): 4280-4289. doi: 10.1109/TIP.2012.2202670
    [8] FAN CH N, ZHANG F Y. Homomorphic filtering based illumination normalization method for face recognition[J]. Pattern Recognition Letters, 2011, 32(10): 1468-1479. doi: 10.1016/j.patrec.2011.03.023
    [9] AL SOBBAHI R, TEKLI J. Low-light homomorphic filtering network for integrating image enhancement and classification[J]. Signal Processing:Image Communication, 2022, 100: 116527. doi: 10.1016/j.image.2021.116527
    [10] LAND E H, MCCANN J J. Lightness and Retinex theory[J]. Journal of the Optical Society of America, 1971, 61(1): 1-11. doi: 10.1364/JOSA.61.000001
    [11] JOBSON D J, RAHMAN Z, WOODELL G A. Properties and performance of a center/surround Retinex[J]. IEEE Transactions on Image Processing, 1997, 6(3): 451-462. doi: 10.1109/83.557356
    [12] ZHANG SH, WANG T, DONG J Y, et al. Underwater image enhancement via extended multi-scale Retinex[J]. Neurocomputing, 2017, 245: 1-9. doi: 10.1016/j.neucom.2017.03.029
    [13] ZHOU J CH, YAO J, ZHANG W SH, et al. Multi-scale Retinex-based adaptive gray-scale transformation method for underwater image enhancement[J]. Multimedia Tools and Applications, 2022, 81(2): 1811-1831. doi: 10.1007/s11042-021-11327-8
    [14] MEI X F, XIE F Y, JIANG ZH G. Uneven illumination removal based on fully convolutional network for dermoscopy images[C]. 2016 13th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), IEEE, 2016: 243-247.
    [15] WANG J H, WANG X, ZHANG P, et al. Correction of uneven illumination in color microscopic image based on fully convolutional network[J]. Optics Express, 2021, 29(18): 28503-28520. doi: 10.1364/OE.433064
  • 加载中
图(8) /表(2)
计量
  • 文章访问数: 49
  • HTML全文浏览量: 15
  • PDF下载量: 31
  • 被引次数: 0
365赌球官网平台
  • 网络出版日期: 2023-09-14

目录

    /

    返回文章
    返回