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赌球注册网站[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赌球注册网站[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彩票官网网页版[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彩票官网网页版[J]. Chinese Optics. doi: 10.37188/CO.2023-0059

365赌球注册网站

doi: 10.37188/CO.2023-0059
  • 1.

    浙江大学 光电科学与工程学院, 浙江 杭州 310027

  • 2.

    之江实验室类人感知研究中心, 浙江 杭州 311100

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彩票官网网页版

  • 1.

    College of Optical Science and Engineering, Zhejiang University, Hangzhou 310027, china

  • 2.

    Research Center for Humanoid Sensing, Zhejiang Lab., Hangzhou 311100, china

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。

    Abstract:

    Cytoendoscopy requires continuous amplification with a maximum magnification rate of about 500 times. Due to fiber-optic illumination and stray light, the image has non-uniform illumination that changes with the magnification rate, which affects the observation and evaluation of lesions by doctors. Therefore, this paper proposes an image non-uniform illumination correction algorithm based on the illumination model of cytoendoscopy. According to the principle that image information is composed of illumination and reflection components, the algorithm obtains the illumination component of the image through a convolutional neural network, and realizes non-uniform illumination correction based on the two-dimensional Gamma function. Experiments show that the average gradient of the illumination channel and the discrete entropy of the image are 0.22 and 7.89, respectively, after the non-uniform illumination correction by the proposed method, which is superior to the traditional methods such as adaptive histogram equalization, homophobic filtering, single-scale Retinex and the WSI-FCN algorithm based on deep learning.

    • HTML全文

  • 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: 51
  • HTML全文浏览量: 15
  • PDF下载量: 32
  • 被引次数: 0
365彩票官网老虎机
  • 网络出版日期: 2023-09-14

目录

    /

    返回文章
    返回