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

基于灰度变换及改进Retinex的低照度图像增强

游达章 陶加涛 张业鹏 张敏

游达章, 陶加涛, 张业鹏, 张敏. 基于灰度变换及改进Retinex的低照度图像增强[J]. 红外技术, 2023, 45(2): 161-170.
引用本文: 游达章, 陶加涛, 张业鹏, 张敏. 基于灰度变换及改进Retinex的低照度图像增强[J]. 红外技术, 2023, 45(2): 161-170.
YOU Dazhang, TAO Jiatao, ZHANG Yepeng, ZHANG Min. Low-light Image Enhancement Based on Gray Scale Transformation and Improved Retinex[J]. Infrared Technology , 2023, 45(2): 161-170.
Citation: YOU Dazhang, TAO Jiatao, ZHANG Yepeng, ZHANG Min. Low-light Image Enhancement Based on Gray Scale Transformation and Improved Retinex[J]. Infrared Technology , 2023, 45(2): 161-170.

基于灰度变换及改进Retinex的低照度图像增强

基金项目: 

国家自然科学基金面上项目 51875180

详细信息
    作者简介:

    游达章(1975-),男,博士,教授,研究方向为机器人与智能控制、数控技术、故障预测与可靠性技术;E-mail: yodazhag@163.com

  • 中图分类号: TP391.41

Low-light Image Enhancement Based on Gray Scale Transformation and Improved Retinex

  • 摘要: 针对低光照条件下拍摄的图像受光和环境的影响,其重要信息丢失严重,出现对比度低、细节模糊等问题,提出了一种基于灰度变换与改进Retinex的图像增强方法。首先采用引力搜索算法(gravitational search algorithm, GSA)优化的全局灰度变换函数对图像的RGB各通道灰度图像进行灰度变换,增强图像光照强度,使其更接近均匀光照场景;然后将图像转为HSV色彩空间,对V通道(亮度通道)采用改进的多尺度Retinex(MSR)算法处理,将基于范围的自适应双边滤波和Gabor滤波作为Retinex算法的环绕函数,结合两种滤波的特性来增强图像的亮度和细节。最后采用伽马校正避免图像融合造成的图像色偏。实验结果显示,该方法处理过的增强图像在主观和客观评价上优于其他方法,图像颜色失真较小,细节更清晰,为图像的后续应用做了铺垫。
  • 图  1  基于灰度变换和改进后的Retinex图像增强算法的实现过程

    Figure  1.  Flow chart of image enhancement algorithm

    图  2  基于灰度变换函数和GSA的图像处理流程

    Figure  2.  GSA-based gray-scale transformation image enhancement flowchart

    图  3  Retinex理论中图像的构成

    Figure  3.  Retinex theory composition

    图  4  基于改进Retinex的图像增强流程

    Figure  4.  Improved Retinex algorithm flow chart

    图  5  Retinex算法改进前后对比

    Figure  5.  Comparison before and after the improvement of the Retinex algorithm

    图  6  图像A各分量适应度收敛图

    Figure  6.  6 Convergence diagram of fitness of each component of image A

    图  7  灰度变换前后图像及其灰度直方图对比

    Figure  7.  Grayscale histogram of each image

    图  8  不同算法对图像A的增强对比图

    Figure  8.  Enhanced comparison of image A by different algorithms

    图  9  不同算法对图像B的增强对比图

    Figure  9.  Enhanced comparison of image B by different algorithms

    图  10  不同算法对图像C的增强对比图

    Figure  10.  Enhanced comparison of image C by different algorithms

    图  11  有无灰度变换预处理的改进Retinex方法处理对比

    Figure  11.  Comparison of the improved Retinex method with and without grayscale transformation preprocessing

    图  12  原图和各算法处理后图像的玻璃瓶瓶口圆心定位比较

    Figure  12.  Comparison of the positioning of the center of the glass bottle mouth

    表  1  各算法参数

    Table  1.   Parameters of each algorithm

    Method Parameter
    BSSR sigma _s={15, 70, 110};
    sigma _s ={0.05, 0.1, 0.3};
    Filter size N=2;
    Ref. [4] sigma ={64, 128, 256};
    Color recovery factor C=1/3
    V-SSR sigma=256
    Ours sigma _s={15, 70, 110};
    sigma _d={0.05, 0.1, 0.3};
    ρ=3; filter size N=2;
    Weight factor m=0.4
    下载: 导出CSV

    表  2  图像A、B、C客观质量评价

    Table  2.   Objective quality evaluation of images A, B and C

    Method Image A Image B Image C
    IE MG PSNR IE MG PSNR IE MG PSNR
    Original image 6.8780 0.0141 - 6.6150 0.0255 - 7.1937 0.0375 -
    BSSR 7.5857 0.0380 52.6133 7.5051 0.0564 41.3939 7.6856 0.0982 36.2253
    Ref.[4] 7.5335 0.0465 51.6841 7.4900 0.0574 37.5988 7.6190 0.0961 35.2424
    V-SSR 7.4974 0.0349 49.9789 7.4368 0.0540 39.4727 7.4950 0.0904 34.0436
    Ours1 7.6121 0.0344 68.0142 7.5252 0.0598 54.4110 7.8207 0.0651 55.6753
    Ours 7.8976 0.0608 75.2760 7.5871 0.0499 64.4282 7.9459 0.1326 79.0920
    下载: 导出CSV
  • [1] Dhal K G, Ray S, Das A, et al. A survey on nature-inspired optimization algorithms and their application in image enhancement domain[J]. Archives of Computational Methods in Engineering, 2019, 26(5): 1607-1638. doi:  10.1007/s11831-018-9289-9
    [2] GAO H, ZENG W, CHEN J. An improved gray-scale transformation method for pseudo-color image enhancement[J]. Computer Optics, 2019, 43(1): 78-82. http://www.researchgate.net/publication/332056355_An_improved_gray-scale_transformation_method_for_pseudo-color_image_enhancement
    [3] Hassan N, Ullah S, Bhatti N, et al. The Retinex based improved underwater image enhancement[J]. Multimedia Tools and Applications, 2020(1): 1-19.
    [4] SHAO Wenbo, LIU Lei, JIANG Jiawei, et al. Low-light-level image enhancement based on fusion and Retinex[J]. Journal of Modern Optics, 2020, 67(13): 1190-1196. doi:  10.1080/09500340.2020.1823502
    [5] 牟琦, 魏妍妍, 李姣, 等. 改进的Retinex低照度图像增强算法研究[J]. 哈尔滨工程大学学报, 2018, 39(12): 2001-2010. https://www.cnki.com.cn/Article/CJFDTOTAL-HEBG201812019.htm

    MU Q, WEI Y Y, LI J, et al. Research on the improved Retinex algorithm for low illumination image enhancement[J]. Journal of Harbin Engineering University, 2018, 39(12): 2001-2010. https://www.cnki.com.cn/Article/CJFDTOTAL-HEBG201812019.htm
    [6] 许凤麟, 苗玉彬, 张铭. 基于彩色加权引导滤波-Retinex算法的导航图像增强[J]. 上海交通大学学报, 2019, 53(8): 921-927. https://www.cnki.com.cn/Article/CJFDTOTAL-SHJT201908007.htm

    XU F L, MIAO Y B, ZHANG M. Navigation image enhancement based on color weighted guided image filtering Retinex algorithm[J]. Journal of Shanghai Jiaotong University, 2019, 53(8): 921-927. https://www.cnki.com.cn/Article/CJFDTOTAL-SHJT201908007.htm
    [7] Oh J G, Hong M C. Adaptive image rendering using a nonlinear mapping-function-based Retinex model[J]. Sensors, 2019, 19(4): 969-985. doi:  10.3390/s19040969
    [8] GAO H, ZENG W, CHEN J. An improved gray-scale transformation method for pseudo-color image enhancement[J]. Computer Optics, 2019, 43(1): 78-82.
    [9] SUN X, XU Q, ZHU L. An effective Gaussian fitting approach for image contrast enhancement[J]. IEEE Access, 2019, 7: 31946- 31958.
    [10] Verma H K, Pal S. Modified sigmoid function based gray scale image contrast enhancement using particle swarm optimization[J]. Journal of the Institution of Engineers, 2016, 97(2): 243-251.
    [11] 刘宾, 赵鹏翔, 赵霞, 等. 变能量X射线融合图像的增强算法研究[J]. 光学学报, 2020, 40(18): 216-221. https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB202018025.htm

    LIU B, ZHAO P X, ZHAO X, et al. Enhancement algorithm of variable energy X-Ray fusion images[J]. Acta Optica Sinica, 2020, 40(18): 216-221. https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB202018025.htm
    [12] Katirciolu F, Cngz Z. A novel gray image enhancement using the regional similarity transformation function and dragonfly algorithm[J]. El-Cezeri Fen ve Mühendislik Dergisi, 2020, 7(3): 1201-1219.
    [13] JIANG S, JI Z, SHEN Y. A novel hybrid particle swarm optimization and gravitational search algorithm for solving economic emission load dispatch problems with various practical constraints[J]. International Journal of Electrical Power & Energy Systems, 2014, 55: 628-644.
    [14] 魏赟, 欧阳鹏. 基于快速亮通双边滤波器的Retinex图像增强算法[J]. 小型微型计算机系统, 2021, 42(9): 1944-1949. https://www.cnki.com.cn/Article/CJFDTOTAL-XXWX202109026.htm

    WEI Y, OU Y P. Retinex image enhancement algorithm based on fast bright-pass bilateral filtering[J]. Journal of Chinese Computer Systems, 2021, 42(9): 1944-1949. https://www.cnki.com.cn/Article/CJFDTOTAL-XXWX202109026.htm
    [15] WANG Z, WANG Z. A generic approach for cell segmentation based on gabor filtering and area-constrained ultimate erosion[J]. Artificial Intelligence in Medicine, 2020, 107: 101929.
    [16] 王奎, 黄福珍. 基于光照补偿的HSV空间多尺度Retinex图像增强[J/OL]. 激光与光电子学进展[2023-01-29]. http://kns.cnki.net/kcms/detail/31.1690.TN.20210713.1635.050.html.

    WANG K, Huang F Z. Multi-scale Retinex Image Enhancement in HSV Space Based on Illumination Compensation[J/OL]. Laser & Optoelectronics Progress [2023-01-29]. http://kns.cnki.net/kcms/detail/31.1690.TN.20210713.1635.050.html
    [17] ZHANG Z, DAI Y, MA C. Design of selectively multilayered periodic gratings by PSO algorithm for radiative cooling[J]. Optics Communications, 2021, 500: 127323.
    [18] Bakhshipour M, Namdari F, Samadinasab S. Optimal coordination of overcurrent relays with constraining communication links using DE–GA algorithm[J]. Electrical Engineering, 2021: 1-15.
    [19] 吕晓宁, 刘扬阳, 谭政, 等. 一种偏振普适性多尺度实时的图像去雾算法[J]. 光子学报, 2019, 48(8): 117-127. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB201908014.htm

    LU Xiaoning, LIU Yangyang, TAN Zheng, et al. A polarizing universal multi-scale and real-time image defogging algorithm[J]. Acta Photonica Sinica, 2019, 48(8): 117-127. https://www.cnki.com.cn/Article/CJFDTOTAL-GZXB201908014.htm
    [20] 吴鹏飞, 王辉亮, 雷思琛, 等. 大气湍流环境下光斑中心定位算法[J/OL]. 光子学报[2022-03-15]. http://kns.cnki.net/kcms/detail/61.1235.O4.20211022.1807.008.html.

    WU Pengfei, WANG Huiliang, LEI Sichen, et al. Spot center localization algorithm in atmospheric turbulence environment[J/OL]. Acta Photonica Sinica [2022-03-15]. http://kns.cnki.net/kcms/detail/61.1235.O4.20211022.1807.008.html.
  • 加载中
图(12) / 表(2)
计量
  • 文章访问数:  180
  • HTML全文浏览量:  79
  • PDF下载量:  61
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-05-14
  • 修回日期:  2022-08-22
  • 刊出日期:  2023-02-20

目录

    /

    返回文章
    返回