基于视觉信息补偿的光照不均图像增强方法

doi:10.13229/j.cnki.jdxbgxb.20230235

摘要/Abstract

摘要：

针对因光照不均导致图像灰度值分布不均、噪声大、视觉传达效果差等问题，提出基于视觉信息补偿的光照不均图像增强方法。计算图像中不同目标和背景区域的像素灰度值，构建灰度衰减序列，构建衰减函数对最弱像素点周围的每一个背景点进行加权处理，采用同态滤波函数根据图像中光线的分量值变化去噪。采用视觉信息补偿法计算图中每个区域的像素值，并转换为分量值模式，按照亮度总量值和局部值进行互补增强。实验数据表明：本文方法增强效果佳，图像清晰度得到了提高，细节刻画效果好。

关键词: 视觉信息补偿, 光照不均, 图像增强, 灰度衰减函数, 亮度总量值

Abstract:

Aiming at the problems of uneven distribution of grayscale values and high noise in images caused by uneven lighting， as well as poor visual communication effect， a visual information compensation based method for enhancing images with uneven lighting is proposed. Calculate the pixel grayscale values of different targets and background regions in the image， construct a grayscale attenuation sequence， construct an attenuation function to weight each background point around the weakest pixel， and use a homomorphic filtering function to denoise based on changes in the component of light in the image. By using the visual information compensation method to calculate the pixel values of each region in the graph， and converting them into component modes， complementary enhancement is implemented based on the total brightness value and local values. The experimental data proves that the proposed method has good enhancement effect， improved image clarity， and good detail characterization effect.

Key words: visual information compensation, uneven illumination, image enhancement, gray attenuation function, total brightness value

中图分类号:

TP327

王欣,党电太. 基于视觉信息补偿的光照不均图像增强方法[J]. 吉林大学学报(工学版), 2024, 54(8): 2301-2306.

Xin WANG,Dian-tai DANG. Image enhancement method of uneven illumination based on visual information compensation[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(8): 2301-2306.

图/表 3

图1

图2

图3

参考文献 20

1	刘卫东, 李吉玉, 张文博, 等. 基于Retinex和ADMM优化的水下光照不均匀图像增强算法[J].西北工业大学学报, 2021, 39(4): 824-830.
	Liu Wei-dong, Li Ji-yu, Zhang Wen-bo, et al. Underwater illumination nonuniform image enhancement algorithm based on Retinex and ADMM optimization[J]. Journal of Northwest University of Technology, 2021,39(4): 824-830.
2	贾洪博, 石蕴玉, 刘翔, 等. 基于光照重映射的低照度图像增强算法[J]. 激光与光电子学进展, 2021, 58(22): 230-236.
	Jia Hong-bo, Shi Yun-yu, Liu Xiang, et al. Low-illuminance image enhancement algorithm based on light remapping[J]. Progress in Laser and Optoelectronics, 2021, 58(22): 230-236.
3	钱宇华, 卢佳佳, 王克琪, 等. 基于信息多重蒸馏的轻量化低照度图像增强方法[J]. 山西大学学报: 自然科学版, 2021, 44(5): 887-896.
	Qian Yu-hua, Lu Jia-jia, Wang Ke-qi, et al. Light and low illumination image enhancement method based on information multiple distillation[J]. Journal of Shanxi University (Natural Science Edition), 2021,44(5): 887-896.
4	耿磊, 史瑞资, 刘彦北, 等. 基于多重感受野UNet的仪表图像分割方法[J].计算机工程与设计, 2022, 43(3): 771-777.
	Geng Lei, Shi Rui-zi, Liu Yan-bei, et al. Instrument image segmentation method based on multiple receptive field UNet[J]. Computer Engineering and Design, 2022, 43(3): 771-777.
5	黄子蒙, 徐望明, 但愿. 基于对称亮度映射和虚拟多曝光融合的非均匀光照图像增强[J]. 液晶与显示, 2022, 37(12): 1580-1589.
	Huang Zi-meng, Xu Wang-ming, Dan Yuan. Non-uniform illumination image enhancement based on symmetric brightness mapping and virtual multi-exposure fusion[J]. Liquid Crystal and Display, 2022, 37(12): 1580-1589.
6	蒲恬, 张子夜, 彭真明. 保持自然度的非均匀光照图像增强的Retinex算法[J]. 数据采集与处理, 2021, 36(1): 76-84.
	Pu Tian, Zhang Zi-ye, Peng Zhen-ming. Retinex algorithm for image enhancement under non-uniform illumination with naturalness[J]. Data Acquisition and Processing, 2021,36(1): 76-84.
7	张志文, 刘天歌, 聂鹏举. 基于实景数据增强和双路径融合网络的实时街景语义分割算法[J]. 电子学报, 2022, 50(7): 1609-1620.
	Zhang Zhi-wen, Liu Tian-ge, Nie Peng-ju. Real-time street scene semantic segmentation algorithm based on real-time data enhancement and dual-path fusion network[J]. Journal of Electronics, 2022, 50 (7): 1609-1620.
8	吴建斌, 牛玉贞, 张宇杰. 基于图像自身信息感知的无参考低光照图像增强[J]. 小型微型计算机系统, 2021, 42(6): 1243-1249.
	Wu Jian-bin, Niu Yu-zhen, Zhang Yu-jie. Unreferenced low-light image enhancement based on image information perception[J]. Miniature Microcomputer System, 2021, 42(6): 1243-1249.
9	王宇龙, 王然风, 曹文艳. 等 , 联合CLAHE和BM3D的浮选泡沫图像预处理方法[J]. 煤炭技术, 2022, 41(6):222-224.
	Wang Yu-long, Wang Ran-feng, Cao Wen-yan, et al. The flotation foam image pre-processing method combined with CLAHE and BM3D[J]. Coal Technology, 2022,41(6): 222-224.
10	翟艳, 潘振宽, 魏伟波. 基于法矢量雅可比的总广义变差图像修复模型[J]. 计算机仿真, 2022, 39(3):150-199.
	Zhai Yan, Pan Zhen-kuan, Wei Wei-bo. A total generalized variation model for image inpainting using the jacobian of normal[J]. Computer Simulation, 2022, 39(3):150-199.
11	Wang J, 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.
12	Xu J J, Zhang H, Tang C S, et al. Automatic soil crack recognition under uneven illumination condition with the application of artificial intelligence[J]. Engineering Geology,2022(296): 106495.
13	Li B, Xie W, Zhang L W, et al. Adaptive fractional differential algorithm for image edge enhancement and texture preserve using fuzzy sets[J]. IET Image Processing,2023,17(7):2204-2213.
14	He L, Liu S X, Long W, et al. Low-light image enhancement via span correction function and discrete mapping model[J]. IET Image Processing,2023,17(6):1812-1836.
15	Liao T L, Peng C Y, Hou Y Y. Application of multi-party computation and error correction with image enhancement and convolution neural networks based on cloud computing[J]. IET Image Processing,2023,17(6):1931-1950.
16	Yang L, Yang B, Gu X. Adversarial reconstruction CNN for illumination-robust frontal face image recovery and recognition[J]. International Journal of Cognitive Informatics and Natural Intelligence, 2021, 15(2):18-33.
17	肖明尧, 李雄飞, 朱芮. 基于NSST域像素相关分析的医学图像融合[J]. 吉林大学学报: 工学版, 2023, 53(9): 2640-2648.
	Xiao Ming-yao, Li Xiong-fei, Zhu rui. Medical image fusion based on pixel correlation analysis in NSST domain[J]. Journal of Jilin University (Engineering and Technology Edition), 2023, 53(9):2640-2648.
18	陈烽, 王浩. 基于多通道视觉注意力的模糊图像质量复原算法设计[J]. 吉林大学学报: 工学版, 2023, 53(9): 2626-2631.
	Chen Feng, Wang Hao. Design of fuzzy image quality restoration algorithm based on multi⁃channel visual attention[J].Journal of Jilin University (Engineering and Technology Edition), 2023, 53(9):2626-2631.
19	He L, Long W, Liu S, et al. A night low‐illumination image enhancement model based on small probability area filtering and lossless mapping enhancement[J]. IET Image Processing, 2021, 15(13): 3221-3238.
20	Acharya U K, Kumar S. Image sub-division and quadruple clipped adaptive histogram equalization (ISQCAHE) for low exposure image enhancement[J]. Multidimensional Systems and Signal Processing,2023, 34(1): 25-45.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

[1]	张锦洲,姬世青,谭创. 融合卷积神经网络和双边滤波的相贯线焊缝提取算法[J]. 吉林大学学报(工学版), 2024, 54(8): 2313-2318.
[2]	王德兴,高凯,袁红春,杨钰锐,王越,孔令栋. 基于色彩校正和TransFormer细节锐化的水下图像增强[J]. 吉林大学学报(工学版), 2024, 54(3): 785-796.
[3]	刘铭,杨雨航,邹松霖,肖志成,张永刚. 增强边缘检测图像算法在多书识别中的应用[J]. 吉林大学学报(工学版), 2022, 52(4): 891-896.
[4]	蒋华伟,杨震,张鑫,董前林. 图像去雾算法研究进展[J]. 吉林大学学报(工学版), 2021, 51(4): 1169-1181.
[5]	刘富,刘璐,侯涛,刘云. 基于优化MSR的夜间道路图像增强方法[J]. 吉林大学学报(工学版), 2021, 51(1): 323-330.
[6]	徐岩,孙美双. 基于卷积神经网络的水下图像增强方法[J]. 吉林大学学报(工学版), 2018, 48(6): 1895-1903.
[7]	吴一全, 吴诗婳, 张宇飞. 基于混沌粒子群优化的Contourlet域红外图像自适应增强[J]. 吉林大学学报(工学版), 2014, 44(5): 1466-1473.
[8]	李骜, 李一兵, 刘丹丹, 杨晓冬. 基于非下采样轮廓波的多曝光工件图像Retinex增强方法[J]. , 2012, (06): 1592-1596.
[9]	孙明超, 张崇, 刘晶红. 多尺度图像增强可见光与红外图像融合 [J]. , 2012, (03): 738-742.