基于多尺度局部直方图均衡化的矿井图像增强方法

涂毅晗; 汪普庆

doi:10.13272/j.issn.1671-251x.2023010015

基于多尺度局部直方图均衡化的矿井图像增强方法

doi: 10.13272/j.issn.1671-251x.2023010015

江西应用科技学院软件与区块链学院, 江西南昌　330100

基金项目: 江西省教育科学“十四五”规划课题(22YB369)；江西省教育厅科学技术研究项目(GJJ212517)；江西省教育科学“十三五”规划 2019年度课题(19YB266)；江西省高等学校教学改革研究项目(JXJG-21-61-1)。

详细信息

作者简介:
涂毅晗(1980—)，女，河南周口人，副教授，硕士，研究方向为图形图像处理和智能信息处理，E-mail：150093605@qq.com

中图分类号: TD67
计量
- 文章访问数: 645
- HTML全文浏览量: 49
- PDF下载量: 13
- 被引次数: 0
出版历程
- 收稿日期: 2023-01-06
- 修回日期: 2023-07-26
- 网络出版日期: 2023-09-04

Mine image enhancement method based on multi-scale local histogram equalization

School of Software and Blockchain, Jiangxi University of Applied Science, Nanchang 330100, China

摘要

摘要: 针对当前常用的直方图均衡化、基于Retinex理论、基于同态滤波、基于小波分析等矿井图像增强方法存在欠增强、过增强等问题，提出了一种基于多尺度局部直方图均衡化的矿井图像增强方法。根据HSI颜色空间图像的颜色分量（色调分量、饱和度分量）与亮度分量相互独立特性，将矿井低照度RGB图像转换到HSI颜色空间；采用双边滤波将亮度分量分解为光照图像和反射图像；对光照图像进行小、中、大3个尺度分块，对图像块分别进行局部直方图均衡化处理，以提升图像亮度和对比度；对反射图像进行8方向梯度增强，以丰富图像的纹理边缘；将经多尺度局部直方图均衡化的光照图像和方向梯度增强的反射图像进行Retinex反变换，得到增强的亮度分量，将其与色调分量和饱和度分量转换至RGB颜色空间，得到增强的矿井图像。采用煤矿井下实际监控图像对基于多尺度局部直方图均衡化的矿井图像增强方法进行实验验证，对其增强效果进行主客观评价。结果表明：该方法与现有图像增强方法相比，在图像亮度和对比度方面均有更大的提升，细节信息更丰富，信息熵提升7.23%以上，平均梯度均值提升31.6%以上，具有更好的图像增强效果。
- 矿井监控图像 /
- 低照度图像 /
- 图像增强 /
- 双边滤波 /
- 局部直方图均衡化 /
- 方向梯度算子
Abstract: There are problems of under-enhancement and over-enhancement in commonly mine image enhancement methods such as histogram equalization, Retinex theory, homomorphic filtering, wavelet analysis, etc. In order to solve the above problems, a mine image enhancement method based on multi-scale local histogram equalization is proposed. According to the independent features of color components (hue component and saturation component) and brightness component of image in HSI color space, the low-light RGB mine image is converted into the HSI color space. The method uses bilateral filtering to decompose the brightness component into lighted images and reflected images. The method divides the lighting image into small, medium, and large blocks, and performs local histogram equalization on each image block to improve image brightness and contrast. The method performs 8-direction gradient enhancement on the reflected image to enrich the texture edges of the image. The method performs Retinex inverse transformation on the light image after multi-scale local histogram equalization and reflection image after directional gradient enhancement to obtain the enhanced brightness component. Then the brightness, hue and saturation components are transformed into RGB color space to obtain an enhanced mine image. Experimental verification of the mine image enhancement method based on multi-scale local histogram equalization is conducted by using actual monitoring images of coal mines. The enhancement effect is evaluated subjectively and objectively. The results show that compared with existing image enhancement methods, this method has a greater improvement in image brightness and contrast with richer detail information. The information entropy has increased by over 7.23%, and the mean average gradient has increased by over 31.6%. It has better image enhancement effects.
- mine monitoring images /
- low-light images /
- image enhancement /
- bilateral filtering /
- local histogram equalization /
- directional gradient operator

HTML全文

图 1 基于多尺度局部直方图均衡化的矿井图像增强流程

Figure 1. Flow of mine image enhancement based on multi-scale local histogram equalization

下载: 全尺寸图片幻灯片

图 2 高斯滤波与双边滤波效果

Figure 2. Effect of Gaussian filtering and Bilateral filtering

下载: 全尺寸图片幻灯片

图 3 方向梯度算子

Figure 3. Directional gradient operators

下载: 全尺寸图片幻灯片

图 4 矿井低照度图像

Figure 4. Mine low-light images

下载: 全尺寸图片幻灯片

图 5 不同方法对矿井低照度图像的增强效果

Figure 5. Enhancement effect of mine low-light images by different methods

下载: 全尺寸图片幻灯片

表 1 增强图像的信息熵

Table 1. Information entropy of enhanced images

图像	经不同方法增强的图像信息熵
图像	未增强	文献[6] 方法	文献[8] 方法	文献[12] 方法	文献[13] 方法	本文方法
1	6.85	7.54	7.64	7.59	7.68	7.93
2	6.16	7.13	7.35	7.39	7.32	7.91
3	5.84	6.64	6.91	7.01	6.96	7.74

下载: 导出CSV

表 2 增强图像的平均梯度

Table 2. Average gradient of enhanced images

图像	经不同方法增强的图像平均梯度
图像	未增强	文献[6] 方法	文献[8] 方法	文献[12] 方法	文献[13] 方法	本文方法
1	13.1	33.4	34.3	41.5	28.1	50.5
2	9.73	33.3	32.9	36.3	26.1	57.7
3	5.91	21.9	16.8	22.9	13.6	24.4

下载: 导出CSV

参考文献(21)

[1]	程德强,郑珍,姜海龙. 一种煤矿井下图像增强算法[J]. 工矿自动化,2015,41(12):31-34. doi: 10.13272/j.issn.1671-251x.2015.12.009 CHENG Deqiang,ZHENG Zhen,JIANG Hailong. An image enhancement algorithm for coal mine underground[J]. Industry and Mine Automation,2015,41(12):31-34. doi: 10.13272/j.issn.1671-251x.2015.12.009
[2]	CHENG Hong,LONG Wei,LI Yanan,et al. Two low illuminance image enhancement algorithms based on grey level mapping[J]. Multimedia Tools and Applications,2021,80(5):1-24.
[3]	GU Zhihao,LI Fang,FANG Faming,et al. A novel Retinex-based fractional-order variational model for images with severely low light[J]. IEEE Transactions on Image Processing,2019,29:3239-3253.
[4]	YUGANDER P,TEJASWINI C H,MEENAKSHI J. MR image enhancement using adaptive weighted mean filtering and homomorphic filtering[J]. Procedia Computer Science,2020,167:677-685. doi: 10.1016/j.procs.2020.03.334
[5]	范凌云,梁修荣. 基于小波分解子带直方图匹配的矿井视频图像增强方法[J]. 金属矿山,2016(6):130-133. FAN Lingyun,LIANG Xiurong. Mine video images enhancement method based on the histogram matching method of the sub-bands of wavelet transform[J]. Metal Mine,2016(6):130-133.
[6]	TAN S F,MAT ISA N A. Exposure based multi-histogram equalization contrast enhancement for non-uniform illumination images[J]. IEEE Access,2019,7:70842-70861. doi: 10.1109/ACCESS.2019.2918557
[7]	SINGH D,KUMAR S. Infrared image enhancement using differential evolution based on double plateau histogram equalization[J]. Soft Computing for Problem Solving,2021,1392:757-770.
[8]	GUO Xiaojie,LI Yu,LING Haibin. LIME:low-light image enhancement via illumination map estimation[J]. IEEE Transactions on Image Processing,2017,26(2):982-993. doi: 10.1109/TIP.2016.2639450
[9]	李晓宇,吕进来,郝晓丽. 一种改进的Retinex矿井图像增强算法[J]. 科学技术与工程,2020,20(29):12028-12034. doi: 10.3969/j.issn.1671-1815.2020.29.030 LI Xiaoyu,LYU Jinlai,HAO Xiaoli. An improved enhancement algorithm of mine image based on Retinex[J]. Science Technology and Engineering,2020,20(29):12028-12034. doi: 10.3969/j.issn.1671-1815.2020.29.030
[10]	GUO Yanhui,KE Xue,MA Jie,et al. A pipeline neural network for low-light image enhancement[J]. IEEE Access,2019,7:13737-13744. doi: 10.1109/ACCESS.2019.2891957
[11]	邵小强,杨涛,卫晋阳,等. 改进同态滤波的矿井监控视频图像增强算法[J]. 西安科技大学学报,2022,42(6):1205-1213. doi: 10.13800/j.cnki.xakjdxxb.2022.0619 SHAO Xiaoqiang,YANG Tao,WEI Jinyang,et al. Image enhancement algorithm of mine surveillance video using improved homomorphic filtering[J]. Journal of Xi'an University of Science and Technology,2022,42(6):1205-1213. doi: 10.13800/j.cnki.xakjdxxb.2022.0619
[12]	龚云, 颉昕宇. 一种改进同态滤波的井下图像增强算法[J/OL]. 煤炭科学技术: 1-8[2023-01-03]. 10.13199/j.cnki.cst.2021-0774">https://doi.org/ 10.13199/j.cnki.cst.2021-0774. DOI: 10.13199/j.cnki.cst.2021-0774. GONG Yun, XIE Xinyu. A downhole image enhancement algorithm based on improved homomorphic filtering[J/OL]. Coal Science and Technology: 1-8[2023-01-03]. 10.13199/j.cnki.cst.2021-0774">https://doi.org/ 10.13199/j.cnki.cst.2021-0774. DOI: 10.13199/j.cnki.cst.2021-0774.
[13]	唐守锋,史可,仝光明,等. 一种矿井低照度图像增强算法[J]. 工矿自动化,2021,47(10):32-36. TANG Shoufeng,SHI Ke,TONG Guangming,et al. A mine low illumination image enhancement algorithm[J]. Industry and Mine Automation,2021,47(10):32-36.
[14]	KAMIYAMA M,TAGUCHI A. HSI color space with same gamut of RGB color space[J]. IEICE Transactions on Fundamentals of Electronics,Communications and Computer Sciences,2017,E100-A(1):341-344. doi: 10.1587/transfun.E100.A.341
[15]	KAMIYAMA M,TAGUCHI A. Color conversion formula with saturation correction from HSI color space to RGB color space[J]. IEICE Transactions on Fundamentals of Electronics,Communications and Computer Sciences,2021,E104-A(7):1000-1005. doi: 10.1587/transfun.2020EAL2087
[16]	JOBSON D,RAHMAN Z,WOODELL G. Properties and performance of a center/surround retinex[J]. IEEE Transactions on Image Processing,1997,6(3):451-462. doi: 10.1109/83.557356
[17]	CHEN Bohao,TSENG Y S,YIN Jiali. Gaussian-adaptive bilateral filter[J]. IEEE Signal Processing Letters,2020,27:1670-1674. doi: 10.1109/LSP.2020.3024990
[18]	KRISHNA G,ARUNITA D,SWARNAJIT R,et al. Histogram equalization variants as optimization problems:a review[J]. Archives of Computational Methods in Engineering,2021,28(3):1471-1496. doi: 10.1007/s11831-020-09425-1
[19]	KAR M,RAVICHANDRAN G,ELANGOVAN P,et al. Analysis of diagnostic features from fundus image using multiscale wavelet decomposition[J]. ICIC Express Letters,2019,10(2):175-184.
[20]	CHEN Jiayi,ZHAN Yinwei,CAO Huiying. Adaptive sequentially weighted median filter for image highly corrupted by impulse noise[J]. IEEE Access,2019,7:158545-158556. doi: 10.1109/ACCESS.2019.2950348
[21]	乔佳伟,贾运红. Retinex算法在煤矿井下图像增强的应用研究[J]. 煤炭技术,2022,41(3):193-195. doi: 10.13301/j.cnki.ct.2022.03.046 QIAO Jiawei,JIA Yunhong. Research on application of Retinex algorithm in image enhancement in coal mine[J]. Coal Technology,2022,41(3):193-195. doi: 10.13301/j.cnki.ct.2022.03.046