基于小波变换和改进双边滤波的红外图像增强算法

郝锦虎; 杜玉红; 王帅; 任维佳

基于小波变换和改进双边滤波的红外图像增强算法

郝锦虎^{1, 2,},
杜玉红^{1, 2, ,},
王帅^{1, 2},
任维佳^{1, 2}

1.
天津工业大学机械工程学院, 天津 300387
2.
天津市现代机电装备技术重点实验室, 天津 300387

详细信息

作者简介:
郝锦虎（1998-），男，硕士研究生，主要从事图像处理以及计算机视觉等方面研究。E-mail：1135046322@qq.com

通讯作者:
杜玉红（1974-），女，博士，教授，主要研究方向为图像处理及模式识别、智能控制与检测。E-mail：duyuhong@tiangong.edu.cn

中图分类号: TP391.9
计量
- 文章访问数: 65
- HTML全文浏览量: 51
- PDF下载量: 30
出版历程
- 收稿日期: 2023-01-08
- 修回日期: 2023-03-13
- 刊出日期: 2024-09-19

Infrared Image Enhancement Algorithm Based on Wavelet Transform and Improved Bilateral Filtering

HAO Jinhu^{1, 2,},
DU Yuhong^{1, 2, ,},
WANG Shuai^{1, 2},
REN Weijia^{1, 2}

1.
School of Mechanical Engineering, Tiangong University, Tianjin 300387, China
2.
Tianjin Key Laboratory of Modern Mechanical and Electrical Equipment Technology, Tianjin 300387, China

摘要

摘要:
针对炮车打靶、夜间车辆侦察、航空航天、士兵巡逻过程中红外图像边缘模糊、对比度低、细节不清晰等问题，本文提出了基于小波变换改进双边滤波的Retinex图像增强算法和改进阈值函数去噪算法。将红外图像进行小波分解，获得红外图像的低、高频系数；对高频进行改进阈值函数增强处理，实现自适应选取像素值域标准差对红外图像进行去噪处理；对低频采用改进双边滤波Retinex图像增强算法处理，平滑红外图像保持图像细节；对高、低频图像进行小波重构，得到重构红外图像；最后进行模糊集函数处理，增强红外图像的对比度。实验结果表明，本文改进算法与对比度受限的自适应直方图均衡方法、多尺度Retinex图像增强方法等相比，有效去除了噪声、细节丰富、背景抑制能力以及对比度提升效果好。
- 红外图像 /
- 小波分解 /
- 双边滤波 /
- 阈值函数 /
- 模糊集函数
Abstract:
To address challenges such as blurry edges, low contrast, and unclear details in infrared images used in artillery shooting, night vehicle reconnaissance, aerospace, and soldiers' patrolling, this study proposes an enhanced Retinex image enhancement algorithm. The method integrates wavelet transform, improved bilateral filtering, an enhanced threshold function denoising algorithm, and fuzzy set functions. First, the infrared image undergoes wavelet decomposition to extract low and high-frequency coefficients. Subsequently, high-frequency components are enhanced using an improved threshold function, adapting σr for denoising purposes. An improved bilateral filtering Retinex algorithm is employed to smooth the infrared image while preserving essential details. The high and low-frequency components are recombined through wavelet reconstruction to reconstruct the enhanced infrared image. A fuzzy set function is applied to further enhance the contrast of the infrared image. Experimental results validate the effectiveness of the proposed algorithm. It effectively reduces noise, enriches image details, suppresses background interference, and enhances contrast compared to conventional methods such as adaptive histogram equalization and multi-scale Retinex image enhancement. This approach not only enhances the quality of infrared images for critical applications but also demonstrates significant improvements over existing methods in terms of clarity and detail retention.
- infrared image /
- wavelet decomposition /
- bilateral filtering /
- threshold function /
- fuzzy set function

HTML全文

图 1 算法原理图

Figure 1. Algorithm schematic diagram

下载: 全尺寸图片幻灯片

图 2 模糊集增强效果图

Figure 2. Enhancement effect of fuzzy set

下载: 全尺寸图片幻灯片

图 3 双边滤波Retinex改进算法前后对比

Figure 3. Comparison of bilateral filtering Retinex improved algorithm before and after

下载: 全尺寸图片幻灯片

图 4 常规阈值函数

Figure 4. Conventional threshold function

下载: 全尺寸图片幻灯片

图 5 sgn、tanh形态变化

Figure 5. Morphological changes of sgn and tanh

下载: 全尺寸图片幻灯片

图 6 改进后阈值函数对比

Figure 6. Comparison of improved threshold function

下载: 全尺寸图片幻灯片

图 7 阈值函数效果对比

Figure 7. Effect comparison of threshold function

下载: 全尺寸图片幻灯片

图 8 场景一对比图

Figure 8. Comparison diagram of scene one

下载: 全尺寸图片幻灯片

图 9 场景二对比图

Figure 9. Comparison diagram of scene two

下载: 全尺寸图片幻灯片

图 10 场景三对比图

Figure 10. Comparison diagram of scene three

下载: 全尺寸图片幻灯片

表 1 增强后的峰值信噪比

Table 1 PSNR after enhancement

	Scene one	Scene two	Scene three
Literature[3]	20.9783	31.6453	30.2314
MSR	22.7092	31.5531	31.9476
BSSR	29.8193	37.9954	37.7579
Literature[5]	32.3434	32.2827	38.1083
Proposed	39.7074	40.6664	44.8500

下载: 导出CSV

表 2 增强后的平均梯度

Table 2 AG after enhancement

	Scene one	Scene two	Scene three
Literature[3]	15.5345	3.6346	4.7657
MSR	17.5824	4.0818	4.9778
BSSR	10.4854	3.0282	3.8244
Literature[5]	11.4232	3.7042	3.7892
Proposed	18.2645	4.1773	5.3737

下载: 导出CSV

表 3 增强后的信息熵

Table 3 IE after enhancement

	Scene one	Scene two	Scene three
Literature[3]	7.2342	7.9845	7.1534
MSR	7.7833	7.4254	7.5192
BSSR	6.9225	6.9165	6.6735
Literature[5]	7.0304	6.7047	6.8864
Proposed	8.5381	7.8748	7.9157

下载: 导出CSV

表 4 运算效率

Table 4 Operational efficiency

	Scene one	Scene two	Scene three
Literature[3]	0.5346	0.7367	0.7487
MSR	0.4232	0.5234	0.7842
BSSR	1.3578	1.1167	1.0732
Literature[5]	1.0018	0.9251	0.7438
Proposed	0.7698	0.6575	0.7742

下载: 导出CSV

参考文献(17)

[1]	Paul Abhisek, Sutradhar Tandra, Bhattacharya Paritosh. Adaptive clip-limit-based bi-histogram equalization algorithm for infrared image enhancement[J]. Applied Optics, 2020, 59(28): 9032-9041. DOI: 10.1364/AO.395848
[2]	曹军峰, 史加成, 罗海波, 等. 采用聚类分割和直方图均衡的图像增强算法[J]. 红外与激光工程, 2012, 41(12): 3436-3441. DOI: 10.3969/j.issn.1007-2276.2012.12.053 CAO Junfeng, SHI Jiacheng, LUO Haibo, et al. Image enhancement algorithm using clustering segmentation and histogram equalization[J]. Infrared and Laser Engineering, 2012, 41(12): 3436-3441. DOI: 10.3969/j.issn.1007-2276.2012.12.053
[3]	李凌杰, 陈菲菲. 基于改进直方图的红外图像增强方法[J]. 航空兵器, 2022, 29(2): 101-105. LI Lingjie, CHEN Feifei. Infrared image enhancement method based on improved histogram [J]. Aviation Weapons, 2022, 29(2): 101-105.
[4]	汪伟, 许德海, 任明艺. 一种改进的红外图像自适应增强方法[J]. 红外与激光工程, 2021, 50(11): 419-427. WANG Wei, XU Dehai, REN Mingyi. An improved adaptive enhancement method for infrared images[J]. Infrared and Laser Engineering, 2021, 50(11): 419-427.
[5]	陈韵竹, 郭剑辉. 基于Canny算子加权引导滤波的Retinex医学图像增强算法[J]. 计算机与数字工程, 2019, 47(2): 407-411, 480. DOI: 10.3969/j.issn.1672-9722.2019.02.030 CHEN Yunzhu, GUO Jianhui. Retinex medical image enhancement algorithm based on Canny operator weighted guided filtering[J]. Computer and Digital Engineering, 2019, 47(2): 407-411, 480. DOI: 10.3969/j.issn.1672-9722.2019.02.030
[6]	Hassan Najmul, Ullah Sami, Bhatti Naeem, et al. The Retinex based improved underwater image enhancement[J]. Multimedia Tools and Applications, 2020, 80(2): 1839-1857.
[7]	常戬, 贺春泽, 董育理, 等. 改进双边滤波和阈值函数的图像增强算法[J]. 计算机工程与应用, 2020, 56(3): 207-213. CHANG Jian, HE Chunze, DONG Yuli, et al. Image enhancement algorithm with improved bilateral filtering and threshold function[J]. Computer Engineering and Application, 2020, 56(3): 207-213.
[8]	LIN Chang, ZHOU Haifeng, CHEN Wu. Gaussian pyramid transform retinex image enhancement algorithm based on bilateral filtering[J]. Laser & Optoelectronics Progress, 2020, 57(16): 161019.
[9]	LU Peng, HUANG Qingjiu. Robotic weld image enhancement based on improved bilateral filtering and CLAHE algorithm[J]. Electronics, 2022, 11(21): 3629-3629. DOI: 10.3390/electronics11213629
[10]	张晓东, 秦娟娟, 贾仲仲. 多尺度Retinex在图像去雾算法中的应用研究[J]. 西昌学院学报(自然科学版), 2021, 35(3): 60-65. DOI: 10.16104/j.issn.1673-1891.2021.03.013. ZHANG Xiaodong, QIN Juanjuan, JIA Zhongzhong. Research on the application of multi-scale Retinex in image defogging algorithm[J]. Journal of Xichang University (Natural Science Edition), 2021, 35(3): 60-65. DOI: 10.16104/j.issn.1673-1891.2021.03.013.
[11]	魏亮, 王炎, 胡文浩, 等. 基于双域分解的夜间车辆红外图像研究[J]. 激光与红外, 2021, 51(11): 1538-1544. DOI: 10.3969/j.issn.1001-5078.2021.11.022 WEI Liang, WANG Yan, HU Wenhao, et al. Research on infrared images of night vehicles based on dual domain decomposition[J]. Laser and Infrared, 2021, 51(11): 1538-1544. DOI: 10.3969/j.issn.1001-5078.2021.11.022
[12]	陈超. 改进单尺度Retinex算法在图像增强中的应用[J]. 计算机应用与软件, 2013, 30(4): 55-57, 74. DOI: 10.3969/j.issn.1000-386x.2013.04.016 CHEN Chao. Application of improved single scale Retinex algorithm in image enhancement[J]. Computer Application and Software, 2013, 30(4): 55-57, 74. DOI: 10.3969/j.issn.1000-386x.2013.04.016
[13]	张铮, 王孙强, 熊盛辉, 等. 结合小波变换和CLAHE的图像增强算法[J]. 现代电子技术, 2022, 45(3): 48-51. DOI: 10.16652/j.issn.1004-373x.2022.03.010. ZHANG Zheng, WANG Sunqiang, XIONG Shenghui et al. Image enhancement algorithm combining wavelet transform and CLAHE[J]. Modern Electronic Technology, 2022, 45(3): 48-51. DOI: 10.16652/j.issn.1004-373x.2022.03.010.
[14]	Arunachalaperumal C, Dhilipkumar S. An efficient image quality enhancement using wavelet transform[J]. Materials Today: Proceedings, 2020, 24(3): 2004-2010.
[15]	Donoho D L. De-noising by soft-thresholding[J]. IEEE Transactions on Information Theory, 1995, 41(3): 613-627. DOI: 10.1109/18.382009
[16]	朱荣亮, 陶晋宜. 基于改进小波阈值去噪算法的心电信号处理及仿真[J]. 数学的实践与认识, 2019, 49(5): 143-150. ZHU Rongliang, TAO Jinyi. ECG signal processing and simulation based on improved wavelet threshold denoising algorithm[J]. Mathematical Practice and Understanding, 2019, 49(5): 143-150.
[17]	徐景秀, 张青. 改进小波软阈值函数在图像去噪中的研究应用[J]. 计算机工程与科学, 2022, 44(1): 92-101. DOI: 10.3969/j.issn.1007-130X.2022.01.011 XU Jingxiu, ZHANG Qing. Research and application of improved wavelet soft threshold function in image denoising[J]. Computer Engineering and Science, 2022, 44(1): 92-101. DOI: 10.3969/j.issn.1007-130X.2022.01.011

施引文献(3)

期刊类型引用(2)

1.	赵佳乐，王广龙，周冰，应家驹，王强辉，李秉璇. 基于边缘剔除的陆基高光谱图像噪声评估方法. 激光技术. 2023(01): 121-126 . 百度学术
2.	闫钧华，黄伟，张寅，许祯瑜，苏恺. 天基高光谱图像仿真算法. 电子设计工程. 2019(13): 165-170 . 百度学术