Infrared and Visible-Light Image Fusion Based on FCM and Guided Filtering
-
摘要: 针对传统红外与可见光图像融合算法中存在的目标模糊、细节丢失、算法不稳定等问题,提出了一种基于模糊C均值聚类(Fuzzy C-means, FCM)与引导滤波的红外与可见光图像融合方法。原图像经过非下采样剪切波变换(Nonsubsampled Shearlet Transform, NSST)后对低频子带进行引导滤波增强,再利用FCM与双通道脉冲发放皮层模型(Dual Channel Spiking Cortical Model, DCSCM)结合对高低频子带进行融合,最后经NSST逆变换得到融合图像。实验结果表明,本文算法稳定,主观评价上所得融合图像目标明确,细节保留较为完整,客观评价上在标准差、互信息、平均梯度、信息熵和边缘保留因子等评价标准中表现优良。
-
关键词:
- 图像处理 /
- 模糊C均值聚类 /
- 引导滤波 /
- 双通道脉冲发放皮层模型
Abstract: To solve the problems of vague targets, detail loss, and algorithm instability in traditional infrared and visible-light image fusion algorithms, a fusion method based on fuzzy c-means (FCM) clustering and guided filtering is proposed. The low-frequency sub-band was enhanced by guided filtering after applying a non-subsampled shearlet transform (NSST) to the original image. The low- and high-frequency sub-bands were then fused using FCM clustering and a dual-channel spiking cortical model. Finally, the fused image was obtained using an inverse NSST transform. The experimental results showed that the proposed algorithm was stable, the fusion image had clear targets and relatively complete details in the subjective evaluation, and the algorithm had an excellent standard deviation, mutual information, average gradient, information entropy, and edge retention factor in the objective evaluation.-
Key words:
- image processing /
- fuzzy C-mean /
- guided filtering /
- dual channel spiking cortical model
-
表 1 主观评价尺度评分
Table 1. Subjective evaluation scale score table
Score Quality scale Obstruction scale 5 very nice Lossless image quality 4 nice The image quality is damaged, but it does not hinder viewing 3 normal Clearly see that the image quality is damaged 2 poor Obstruction to viewing 1 very poor Serious impact on viewing 表 2 五分制评价结果
Table 2. Five point evaluation results
First set of image scores Second set of image scores Third set of image scores Professional person 1 4 5 4 Professional person 2 5 5 4 Professional person 3 4 4 4 Nonprofessional person 1 5 5 5 Nonprofessional person 2 5 5 4 Average score 4.6 4.8 4.2 表 3 客观评价指标
Table 3. Objective evaluation results
Image Algorithm STD MI AG EN QAB/F SSIM Group 1 MGFF 48.5438 2.5642 10.7398 7.3355 0.5691 0.5038 MSD 48.3475 2.5589 11.2680 7.2762 0.5925 0.4877 MTD 43.3842 3.0839 9.8755 6.9701 0.5456 0.4722 VIP 44.8607 0.5109 10.4776 7.2307 0.5665 0.6142 FCMA 43.9961 3.1582 10.5662 7.3527 0.6230 0.4964 Proposed 45.0086 3.1720 10.7624 7.3768 0.5978 0.5090 Group 2 MGFF 36.6809 1.7426 4.9351 6.8599 0.4702 0.5268 MSD 52.3717 2.5234 4.7900 7.0811 0.4706 0.4854 MTD 52.1024 3.0416 4.3414 6.8654 0.4563 0.4920 VIP 52.8195 0.3818 4.3009 6.9521 0.5332 0.7334 FCMA 60.5238 3.1647 4.6397 7.3857 0.4877 0.4375 Proposed 60.1718 3.2102 4.6594 7.4388 0.4564 0.4693 Group 3 MGFF 40.0211 1.5924 6.7958 7.2387 0.4799 0.5095 MSD 49.7948 2.3439 6.8837 7.2386 0.5371 0.4871 MTD 60.7380 4.4287 6.3965 7.1101 0.5810 0.4641 VIP 56.0103 0.6042 5.6657 6.7389 0.5663 0.6618 FCMA 57.0775 2.3680 6.1483 7.2681 0.4667 0.4515 Proposed 57.4021 3.0526 6.6048 7.2777 0.5556 0.4753 -
[1] LI Shutao, KANG Xudong, FANG Leyuan, et al. Pixel-level image fusion: a survey of the state of the art[J]. Information Fusion, 2017, 33(1): 100-112 [2] 蔡李美, 李新福, 田学东. 基于分层图像融合的虚拟视点绘制算法[J]. 计算机工程, 2021, 47(4): 204-210. DOI: 10.19678/j.issn.1000-3428.0058057.CAI L M, LI X F, TIAN X D. Virtual viewpoint rendering algorithm based on hierarchical image fusio [J]. Computer Engineering, 2021, 47(4): 204-210. DOI: 10.19678/j.issn.1000-3428.0058057 [3] 冯鑫, 张建华, 胡开群, 等. 基于变分多尺度的红外与可见光图像融合[J]. 电子学报, 2018, 46(3): 680-687. https://www.cnki.com.cn/Article/CJFDTOTAL-DZXU201803025.htmFENG X, ZHANG J H, HU K Q, et al. The infrared and visible image fusion method based on variational multiscale[J]. Acta Electronica Sinica, 2018, 46(3): 680-687. https://www.cnki.com.cn/Article/CJFDTOTAL-DZXU201803025.htm [4] LIU Y, LIU S, WANG Z. A general framework for image fusion based on multi-scale transform and sparse representation[J]. Information Fusion, 2015, 24: 147-164. doi: 10.1016/j.inffus.2014.09.004 [5] 李威, 李忠民. NSST域红外和可见光图像感知融合[J]. 激光与光电子学进展, 2021, 58(20): 202-210. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202120021.htmLI W, LI Z M. NSST-Based perception fusion method for infrared and visible images[J]. Laser & Optoelectronics Progress, 2021, 58(20): 202-210. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202120021.htm [6] ZHAO W D, LU H C. Medical image fusion and denoising with altering sequential filter and adaptive fractional order total variation[J]. IEEE Transactions on Instrumentation and Measurement, 2017, 66(9) : 2283-2294 doi: 10.1109/TIM.2017.2700198 [7] 任亚飞, 张娟梅. 基于NSST多尺度熵的红外与可见光图像融合[J]. 兵器装备工程学报, 2022, 43(7): 278-285. https://www.cnki.com.cn/Article/CJFDTOTAL-CUXI202207042.htmREN Y F, ZHANG J M. Infrared and visible image fusion based on NSST multi-scale entropy[J]. Journal of Ordnance Equipment Engineering, 2022, 43(7): 278-285. https://www.cnki.com.cn/Article/CJFDTOTAL-CUXI202207042.htm [8] ZHOU Z Q, WANG B, LI S, et al. Perceptual fusion of infrared and visible images through a hybrid multiscale decomposition with Gaussian and bilateral filters[J]. Information Fusion, 2016, 30(30): 15-26. [9] 李文, 叶坤涛, 舒蕾蕾, 等. 基于高斯模糊逻辑和ADCSCM的红外与可见光图像融合算法[J]. 红外技术, 2022, 44(7): 693-701. http://hwjs.nvir.cn/article/id/227ae3cd-57b4-4ec7-a248-bdc1de60993cLI W, YE K T, SHU L L, et al. Infrared and visible image fusion algorithm based on gaussian fuzzy logic and adaptive dual-channel spiking cortical model[J]. Infrared Technology, 2022, 44(7): 693-701. http://hwjs.nvir.cn/article/id/227ae3cd-57b4-4ec7-a248-bdc1de60993c [10] 张莲, 杨森淋, 禹红良, 等. 改进非局部核模糊C-均值聚类的红外图像分割[J]. 重庆理工大学学报: 自然科学, 2020, 34(11): 130-137. https://www.cnki.com.cn/Article/CJFDTOTAL-CGGL202011018.htmZHANG L, YANG S L, YU H L, et al. Improved infrared image segmentation based on nonlocal nuclear fuzzy C-means clustering[J]. Journal of Chongqing University of Technology: Natural Science, 2020, 34(11): 130-137. https://www.cnki.com.cn/Article/CJFDTOTAL-CGGL202011018.htm [11] 赵程, 黄永东. 基于滚动导向滤波和混合多尺度分解的红外与可见光图像融合方法[J]. 激光与光电子学进展, 2019, 56(14): 106-120. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ201914013.htmZHAO C, HUANG Y D. Infrared and visible image fusion via rolling guidance filtering and hybrid multi-sacle decomposition[J]. Laser & Optoelectronics Progress, 2019, 56(14): 106-120. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ201914013.htm [12] 李旭超, 刘海宽, 王飞, 等. 图像分割中的模糊聚类方法[J]. 中国图象图形学报, 2012, 17(4): 447-458. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201204004.htmLI X C, LIU H K, WANG F, et al. The survey of fuzzy clustering method for image segmentation[J]. Journal of Image and Graphics, 2012, 17(4): 447-458. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201204004.htm [13] 谢伟, 周玉钦, 游敏. 融合梯度信息的改进引导滤波[J]. 中国图象图形学报, 2016, 21(9): 1119-1126. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201609001.htmXIE W, ZHOU Y, YOU M. Improved guided image filtering integrated with gradient information[J]. Journal of Image and Graphics, 2016, 21(9): 1119-1126. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB201609001.htm [14] 江泽涛, 吴辉, 周哓玲. 基于改进引导滤波和双通道脉冲发放皮层模型的红外与可见光图像融合算法[J]. 光学学报, 2018, 38(2): 0210002. https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201802015.htmJIANG Z T, WU H, ZHOU X L. Infrared and visible image fusion algorithm based on improved guided filtering and dual-channel spiking cortical model[J]. Acta Optica Sinica, 2018, 38(2): 0210002. https://www.cnki.com.cn/Article/CJFDTOTAL-GXXB201802015.htm [15] HUANG W, JING Z L. Evaluation of focus measures in multi-foucus image fusion[J]. Pattern Recognition Letters, 2007, 28(4): 493-500 [16] Bavirisetti D P, XIAO G, ZHAO J, et al. Multi-scale guided image and video fusion: a fast and efficient approach[J]. Circuits Syst Signal Process, 2019, 38: 5576–5605. [17] ZHOU Z Q, WANG B, LI S, et al. Perceptual fusion of infrared and visible images through a hybrid multi-scale decomposition with Gaussian and bilateral filters[J]. Information Fusion, 2016, 30: 16-25. [18] CHEN J, LI X J, LUO L B, et al. Infrared and visible image fusion based on target-enhanced multiscale transform decomposition[J]. Information Sciences, 2020, 508: 64-78. [19] ZHANG Y, ZHANG L J, BAI X Z, et al. Infrared and visual image fusion through infrared feature extraction and visual information preservation[J]. Infrared Physics and Technology, 2017, 83: 227-237. [20] 巩稼民, 刘爱萍, 张晨, 等. 基于FCM与ADSCM的红外与可见光图像融合[J]. 激光与光电子学进展, 2020, 57(20): 222-230. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202020025.htmGONG J M, LIU A P, ZHANG C, et al. Infrared and visible light image fusion based on FCM and ADSCM[J]. Laser & Optoelectronics Progress, 2020, 57(20): 222-230. https://www.cnki.com.cn/Article/CJFDTOTAL-JGDJ202020025.htm