Journal of Jilin University(Engineering and Technology Edition) ›› 2022, Vol. 52 ›› Issue (8): 1857-1864.doi: 10.13229/j.cnki.jdxbgxb20211096

Previous Articles    

Multi⁃focus image fusion algorithm based on pixel⁃level convolutional neural network

Xuan-jing SHEN1,2(),Xue-feng ZHANG1,2,Yu WANG1,2,Yu-bo JIN3()   

  1. 1.College of Computer Science and Technology,Jilin University,Changchun 130012,China
    2.Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education,Jilin University,Changchun 130012,China
    3.Changchun Expert Information Technology Co. ,Ltd. ,Changchun 130012,China
  • Received:2021-10-21 Online:2022-08-01 Published:2022-08-12
  • Contact: Yu-bo JIN E-mail:xjshen@jlu.edu.cn;jinyubo@expservice.cn

Abstract:

In this paper, a novel convolutional neural network(CNN) for multi-focus image fusion is proposed. Compared with existing image fusion methods based on CNN which decompose the source image into several patches and adopt a classifier to estimate whether the patch is focused or defocused, the method in this paper directly converts the whole image into a decision diagram. The pixel-level regression strategy can make use of the complementary information and address the difficulty of estimating blur level around the focused/defocused region. Furthermore, the ringed residual network(RResNet) block is utilized to extract more semantic information from the focused region in image fusion field. In the meanwhile, the structural similarity index(SSIM) loss is utilized to estimate the structural similarity between the generated fusion image and the ground-truth reference to improve the quality of the fused images, and the edge preservation loss function is applied to preserve more gradient information from source image. Experimental results demonstrate that the proposed method is superior to other fusion algorithms in subjective visual effect and objective assessment.

Key words: multi-focus image fusion, deep learning, pixel-level regression, convolutional neural network

CLC Number: 

  • TP391

Fig.1

Schematic diagram of recurrent residual network"

Fig.2

Schematic diagram of proposed algorithm"

Fig.3

Schematic diagram of squeeze and excitation attention mechanism module"

Fig.4

Comparison of our proposed method with other methods on dataset Lytro"

Table 1

Average values of six metrics obtained by several methods on Lytro dataset"

方法AGEISTDVIFQAB/FMI
CNN216.874471.399764.36320.94060.71455.5862
SESF156.935472.040864.48240.94390.71445.6415
MWGF196.744270.109364.18200.92440.69955.3950
MST_SR186.899671.601264.28760.94370.70314.8962
DSIFT46.937072.050964.45180.94270.71495.6584
ECNN136.917371.849564.44880.94000.71345.7165
IFCNN126.933971.989564.27280.93860.68904.6187
CSR204.788250.952462.71710.79390.50264.8318

GF17

本文

6.7656

6.9459

70.1844

72.0919

64.0856

64.4815

0.9283

0.9444

0.7059

0.7153

5.0743

5.6633

Fig.5

Comparison of our proposed method with other methods on the SF dataset"

Table 2

Average values of six metrics obtained by several methods on SF dataset"

方法AGEISTDVIFQAB/FMI
CNN214.791850.495061.01540.86400.51694.1046
SESF154.849351.086561.07060.87060.51764.1208
MWGF194.804750.655161.10960.87960.51714.0131
MST_SR184.790250.426160.96140.87150.50913.7675
DSIFT44.847451.060261.05770.86880.51814.1049
ECNN134.799650.550560.97480.85150.51324.1329
IFCNN124.767450.058360.52220.83570.49973.7195
CSR203.579438.441060.16930.75560.38224.0791
GF174.356645.953660.47380.80730.49363.9264
本文4.849551.087461.08340.88020.51874.1213

Fig.6

Fusion images and corresponding masks obtained by four network architectures"

Table 3

Average values of six metrics of four network architectures"

指标结构1结构2结构3结构4
AG6.88936.92376.93336.9459
EI71.293471.976371.987772.0919
STD64.294364.376564.382264.4815
VIF0.92390.93330.93020.9444
QAB/F0.71320.71420.71440.7153
MI5.32335.44565.45375.6633

Fig.7

Fusion images and corresponding masks obtained by four loss functions"

Table 4

Average values of six metrics of four loss functions"

loss函数1函数2函数3函数4
AG6.92346.93226.93896.9459
EI71.484371.983271.989972.0919
STD64.376864.457664.463864.4815
VIF0.93220.93560.93640.9444
QAB/F0.71280.71360.71450.7153
MI5.43235.45385.46495.6633
1 Li S, Kang X, Fang L, et al. Pixel-level image fusion: a survey of the state of the art[J]. Information Fusion, 2017, 33: 100-112.
2 Huang W, Jing Z. Evaluation of focus measures in multi-focus image fusion[J]. Pattern Recognition Letters, 2007, 28(4): 493-500.
3 Aslantas V, Kurban R. Fusion of multi-focus images using differential evolution algorithm[J]. Expert Systems with Applications, 2010, 37(12): 8861-8870.
4 Liu Y, Liu S, Wang Z. Multi-focus image fusion with dense SIFT[J]. Information Fusion, 2015, 23: 139-155.
5 Hill P, Al-Mualla M E, Bull D. Perceptual image fusion using wavelets[J]. IEEE Transactions on Image Processing, 2016, 26(3): 1076-1088.
6 Yu B, Jia B, Ding L, et al. Hybrid dual-tree complex wavelet transform and support vector machine for digital multi-focus image fusion[J]. Neurocomputing, 2016, 182: 1-9.
7 张强,郭宝龙.基于Curvelet变换的图像融合算法[J]. 吉林大学学报: 工学版, 2007, 37(2): 458-463.
Zhang Qiang, Guo Bao-long. Image fusion algorithm based on Curvelet transform[J]. Journal of Jilin University(Engineering and Technology Edition), 2007, 37(2): 458-463.
8 孙伟, 郭宝龙, 陈龙. 非降采样Contourlet域方向区域多聚焦图像融合算法[J]. 吉林大学学报: 工学版, 2009, 39(5): 1384-1389.
Sun Wei, Guo Bao-long, Chen Long. Multi-focus image fusion algorithm for non-down-sampling Contourlet domain direction region[J]. Journal of Jilin University(Engineering and Technology Edition), 2009, 39(5): 1384-1389.
9 Bhatnagar G, Wu Q M J, Liu Z. Directive contrast based multimodal medical image fusion in NSCT domain[J]. IEEE Transactions on Multimedia, 2013, 15(5): 1014-1024.
10 Liu X, Mei W, Du H. Multi-modality medical image fusion based on image decomposition framework and nonsubsampled shearlet transform[J]. Biomedical Signal Processing and Control, 2018, 40: 343-350.
11 Liu Y, Chen X, Peng H, et al. Multi-focus image fusion with a deep convolutional neural network[J]. Information Fusion, 2017, 36: 191-207.
12 Zhang Y, Liu Y, Sun P, et al. IFCNN: a general image fusion framework based on convolutional neural network[J]. Information Fusion, 2020, 54: 99-118.
13 Amin-Naji M, Aghagolzadeh A, Ezoji M. Ensemble of CNN for multi-focus image fusion[J]. Information fusion, 2019, 51: 201-214.
14 Gai D, Shen X, Chen H, et al. Multi-focus image fusion method based on two stage of convolutional neural network[J]. Signal Processing, 2020, 176: 107681.
15 Ma B, Zhu Y, Yin X, et al. Sesf-fuse: an unsupervised deep model for multi-focus image fusion[J]. Neural Computing and Applications, 2021, 33(11): 5793-5804.
16 Zhang H, Le Z, Shao Z, et al. MFF-GAN: an unsupervised generative adversarial network with adaptive and gradient joint constraints for multi-focus image fusion[J]. Information Fusion, 2021, 66: 40-53.
17 Li S, Kang X, Hu J. Image fusion with guided filtering[J]. IEEE Transactions on Image Processing, 2013, 22(7): 2864-2875.
18 Fakhari F, Mosavi M R, Lajvardi M M. Image fusion based on multi-scale transform and sparse representation: an image energy approach[J]. Iet Image Processing, 2017, 11(11): 1041-1049.
19 Zhou Z, Li S, Wang B. Multi-scale weighted gradient-based fusion for multi-focus images[J]. Information Fusion, 2014, 20: 60-72.
20 Liu Y, Chen X, Ward R K, et al. Image fusion with convolutional sparse representation[J]. IEEE Signal Processing Letters, 2016, 23(12): 1882-1886.
21 Liu Y, Chen X, Peng H, et al. Multi-focus image fusion with a deep convolutional neural network[J]. Information Fusion, 2017, 36: 191-207.
[1] Ming-hua GAO,Can YANG. Traffic target detection method based on improved convolution neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(6): 1353-1361.
[2] Huai-jiang YANG,Er-shuai WANG,Yong-xin SUI,Feng YAN,Yue ZHOU. Simplified residual structure and fast deep residual networks [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(6): 1413-1421.
[3] Xue-zhi WANG,Qing-liang LI,Wen-hui LI. Spatio⁃temporal model of soil moisture prediction integrated with transfer learning [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 675-683.
[4] Xiang-jun LI,Jie-ying TU,Zhi-bin ZHAO. Validity classification of melting curve based on multi⁃scale fusion convolutional neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 633-639.
[5] Ji-hong OUYANG,Ze-qi GUO,Si-guang LIU. Dual⁃branch hybrid attention decision net for diabetic retinopathy classification [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 648-656.
[6] Xian-tong LI,Wei QUAN,Hua WANG,Peng-cheng SUN,Peng-jin AN,Yong-xing MAN. Route travel time prediction on deep learning model through spatiotemporal features [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(3): 557-563.
[7] Lin SONG,Li-ping WANG,Jun WU,Li-wen GUAN,Zhi-gui LIU. Reliability analysis based on cyber⁃physical system and digital twin [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(2): 439-449.
[8] Jie CAO,Jia-lin MA,Dai-lin HUANG,Ping YU. A fault diagnosis method based on multi Markov transition field [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(2): 491-496.
[9] Wen-zhi GAO,Yan-jun WANG,Xin-wei WANG,Pan ZHANG,Yong LI,Yang DONG. Real⁃time diagnosis for misfire fault of diesel engine based on convolutional neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(2): 417-424.
[10] Long ZHANG,Tian-peng XU,Chao-bing WANG,Jian-yu YI,Can-zhuang ZHEN. Gearbox fault diagnosis baed on convolutional gated recurrent network [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(2): 368-376.
[11] Liang DUAN,Chun-yuan SONG,Chao LIU,Wei WEI,Cheng-ji LYU. State recognition in bearing temperature of high-speed train based on machine learning algorithms [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(1): 53-62.
[12] You QU,Wen-hui LI. Single-stage rotated object detection network based on anchor transformation [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(1): 162-173.
[13] Gui-xia LIU,Zhi-yao PEI,Jia-zhi SONG. Prediction of protein-ATP binding site based on deep learning [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(1): 187-194.
[14] Jie ZHANG,Wen JING,Fu CHEN. Vulnerability detection of instant messaging network protocol based on passive clustering algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(6): 2253-2258.
[15] Hui ZHONG,Heng KANG,Ying-da LYU,Zhen-jian LI,Hong LI,Ruo-chuan OUYANG. Image manipulation localization algorithm based on channel attention convolutional neural networks [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(5): 1838-1844.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!