Abstract
Multi-focus image fusion is always a difficult problem in digital image processing. To achieve efficient integration, we propose a new end-to-end network. This network uses the residual atrous spatial pyramid pooling module to extract multi-level features from the space of different scales and share parameters to ensure the consistency and correspondence of features. We also introduced a disparities attention module for the network which allows for information retention. These two parts can make our method overcome the difficulties of target edge artifacts, small range blur, poor detail capture, and so on. In addition, in order to improve the semantic ambiguity easily caused by unsupervised learning, we also proposed a new multi-focus image fusion dataset with groundtruth for supervised learning. We performed sufficient experiments, and the results show that the network can quickly capture the corresponding features of multi-focus images, and improve the fusion performance with less computation and lower storage cost. Compared with the existing nine fusion methods, our network is superior to other methods in subjective visual evaluation and objective evaluation, reaching a higher level.
Similar content being viewed by others
References
Li S, Kang X, Fang L, Hu J, Yin H (2017) Pixel-level image fusion:, A survey of the state of the art. Info Fus 33:100–112
Liu Y, Chen X, Peng H, Wang Z (2017) Multi-focus image fusion with a deep convolutional neural network. Info Fus 36:191–207
Yang B, Zhong J, Li Y, Chen Z (2017) Multi-focus image fusion and super-resolution with convolutional neural network. International Journal of Wavelets, Multiresolution and Information Processing 15 (04):136–146
Wang L, Wang Y, Liang Z, Lin Z, Yang J, An W, Guo Y (2019) Learning parallax attention for stereo image super-resolution. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 12250–12259
Nencini F, Garzelli A, Baronti S, Alparone L (2007) Remote sensing image fusion using the curvelet transform. Info Fus 8(2):143–156
Chai Y, Li H, Zhang X (2012) Multifocus image fusion based on features contrast of multiscale products in nonsubsampled contourlet transform domain. Optik 123(7):569–581
Sahu A, Bhateja V, Krishn A (2014) Medical image fusion with Laplacian pyramids. In: 2014 International conference on medical imaging, m-health and emerging communication systems (MedCom), pp 448–453
Joshi K, Kirola M, Chaudhary S, Diwakar M, Joshi NK (2019) Multi-Focus Image fusion using discrete wavelet transform method international conference on advances in engineering science management and technology (ICAESMT)
Li S, Kwok JT, Wang Y (2001) Combination of images with diverse focuses using the spatial frequency. Info Fus 2(3):169–176
Aslantas V, Kurban R (2010) Fusion of multi-focus images using differential evolution algorithm. Expert Syst Appl 37(12):8861–8870
Liu Y, Liu S, Wang Z (2015) Multi-focus image fusion with dense SIFT. Info Fus 23:139–155
Nejati M, Samavi S, Shirani S (2015) Multi-focus image fusion using dictionary-based sparse representation. Info Fus 25:72–84
Li H, Wu XJ, Durrani T (2018) Multi-focus noisy image fusion using low-rank representation. arXiv:1804.09325
Qiu X, Li M, Zhang L, Yuan X (2019) Guided filter-based multi-focus image fusion through focus region detection. Signal Processing: Image Communication 72:35–46
Mao X, Li Q, Xie H, Lau RY, Wang Z, Paul Smolley S (2017) Least squares generative adversarial networks. Proceedings of the IEEE international conference on computer vision, pp 2794–2802
Ma B, Ban X, Huang H, Zhu Y (2019) SESF-fuse: An unsupervised deep model for multi-focus image fusion. arXiv preprint arXiv:1908.01703
Chen Q, Wang Z, Chai Y (2020) A multi focus image fusion method based on improved VGG network. Appl Opt 041(003):500–507
Tang H, Xiao B, Li W, Wang G (2018) Pixel convolutional neural network for multi-focus image fusion. Inf Sci 433:125–141
Guo X, Nie R, Cao J, Zhou D, Qian W (2018) Fully convolutional network-based multifocus image fusion. Neural Comp 30(7):1775–1800
Lai R, Li Y, Guan J, Xiong A (2019) Multi-scale visual attention deep convolutional neural network for multi-focus image fusion. IEEE Access 7:114385–114399
Zhang Y, Liu Y, Sun P, Yan H, Zhao X, Zhang L (2020) IFCNN: A general image fusion framework based on convolutional neural network. Info Fus 54:99–118
Ma H, Liao Q, Zhang J, Liu S, Xie JH (2019) An α-Matte Boundary Defocus Model Based Cascaded Network for Multi-focus Image Fusion. arXiv preprint arXiv:1910.13136
Gregor K, Danihelka I, Graves A, Rezende DJ, Wierstra D (2015) Draw:, A recurrent neural network for image generation. arXiv preprint arXiv:1502.04623
Wang F, Jiang M, Qian C, Yang S, Li C, Zhang H, Wang X, Tang X (2017) Residual attention network for image classification, proceedings of the IEEE conference on computer vision and pattern recognition, pp 3156–3164
Zhang H, Goodfellow I, Metaxas D, Odena A (2019) Self-attention generative adversarial networks, international conference on machine learning, pp 7354–7363
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition, proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Everingham M, Winn J (2011) The pascal visual object classes challenge 2012 (voc2012) development kit. Pattern Analysis, Statistical Modelling and Computational Learning, Tech. Rep, 8
Nejati M, Samavi S, Shirani S (2015) Multi-focus image fusion using dictionary-based sparse representation. Info Fus 25:72–84
Savić S, Babić Z (2012) Multifocus image fusion based on empirical mode decomposition, 19th IEEE International conference on systems signals and image processing (IWSSIP)
Xu H, Fan F, Zhang H, Le Z, Huang J (2020) A deep model for Multi-Focus image fusion based on gradients and connected regions. IEEE Access 8:26316–26327
Ma B, Yin X, Wu D, Ban X, Huang H (2020) Gradient aware cascade network for multi-focus image fusion. arXiv preprint arXiv:2010.08751
Tan W, Zhou H, Rong S, Qian K, Yu Y (2018) Fusion of multi-focus images via a Gaussian curvature filter and synthetic focusing degree criterion. App Opt 57(35):10092–10101
Ma J, Zhou Z, Wang B, Miao L, Zong H (2019) Multi-focus image fusion using boosted random walks-based algorithm with two-scale focus maps. Neurocomputing 335:9–20
Bai X, Zhang Y, Zhou F, Xue B (2015) Quadtree-based multi-focus image fusion using a weighted focus-measure. Info Fus 22:105–118
Liu Z, Blasch E, Xue Z, Zhao J, Laganiere R, Wu W (2011) Objective assessment of multiresolution image fusion algorithms for context enhancement in night vision: a comparative study. IEEE transactions on pattern analysis and machine intelligence 34(1):94–109
Zheng Y, Essock EA, Hansen BC, Haun AM (2007) A new metric based on extended spatial frequency and its application to DWT based fusion algorithms. Info Fus 8(2):177–192
Yang C, Zhang JQ, Wang XR, Liu X (2008) A novel similarity based quality metric for image fusion. Info Fus 9(2):156–160
Acknowledgments
This research was supported by the National Natural Science Foundation of China (61772319, 61773244, 61976125, 61976124), Shandong Natural Science Foundation of China (ZR2017MF049) and Yantai Key Research and Development Plan (2019XDHZ081).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jiang, L., Fan, H. & Li, J. A multi-focus image fusion method based on attention mechanism and supervised learning. Appl Intell 52, 339–357 (2022). https://doi.org/10.1007/s10489-021-02358-7
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02358-7