Abstract
Muti-focus image fusion is the extraction of focused regions from different images to create one all-in-focus fused image. The key point is that only objects within the depth-of-field have a sharp appearance in the photograph, while other objects are likely to be blurred. We propose an unsupervised deep learning model for multi-focus image fusion. We train an encoder–decoder network in an unsupervised manner to acquire deep features of input images. Then, we utilize spatial frequency, a gradient-based method to measure sharp variation from these deep features, to reflect activity levels. We apply some consistency verification methods to adjust the decision map and draw out the fused result. Our method analyzes sharp appearances in deep features instead of original images, which can be seen as another success story of unsupervised learning in image processing. Experimental results demonstrate that the proposed method achieves state-of-the-art fusion performance compared to 16 fusion methods in objective and subjective assessments, especially in gradient-based fusion metrics.
Similar content being viewed by others
Notes
Experimental data and code can be found at https://github.com/Keep-Passion/SESF-Fuse.
References
Aslantas V, Kurban R (2010) Fusion of multi-focus images using differential evolution algorithm. Expert Syst Appl 37(12):8861–8870. https://doi.org/10.1016/j.eswa.2010.06.011
Burt P, Adelson E (1983) The laplacian pyramid as a compact image code. IEEE Trans Commun 31(4):532–540. https://doi.org/10.1109/TCOM.1983.1095851
Chen Y, Blum RS (2009) A new automated quality assessment algorithm for image fusion. Image Vis Comput 27(10):1421–1432. https://doi.org/10.1016/j.imavis.2007.12.002(Special Section: Computer Vision Methods for Ambient Intelligence)
De I, Chanda B, Chattopadhyay B (2006) Enhancing effective depth-of-field by image fusion using mathematical morphology. Image Vision Comput 24(12):1278–1287. https://doi.org/10.1016/j.imavis.2006.04.005
Facebook: Pytorch. https://pytorch.org (2019)
Haghighat M, Aghagolzadeh A, Seyedarabi H (2011) Multi-focus image fusion for visual sensor networks in DCT domain. Comput Electr Eng 37(5):789–797
He K, Sun J, Tang X (2013) Guided image filtering. IEEE Trans Pattern Anal Mach Intell 35(6):1397–1409. https://doi.org/10.1109/TPAMI.2012.213
Huang J, Le Z, Ma Y, Mei X, Fan F (2020) A generative adversarial network with adaptive constraints for multi-focus image fusion. Neural Comput Appl. https://doi.org/10.1007/s00521-020-04863-1.pdf
Huang G, Liu Z, Van Der Maaten L, Weinberger K.Q (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708
Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks. In: The IEEE conference on computer vision and pattern recognition (CVPR)
Itzcovich E, Riani M, Sannita WG (2017) Stochastic resonance improves vision in the severely impaired. Sci Rep 7(1):1–8
Jung H, Kim Y, Jang H, Ha N, Sohn K (2020) Unsupervised deep image fusion with structure tensor representations. IEEE Trans Image Process 29:3845–3858
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: International conference on learning representations
Lewis JJ, O'Callaghan RJ, Nikolov SG, Bull DR, Canagarajah N, (2007) Pixel- and region-based image fusion with complex wavelets. Inf Fusion 8(2):119–130. https://doi.org/10.1016/j.inffus.2005.09.006 Special Issue on Image Fusion: Advances in the State of the Art
Li H, Wu X (2019) Densefuse: A fusion approach to infrared and visible images. IEEE Trans Image Process 28(5):2614–2623. https://doi.org/10.1109/TIP.2018.2887342
Li H, Manjunath B, Mitra S (1995) Multisensor image fusion using the wavelet transform. Graph Models Image Process 57(3):235–245. https://doi.org/10.1006/gmip.1995.1022
Li S, Kwok JT, Wang Y (2001) Combination of images with diverse focuses using the spatial frequency. Inf Fusion 2(3):169–176. https://doi.org/10.1016/S1566-2535(01)00038-0
Li S, Kang X, Hu J (2013) Image fusion with guided filtering. IEEE Trans Image Process 22(7):2864–2875. https://doi.org/10.1109/TIP.2013.2244222
Li S, Kang X, Hu J, Yang B (2013) Image matting for fusion of multi-focus images in dynamic scenes. Inf Fusion 14(2):147–162. https://doi.org/10.1016/j.inffus.2011.07.001
Li S, Kang X, Fang L, Hu J, Yin H (2017) Pixel-level image fusion: a survey of the state of the art. Inf Fusion 33:100–112. https://doi.org/10.1016/j.inffus.2016.05.004
Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollár P, Zitnick CL (2014) Microsoft coco: common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision—ECCV 2014. Springer, Cham, pp 740–755
Liu Y (2019) Image fusion. http://www.escience.cn/people/liuyu1/Codes.html
Liu Z (2012) Image fusion metrics. https://github.com/zhengliu6699/imageFusionMetrics
Liu Z, Blasch E, Xue Z, Zhao J, Laganiere R, Wu W (2012) Objective assessment of multiresolution image fusion algorithms for context enhancement in night vision: a comparative study. IEEE Trans Pattern Anal Mach Intell 34(1):94–109. https://doi.org/10.1109/TPAMI.2011.109
Liu Y, Liu S, Wang Z (2015) Multi-focus image fusion with dense sift. Inf Fusion 23:139–155. https://doi.org/10.1016/j.inffus.2014.05.004
Liu Y, Chen X, Peng H, Wang Z (2017) Multi-focus image fusion with a deep convolutional neural network. Inf Fusion 36:191–207. https://doi.org/10.1016/j.inffus.2016.12.001
Ma H, Liao Q, Zhang J, Liu S, Xue JH (2019) An \(\alpha \) matte boundary defocus model based cascaded network for multi-focus image fusion
Nejati M, Samavi S, Shirani S (2015) Multi-focus image fusion using dictionary-based sparse representation. Inf Fusion 25:72–84. https://doi.org/10.1016/j.inffus.2014.10.004
Nencini F, Garzelli A, Baronti S, Alparone L (2007) Remote sensing image fusion using the curvelet transform. Inf Fusion 8(2):143–156. https://doi.org/10.1016/j.inffus.2006.02.001(Special Issue on Image Fusion: Advances in the State of the Art)
Paul S, Sevcenco IS, Agathoklis P (2016) Multi-exposure and multi-focus image fusion in gradient domain. J Circuits Syst Comput 25:1650123
Peng-wei Wang, Bo Liu (2008) A novel image fusion metric based on multi-scale analysis. In: 2008 9th international conference on signal processing, pp 965–968 . https://doi.org/10.1109/ICOSP.2008.4697288
Prabhakar R (2017) Deepfuse: A deep unsupervised approach for exposure fusion with extreme exposure image pairs. In: The IEEE international conference on computer vision (ICCV)
Riani M, Simonotto E (1994) Stochastic resonance in the perceptual interpretation of ambiguous figures: a neural network model. Phys Rev Lett 72(19):3120
Roy AG, Navab N, Wachinger C (2018) Concurrent spatial and channel squeeze and excitation in fully convolutional networks. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 421–429
Savić S, Babić Z (2012) Multifocus image fusion based on empirical mode decomposition. In: 19th IEEE international conference on systems, signals and image processing (IWSSIP)
Simonotto E, Riani M, Seife C, Roberts M, Twitty J, Moss F (1997) Visual perception of stochastic resonance. Phys Rev Lett 78(6):1186
Spagnolo B, Valenti D, Guarcello C, Carollo A, Adorno DP, Spezia S, Pizzolato N, Di Paola B (2015) Noise-induced effects in nonlinear relaxation of condensed matter systems. Chaos Solitons Fractals 81:412–424
Spagnolo B, Guarcello C, Magazzù L, Carollo A, Persano Adorno D, Valenti D (2017) Nonlinear relaxation phenomena in metastable condensed matter systems. Entropy 19(1):20
Stathaki T (2011) Image fusion: algorithms and applications. Elsevier, Amsterdam
Tang H, Xiao B, Li W, Wang G (2017) Pixel convolutional neural network for multi-focus image fusion. Inf Sci. https://doi.org/10.1016/j.ins.2017.12.043
Toet A (1989) Image fusion by a ratio of low-pass pyramid. Pattern Recogn Lett 9(4):245–253. https://doi.org/10.1016/0167-8655(89)90003-2
Valenti D, Magazzù L, Caldara P, Spagnolo B (2015) Stabilization of quantum metastable states by dissipation. Phys Rev B 91(23):235412
Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612
Wikipedia: Focus stacking. https://github.com/cmcguinness/focusstack (2019)
Xu K (2019) Image fusion. http://xudongkang.weebly.com/index.html
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
Xu S, Wei X, Zhang C, Liu J, Zhang J (2020) Mffw: A new dataset for multi-focus image fusion. arXiv preprint arXiv:2002.04780
Xydeas CS, Petrovic V (2000) Objective image fusion performance measure. Electron Lett 36(4):308–309. https://doi.org/10.1049/el:20000267
Yang B, Li S (2010) Multifocus image fusion and restoration with sparse representation. IEEE Trans Instrum Meas 59(4):884–892. https://doi.org/10.1109/TIM.2009.2026612
Zhang Q, Long Guo B (2009) Multifocus image fusion using the nonsubsampled contourlet transform. Signal Process 89(7):1334–1346. https://doi.org/10.1016/j.sigpro.2009.01.012
Zhang Y, Liu Y, Sun P, Yan H, Zhao X, Zhang L (2020) IFCNN: a general image fusion framework based on convolutional neural network. Inf Fusion 54:99–118
Zhou Z, Li S, Wang B (2014) Multi-scale weighted gradient-based fusion for multi-focus images. Inf Fusion 20:60–72. https://doi.org/10.1016/j.inffus.2013.11.005
Acknowledgements
We acknowledge the support of the National Key Research and Development Program of China (No. 2016YFB0700500), National Science Foundation of China (No. 6170203, No. 61873299), Key Research Plan of Hainan Province (No. ZDYF2019009), Guangdong Province Key Area R and D Program (No. 2019B010940001), Scientific and Technological Innovation Foundation of Shunde Graduate School, USTB (No. BK19BE030), and Fundamental Research Funds for the University of Science and Technology Beijing (No. FRF-BD-19-012A, No. FRF-TP-19-043A2). The computing work was supported by USTB MatCom of Beijing Advanced Innovation Center for Materials Genome Engineering.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflicts of interest
The authors declare that there is no conflict of interest.
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
Ma, B., Zhu, Y., Yin, X. et al. SESF-Fuse: an unsupervised deep model for multi-focus image fusion. Neural Comput & Applic 33, 5793–5804 (2021). https://doi.org/10.1007/s00521-020-05358-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-020-05358-9