A Survey of Multi-Focus Image Fusion Methods
Source abstract
Abstract
As an important branch in the field of image fusion, the multi-focus image fusion technique can effectively solve the problem of optical lens depth of field, making two or more partially focused images fuse into a fully focused image. In this paper, the methods based on boundary segmentation was put forward as a group of image fusion method. Thus, a novel classification method of image fusion algorithms is proposed: transform domain methods, boundary segmentation methods, deep learning methods, and combination fusion methods. In addition, the subjective and objective evaluation standards are listed, and eight common objective evaluation indicators are described in detail. On the basis of lots of literature, this paper compares and summarizes various representative methods. At the end of this paper, some main limitations in current research are discussed, and the future development of multi-focus image fusion is prospected.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Image Fusion Techniques · Remote-Sensing Image Classification · Remote Sensing and Land Use
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Textile Science and Engineering, Xi’an Polytechnic University, Xi’an 710048, China
School of Textile, Apparel & Art Design, Shaoxing University Yuanpei College, Shaoxing 312000, China
China-Australia Institute for Advanced Materials and Manufacturing, Jiaxing University, Jiaxing 314001, China
Funding
National Natural Science Foundation of China · Outstanding Young Talents Support Plan of Shaanxi Universities · Natural Science Basic Research Program of Shaanxi · Scientific Research Program Funded by Shaanxi Provincial Education Department · Innovation Capability Support Program of Shaanxi · Science and Technology Guiding Project of China National Textile and Apparel Council · Open Project Program of Key Laboratory of Eco-textiles, Ministry of Education, Jiangnan University · Graduate Scientific Innovation Fund for Xi’an Polytechnic University · Work and Research Project of University Laboratory of Zhejiang Province
References (66)
Show source-provided references
1. Medical image fusion: A survey of the state of the art10.1016/j.inffus.2013.12.002 ↗
2. Infrared and visible image fusion methods and applications: A survey10.1016/j.inffus.2018.02.004 ↗
3. Li, Q., Yang, X., Wu, W., Liu, K., and Jeon, G. (2018). Multi-focus image fusion method for vision sensor systems via dictionary learning with guided filter. Sensors, 18.10.3390/s18072143 ↗
4. A survey on region based image fusion methods10.1016/j.inffus.2018.07.010 ↗
5. A Hybrid method for multi-focus image fusion based on fast discrete curvelet transform10.1109/ACCESS.2017.2698217 ↗
6. Xiao, G., Bavirisetti, D.P., Liu, G., and Zhang, X. (2020). Decision-Level Image Fusion. Image Fusion, Springer.10.1007/978-981-15-4867-3 ↗
7. An improved fusion algorithm for infrared and visible images based on multi-scale transform10.1016/j.infrared.2015.11.002 ↗
8. Pixel-level image fusion: A survey of the state of the art10.1016/j.inffus.2016.05.004 ↗
9. The Laplacian pyramid as a compact image code
10. Gradient-based multiresolution image fusion10.1109/TIP.2004.823821 ↗
11. Merging thermal and visual images by a contrast pyramid10.1117/12.7977034 ↗
12. Multi-focus image fusion algorithm based on Laplacian pyramids10.1364/JOSAA.35.000480 ↗
13. Hybrid dual-tree complex wavelet transform and support vector machine for digital multi-focus image fusion10.1016/j.neucom.2015.10.084 ↗
14. Directive contrast based multimodal medical image fusion in NSCT domain
15. Structure tensor and nonsubsampled shearlet transform based algorithm for CT and MRI image fusion10.1016/j.neucom.2017.01.006 ↗
16. Multisource geospatial data fusion via local joint sparse representation10.1109/TGRS.2016.2514481 ↗
17. Pixel-based and region-based image fusion schemes using ICA bases10.1016/j.inffus.2005.09.001 ↗
18. Multi-focus image fusion for visual sensor networks in DCT domain10.1016/j.compeleceng.2011.04.016 ↗
19. Adaptive region-segmentation multi-focus image fusion based on differential evolution10.1142/S0218001419540107 ↗
20. Multi-focus image fusion using a morphology-based focus measure in a quad-tree structure10.1016/j.inffus.2012.01.007 ↗
21. Multi-focus image fusion using content adaptive blurring10.1016/j.inffus.2018.01.009 ↗
22. Multifocus image fusion based on robust principal component analysis10.1016/j.patrec.2013.03.003 ↗
23. Poisson image fusion based on Markov random field fusion model10.1016/j.inffus.2012.07.003 ↗
24. Multi-focus image fusion based on optimal defocus estimation10.1016/j.compeleceng.2017.02.003 ↗
25. Multi-focus image fusion with a deep convolutional neural network10.1016/j.inffus.2016.12.001 ↗
26. Ensemble of CNN for multi-focus image fusion10.1016/j.inffus.2019.02.003 ↗
27. Novel multi-focus image fusion based on PCNN and random walks10.1007/s00521-016-2633-9 ↗
28. Multi-focus Image Fusion Based on the Improved PCNN and Guided Filter10.1007/s11063-016-9513-2 ↗
29. FuseGAN: Learning to fuse multi-focus image via conditional generativeadversarial network10.1109/TMM.2019.2895292 ↗
30. A novel multi-modality image fusion method based on image decomposition and sparse representation10.1016/j.ins.2017.09.010 ↗
31. Multi-focus image fusion via clustering PCA based joint dictionary learning10.1109/ACCESS.2017.2741500 ↗
32. A novel approach for multi-focus image fusion based on SF-PAPCNN and ISML in NSST domain10.1007/s11042-020-09154-4 ↗
33. Wei, B., Feng, X., Wang, K., and Gao, B. (2021). The multi-focus-image-fusion method based on convolutional neural network and sparse representation. Entropy, 23.10.3390/e23070827 ↗
34. Multi-focus image fusion: A Survey of the state of the art10.1016/j.inffus.2020.06.013 ↗
35. Multi-resolution MRI brain image segmentation based on Morphological pyramid and fuzzy C-mean clustering10.1007/s13369-015-1791-x ↗
36. An edge preserving multiresolution fusion: Use of contourlet transform and MRF prior10.1109/TGRS.2014.2371812 ↗
37. Sparse directional image representations using the discrete shearlet transform10.1016/j.acha.2007.09.003 ↗
38. Du, G., Dong, M., Sun, Y., Li, S., Mu, X., Wei, H., Lei, M., and Liu, B. (2019). A new method for detecting architectural distortion in mammograms by NonSubsampled contourlet transform and improved PCNN. Appl. Sci., 9.10.3390/app9224916 ↗
39. Multifocus Image Fusion and Restoration With Sparse Representation10.1109/TIM.2009.2026612 ↗
40. Multi-focus image fusion based on joint sparse representation and optimum theory10.1016/j.image.2019.06.002 ↗
41. Group-sparse representation with dictionary learning for medical image denoising and fusion10.1109/TBME.2012.2217493 ↗
42. A novel sparse-representation-based multi-focus image fusion approach10.1016/j.neucom.2016.07.039 ↗
43. Multi-exposure and multi-focus image fusion in gradient domain10.1142/S0218126616501231 ↗
44. Fusion of 3-D medical image gradient domain based on detail-driven and directional structure tensor
45. Multi-focus image fusion using HOSVD and edge intensity10.1016/j.jvcir.2017.02.006 ↗
46. Fusion framework for multi-focus images based on compressed sensing10.1049/iet-ipr.2012.0543 ↗
47. A novel multi-focus image fusion approach based on image decomposition10.1016/j.inffus.2016.09.007 ↗
48. A region-based multi-sensor image fusion scheme using pulse-coupled neural network10.1016/j.patrec.2006.05.004 ↗
49. Multi-focus image fusion based on depth extraction with inhomogeneous diffusion equation10.1016/j.sigpro.2016.01.014 ↗
50. Image segmentation-based multi-focus image fusion through multi-scale convolutional neural network10.1109/ACCESS.2017.2735019 ↗
51. Multi-focus image fusion using boosted random walks-based algorithm with two-scale focus maps10.1016/j.neucom.2019.01.048 ↗
52. Improved faster R-CNN for fabric defect detection based on Gabor filter with Genetic Algorithm optimization10.1016/j.compind.2021.103551 ↗
53. Kowsher, M., Alam, M.A., Uddin, M.J., Ahmed, F., Ullah, M.W., and Islam, M.R. (2019, January 11–12). Detecting third umpire decisions & automated scoring system of cricket. Proceedings of the 2019 International Conference on Computer, Communication, Chemical, Materials and Electronic Engineering (IC4ME2), Rajshahi, Bangladesh.10.1109/IC4ME247184.2019.9036705 ↗
54. Javed Awan, M., Mohd Rahim, M.S., Salim, N., Mohammed, M.A., Garcia-Zapirain, B., and Abdulkareem, K.H. (2021). Efficient detection of knee anterior cruciate ligament from magnetic resonance imaging using deep learning approach. Diagnostics, 11.10.3390/diagnostics11010105 ↗
55. Zhang, X., Yang, Y., Li, Z., Ning, X., Qin, Y., and Cai, W. (2021). An improved encoder-decoder network based on strip pool method applied to segmentation of farmland vacancy field. Entropy, 23.10.3390/e23040435 ↗
56. Detection of non-stationary GW signals in high noise from cohen’s class of time-frequency representations using deep learning10.1109/ACCESS.2021.3139850 ↗
57. Pixel convolutional neural network for multi-focus image fusion10.1016/j.ins.2017.12.043 ↗
58. Wang, K., Zheng, M., Wei, H., Qi, G., and Li, Y. (2020). Multi-modality medical image fusion using convolutional neural network and contrast pyramid. Sensors, 20.10.3390/s20082169 ↗
59. IFCNN: A general image fusion framework based on convolutional neural network10.1016/j.inffus.2019.07.011 ↗
60. Robust sparse representation combined with adaptive PCNN for multifocus image fusion10.1109/ACCESS.2018.2822688 ↗
61. Basar, S., Waheed, A., Ali, M., Zahid, S., Zareei, M., and Biswal, R.R. (2022). An efficient defocus blur segmentation scheme based on Hybrid LTP and PCNN. Sensors, 22.10.3390/s22072724 ↗
62. Objective assessment of multiresolution image fusion algorithms for context enhancement in night vision: A comparative study10.1109/TPAMI.2011.109 ↗
63. Reciprocal focus profile10.1109/TIP.2011.2164417 ↗
64. Ferris, M.H., Blasen, E., and McLaughlin, M. (2014, January 14–16). Extension of no-reference deblurring methods through image fusion. Proceedings of the 2014 IEEE Applied Imagery Pattern Recognition Workshop (AIPR 2014), Washington, DC, USA.10.1109/AIPR.2014.7041905 ↗
65. Shape-from-focus by tensor voting10.1109/TIP.2012.2190612 ↗
66. Signal-level information fusion for less constrained iris recognition using sparse-error low rank matrix factorization10.1109/TIFS.2016.2541612 ↗