Lokesh Gopinath; A. Ruhan Bevi

A Statistical Analysis of Multi-Modal Image Fusion Techniques Using Gaussian Blur Decomposition and Combinative Concatenation

PDF (1070KB), PP.197-212

Views: 0 Downloads: 0

Author(s)

1. Department of Electronics and Communication Engineering, SRM Institute of Science and Technology, Kattankulathur, 603203, Tamil Nadu, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2026.04.11

Received: 3 Jul. 2024 / Revised: 5 Jul. 2025 / Accepted: 21 Jan. 2026 / Published: 8 Aug. 2026

Index Terms

Visible Image, Infrared Image, Image Fusion, Image Decomposition, Deep Learning

Abstract

Image fusion is the method of combining the features of different images into one to get a more informative or high-quality image. Among its various types, multi-modal image fusion is a crucial one where images obtained using sensors receptive to different light radiation are integrated into one final image. Infrared (IR) and Visible (VIS) Image Fusion (IVIF) is one such popular fusion technology. In IVIF, visible sensor produces clean texture and structure information, while it is sensitive to illumination and occlusion. IR sensor, though vulnerable to noise, captures salient targets that emit thermal radiation. The contrasting properties of the two images can be exploited by producing a fused image that both highlights the prominent target as well manifests detailed information. First, the acquired IR and VIS source images are each decomposed using the Gaussian blur filter into base (low-frequency) and detail (high-frequency) components. As opposed to the conventional way of concatenating the respective base and detailed components of the source images, a new technique of combinative concatenation has been performed providing a comprehensive set of 6 unique features to perform fusion. The proposed combinative concatenation is mathematically formulated, illustrating how cross-modal feature generation improves the retention of information and enhances modal complementarity. Weighted Sum (WS), Principal Component Analysis (PCA) and Laplacian Pyramid (LP) have been used for the fusion process. The 6 unique features extracted are fused in 20 different ways considering all combinations to provide fused results with different properties. Finally, a set of 4 statistical analysis methods are applied to identify the best fusion strategy. As a highlight, this paper has assessed these fusion strategies over live images captured using a Near-Infrared (NIR) and VIS camera depicting different illumination conditions (bright, dim and dark), and its effects over the fusion performance are assessed in comparison to fusion of similar images from an existing dataset.

Cite This Paper

Lokesh Gopinath, A. Ruhan Bevi, "A Statistical Analysis of Multi-Modal Image Fusion Techniques Using Gaussian Blur Decomposition and Combinative Concatenation", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.18, No.4, pp. 197-212, 2026. DOI:10.5815/ijigsp.2026.04.11

Reference

[1]Z. Chao, X. Duan, S. Jia, X. Guo, H. Liu, and F. Jia, “Medical image fusion via discrete stationary wavelet transform and an enhanced radial basis function neural network,” Appl Soft Comput, vol. 118, p. 108542, 2022, doi: https://doi.org/10.1016/j.asoc.2022.108542.
[2] V. Saravanan and S. Malarvizhi, “Edge Retention based CT and MRI fusion using decomposition techniques NSST and SWT,” in 2023 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI), 2023, pp.1–5.doi: 10.1109/RAEEUCCI57140.2023.10134348.
[3]X. Li, H. Tan, F. Zhou, G. Wang, and X. Li, “Infrared and visible image fusion based on domain transform filtering and sparse representation,” Infrared Phys Technol, vol. 131, p. 104701, 2023, doi: https://doi.org/10.1016/j.infrared.2023.104701.
[4]C. Xing, Y. Cong, Z. Wang, and M. Wang, “Fusion of Hyperspectral and Multispectral Images by Convolutional Sparse Representation,” IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, 2022, doi: 10.1109/LGRS.2022.3155595.
[5]H. Li, C. Zhang, S. He, Z. Feng, and L. Yi, “A Novel Fusion Method Based on Online Convolutional Sparse Coding with Sample-Dependent Dictionary for Visible–Infrared Images,” Arab J Sci Eng, vol. 48, no. 8, pp. 10605–10615, 2023, doi: 10.1007/s13369-023-07716-w.
[6]S. Zhang, F. Huang, H. Zhong, B. Liu, Y. Chen, and Z. Wang, “Multi-Modal Image Fusion via Sparse Representation and Multi-Scale Anisotropic Guided Measure,” IEEE Access, vol. 8, pp. 35638–35649, 2020, doi: 10.1109/ACCESS.2020.2973269.
[7]L. Gopinath and A. Ruhan Bevi, “A Dimensionality Reduction Method for the Fusion of NIR and Visible Image,” in Fourth International Conference on Image Processing and Capsule Networks, S. Shakya, J. M. R. S. Tavares, A. Fernández-Caballero, and G. Papakostas, Eds., Singapore: Springer Nature Singapore, 2023, pp. 629–645. https://doi.org/10.1007/978-981-99-7093-3_42
[8]L. Gopinath and A. R. Bevi, “Anisotropic Guided Filtering and Multi-level Disintegration Method for NIR and Visible Image Fusion,” in Cognitive Computing and Information Processing, V. N. M. Aradhya, M. Mahmud, S. Srinath, B. S. Mahanand, and R. K. Bharathi, Eds., Cham: Springer Nature Switzerland, 2024, pp. 165–175. https://doi.org/10.1007/978-3-031-60725-7_13
[9]T.-H. Chan, K. Jia, S. Gao, J. Lu, Z. Zeng, and Y. Ma, “PCANet: A Simple Deep Learning Baseline for Image Classification?,” IEEE Transactions on Image Processing, vol. 24, no. 12, pp. 5017–5032, 2015, doi: 10.1109/TIP.2015.2475625.
[10]E. Adelson, C. Anderson, J. Bergen, P. Burt, and J. Ogden, “Pyramid Methods in Image Processing,” RCA Eng., vol. 29, Nov. 1983.
[11]C. N. Ochotorena and Y. Yamashita, “Anisotropic Guided Filtering,” IEEE Transactions on Image Processing, vol. 29, pp. 1397–1412, 2020, doi: 10.1109/TIP.2019.2941326.
[12]K. R. Prabhakar, V. S. Srikar, and R. V Babu, “DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs,” in 2017 IEEE International Conference on Computer Vision (ICCV), 2017, pp. 4724–4732. doi: 10.1109/ICCV.2017.505.
[13]H. Zhang, H. Xu, Y. Xiao, X. Guo, and J. Ma, “Rethinking the Image Fusion: A Fast Unified Image Fusion Network based on Proportional Maintenance of Gradient and Intensity,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, pp. 12797–12804, Apr. 2020, doi: 10.1609/aaai.v34i07.6975.
[14]H. Zhang and J. Ma, “SDNet: A Versatile Squeeze-and-Decomposition Network for Real-Time Image Fusion,” Int J Comput Vis, vol. 129, no. 10, pp. 2761–2785, 2021, doi: 10.1007/s11263-021-01501-8.
[15]H. Xu, J. Ma, J. Jiang, X. Guo, and H. Ling, “U2Fusion: A Unified Unsupervised Image Fusion Network,” IEEE Trans Pattern Anal Mach Intell, vol. 44, no. 1, pp. 502–518, 2022, doi: 10.1109/TPAMI.2020.3012548.
[16]H. Li, X.-J. Wu, and J. Kittler, “Infrared and Visible Image Fusion using a Deep Learning Framework,” in 2018 24th International Conference on Pattern Recognition (ICPR), 2018, pp. 2705–2710. doi: 10.1109/ICPR.2018.8546006.
[17]H. Li, X. Wu, and T. S. Durrani, “Infrared and visible image fusion with ResNet and zero-phase component analysis,” Infrared Phys Technol, vol. 102, p. 103039, 2019, doi: https://doi.org/10.1016/j.infrared.2019.103039.
[18]K. Ren, D. Zhang, M. Wan, X. Miao, G. Gu, and Q. Chen, “An infrared and visible image fusion method based on improved DenseNet and mRMR-ZCA,” Infrared Phys Technol, vol. 115, p. 103707, 2021, doi: https://doi.org/10.1016/j.infrared.2021.103707.
[19]T.-Y. Lin et al., “Microsoft COCO: Common Objects in Context,” in Computer Vision – ECCV 2014, D. Fleet, T. Pajdla, B. Schiele, and T. Tuytelaars, Eds., Cham: Springer International Publishing, 2014, pp. 740–755.
[20]K. A. Reddy, P. S. V. S. P. Teja, G. K. Teja, K. Divya, and J. Aravinth., “Multispectral Image Super Resolution with Auto-Encoder Model and Fusion Technique,” in 2022 7th International Conference on Communication and Electronics Systems (ICCES), 2022, pp. 1485–1490. doi: 10.1109/ICCES54183.2022.9835943.
[21]Z. Zhang, Y. Gao, M. Xiong, X. Luo, and X.-J. Wu, “A joint convolution auto-encoder network for infrared and visible image fusion,” Multimed Tools Appl, vol. 82, no. 19, pp. 29017–29035, 2023, doi: 10.1007/s11042-023-14758-7.
[22]I. J. Goodfellow et al., “Generative adversarial nets,” in Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2, in NIPS’14. Cambridge, MA, USA: MIT Press, 2014, pp. 2672–2680.
[23]J. Ma, W. Yu, P. Liang, C. Li, and J. Jiang, “FusionGAN: A generative adversarial network for infrared and visible image fusion,” Information Fusion, vol. 48, pp. 11–26, 2019, doi: https://doi.org/10.1016/j.inffus.2018.09.004.
[24]H. Xu, P. Liang, W. Yu, J. Jiang, and J. Ma, “Learning a Generative Model for Fusing Infrared and Visible Images via Conditional Generative Adversarial Network with Dual Discriminators,” in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, International Joint Conferences on Artificial Intelligence Organization, Jun. 2019, pp. 3954–3960. doi: 10.24963/ijcai.2019/549.
[25]J. Ma, H. Zhang, Z. Shao, P. Liang, and H. Xu, “GANMcC: A Generative Adversarial Network with Multiclassification Constraints for Infrared and Visible Image Fusion,” IEEE Trans Instrum Meas, vol. 70, pp. 1–14, 2021, doi: 10.1109/TIM.2020.3038013.
[26] Gopinath, L., & Bevi, A. R. (2025a). A Hybrid Network with Multicategory Adversarial Feature Learning: McAFL Fusion. International Journal of Uncertainty Fuzziness and Knowledge-Based Systems, 33(05), 549–558. https://doi.org/10.1142/s0218488525400033.

International Journal of Image, Graphics and Signal Processing (IJIGSP)