Ship imaging has an impact on the visual judgment of the steersman and influences ship navigation safety. Traditional image enhancement methods struggle under adverse conditions and fail to account for the physiological mechanisms of human visual perception. Therefore, a novel method was proposed to enhance ship imaging by combining a visual neural signal encoding mechanism (accomplished by multi-scale spiking neural networks) with a multi-scale frequency-domain stochastic resonance model. First, the noisy image is encoded by mapping the neuron pulse count per unit time, and then the encoded signal is directionally filtered by constructing a spatial dot-matrix dual-view perception receptive field model to achieve preliminary low-level noise reduction. Second, a stochastic resonance system is constructed and applied in series to enhance the decomposed multi-scale wavelet coefficients. Finally, considering the brightness characteristics of the visual system, the processed wavelet coefficients of each scale are inversely transformed and reconstructed. The reconstructed image is then fused with the image obtained by directional filtering of the spatial dot-matrix dual-view pathway receptive field model to produce the final enhanced image. According to the experimental results, compared with the original noisy image, the peak signal-to-noise ratio (PSNR) and visual information fidelity (VIF) improve by 27% and 30%, respectively. These findings indicate that the proposed method can effectively enhance ship images in a manner more consistent with the physiological characteristics of human visual imaging and signal processing.
Citation: Di Wang, Yang Wang, Zonglian Wang, Jianhong Huang, Xiaowen Xu. A novel ship image enhancement method based on fusion of parallel-series stochastic resonance model and multi-scale spiking neural networks[J]. Electronic Research Archive, 2025, 33(9): 5638-5660. doi: 10.3934/era.2025251
Ship imaging has an impact on the visual judgment of the steersman and influences ship navigation safety. Traditional image enhancement methods struggle under adverse conditions and fail to account for the physiological mechanisms of human visual perception. Therefore, a novel method was proposed to enhance ship imaging by combining a visual neural signal encoding mechanism (accomplished by multi-scale spiking neural networks) with a multi-scale frequency-domain stochastic resonance model. First, the noisy image is encoded by mapping the neuron pulse count per unit time, and then the encoded signal is directionally filtered by constructing a spatial dot-matrix dual-view perception receptive field model to achieve preliminary low-level noise reduction. Second, a stochastic resonance system is constructed and applied in series to enhance the decomposed multi-scale wavelet coefficients. Finally, considering the brightness characteristics of the visual system, the processed wavelet coefficients of each scale are inversely transformed and reconstructed. The reconstructed image is then fused with the image obtained by directional filtering of the spatial dot-matrix dual-view pathway receptive field model to produce the final enhanced image. According to the experimental results, compared with the original noisy image, the peak signal-to-noise ratio (PSNR) and visual information fidelity (VIF) improve by 27% and 30%, respectively. These findings indicate that the proposed method can effectively enhance ship images in a manner more consistent with the physiological characteristics of human visual imaging and signal processing.
| [1] |
H. Li, X. L. Duan, SAR ship image speckle noise suppression algorithm based on adaptive bilateral filter, Wireless Commun. Mobile Comput., 2022 (2022), 9392648. https://doi.org/10.1155/2022/9392648 doi: 10.1155/2022/9392648
|
| [2] |
X. Bai, F. Zhou, B. Xue, Infrared image enhancement through contrast enhancement by using multiscale new top-hat transform, Infrared Phys. Technol., 54 (2011), 61–69. https://doi.org/10.1016/j.infrared.2010.12.001 doi: 10.1016/j.infrared.2010.12.001
|
| [3] |
J. C. M. Román, R. Escobar, F. Martínez, J. L. V. Noguera, H. Legal-Ayala, D. P. Pinto-Roa, Medical image enhancement with brightness and detail preserving using multiscale top-hat transform by reconstruction, Electron. Notes Theor. Comput. Sci., 349 (2020), 69–80. https://doi.org/10.1016/j.entcs.2020.02.013 doi: 10.1016/j.entcs.2020.02.013
|
| [4] |
J. Pei, Z. Yu, J. Wu, Y. Zhao, X. Yang, Maritime infrared image enhancement based on morphological pseudo transmittance modulation and radiation source enhancement, Infrared Phys. Technol., 142 (2024), 105564. https://doi.org/10.1016/j.infrared.2024.105564 doi: 10.1016/j.infrared.2024.105564
|
| [5] |
L. Gammaitoni, P. Hänggi, P. Jung, F. Marchesoni, Stochastic resonance, Rev. Mod. Phys., 70 (1998), 224–287. https://doi.org/10.1103/RevModPhys.70.223 doi: 10.1103/RevModPhys.70.223
|
| [6] |
Z. Shi, Z. Liao, H. Tabata, Enhancing performance of convolutional neural network-based epileptic electroencephalogram diagnosis by asymmetric stochastic resonance, IEEE J. Biomed. Health. Inf., 27 (2023), 4228–4239. https://doi.org/10.1109/JBHI.2023.3282251 doi: 10.1109/JBHI.2023.3282251
|
| [7] |
D. V. Dylov, J. W. Fleischer, Nonlinear self-filtering of noisy images via dynamical stochastic resonance, Nat. Photonics, 4 (2010), 323–328. https://doi.org/10.1038/nphoton.2010.31 doi: 10.1038/nphoton.2010.31
|
| [8] |
Z. Liao, Z. Shi, H. Tabata, One-dimensional lattice potential-based stochastic resonance for robust QRS detection in noisy electrocardiogram, IEEE Sens. J., 24 (2024), 35323–35332. https://doi.org/10.1109/JSEN.2024.3462799 doi: 10.1109/JSEN.2024.3462799
|
| [9] |
Z. Liao, K. Ma, S. Sarker, H. Yamahara, M. Seki, H. Tabata, Overdamped Ising machine with stochastic resonance phenomena in large noise condition, Nonlinear Dyn., 112 (2024), 8967–8984. https://doi.org/10.1007/s11071-024-09486-y doi: 10.1007/s11071-024-09486-y
|
| [10] |
Z. Liao, Z. Wang, H. Yamahara, H. Tabata, Echo state network activation function based on bistable stochastic resonance, Chaos, Solitons Fractals, 153 (2021), 111503. https://doi.org/10.1016/j.chaos.2021.111503 doi: 10.1016/j.chaos.2021.111503
|
| [11] | L. Li, R. Wang, W. Wang, W. Gao, A low-light image enhancement method for both denoising and contrast enlarging, in 2015 IEEE International Conference on Image Processing (ICIP), (2015), 3730–3734. https://doi.org/10.1109/ICIP.2015.7351501 |
| [12] |
H. Ackar, A. Abd Almisreb, M. A. Saleh, A review on image enhancement techniques, Southeast Eur. J. Soft Comput., 8 (2019), 42–48. http://doi.org/10.21533/scjournal.v8i1.175 doi: 10.21533/scjournal.v8i1.175
|
| [13] |
W. Wang, X. Wu, X. Yuan, Z. Gao, An experiment-based review of low-light image enhancement methods, IEEE Access, 8 (2020), 87884–87917. http://doi.org/10.1109/ACCESS.2020.2992749 doi: 10.1109/ACCESS.2020.2992749
|
| [14] | D. A. Tarzanagh, Y. Li, X. Zhang, S. Oymak, Max-margin token selection in attention mechanism, in Proceedings of the 37th International Conference on Neural Information Processing Systems, 36 (2023), 48314–48362. |
| [15] | Q. X. Wu, M. McGinnity, L. Maguire, A. Belatreche, B. Glackin, Edge detection based on spiking neural network model, in Advanced Intelligent Computing Theories and Applications. With Aspects of Artificial Intelligence, (2007), 26–34. https://doi.org/10.1007/978-3-540-74205-0_4 |
| [16] | K. Ghosh, S. Sarkar, K.Bhaumik, Image enhancement by high-order Gaussian derivative filters simulating non-classical receptive fields in the human visual system, in Pattern Recognition and Machine Intelligence, (2005), 453–458. https://doi.org/10.1007/11590316_70 |
| [17] | X. Du, Y. Cheng, Z. Gu, Non-classical receptive field models with inhibitory subunits for high-speed railway image enhancement, in Proceedings of the 4th International Conference on Computer Science and Application Engineering, (2020), 1–5. https://doi.org/10.1145/3424978.3425113 |
| [18] |
K. F. Yang, C. Y. Li, Y. J. Li, Multifeature-based surround inhibition improves contour detection in natural images, IEEE Trans. Image Process., 23 (2014), 5020–5032. https://doi.org/10.1109/TIP.2014.2361210 doi: 10.1109/TIP.2014.2361210
|
| [19] |
J. K. Han, M. S. Kim, S. I. Kim, M. W. Lee, S. W. Lee, J. M. Yu, Investigation of leaky characteristic in a single-transistor-based leaky integrate-and-fire neuron, IEEE Trans. Electron Devices, 68 (2021), 5912–5915. https://doi.org/10.1109/TED.2021.3110830 doi: 10.1109/TED.2021.3110830
|
| [20] |
Y. Chen, B. Paromita, On the incorporation of time-delay regularization into curvature-based diffusion, J. Math. Imaging Vision, 14 (2001), 149–164. https://doi.org/10.1023/A:1011211315825 doi: 10.1023/A:1011211315825
|
| [21] | J. J. DiCarlo, D. Zoccolan, N. C. Rust, How does the brain solve visual object recognition? Neuron, 73 (2012), 415–434. https://doi.org/10.1016/j.neuron.2012.01.010 |
| [22] | J. E. LeDoux, The emotional brain: The mysterious underpinnings of emotional life, Simon & Schuster, 1996. |
| [23] | J. V. Stone, Vision and brain: How we perceive the world, MIT press, 2012. https://doi.org/10.1002/col.21807 |
| [24] |
H. Wassle, B. B. Boycott, Functional architecture of the mammalian retina, Physiol. Rev., 71 (1991), 447–480. https://doi.org/10.1152/physrev.1991.71.2.447 doi: 10.1152/physrev.1991.71.2.447
|
| [25] |
S. C. Lo, H. Li, M. T. Freedman, Optimization of wavelet decomposition for image compression and feature preservation, IEEE Trans. Med. Imaging, 22 (2003), 1141–1151. https://doi.org/10.1109/TMI.2003.816953 doi: 10.1109/TMI.2003.816953
|
| [26] |
A. Longtin, Stochastic resonance in neuron models, J. Stat. Phys., 70 (1993), 309–327. https://doi.org/10.1007/BF01053970 doi: 10.1007/BF01053970
|
| [27] |
Y. F. Guo, B. Xi, F. Wei, J. G. Tan, Stochastic resonance in FitzHugh-Nagumo neural system driven by correlated non-Gaussian noise and Gaussian noise, Int. J. Mod. Phys. B, 31 (2017), 1750264. https://doi.org/10.1142/S0217979217502642 doi: 10.1142/S0217979217502642
|
| [28] |
W. Fang, J. Sun, Y. Ding, X. Wu, W. Xu, A review of quantum-behaved particle swarm optimization, IETE Tech. Rev., 27 (2010), 336–348. https://doi.org/10.4103/0256-4602.64601 doi: 10.4103/0256-4602.64601
|
| [29] |
Y. Fu, Y. Kang, G. Chen, Stochastic resonance based visual perception using spiking neural networks, Front. Comput. Neurosci., 14 (2020), 24. https://doi.org/10.3389/fncom.2020.00024 doi: 10.3389/fncom.2020.00024
|
| [30] |
Z. Xu, Y. Zhai, Y. Kang, Mutual information measure of visual perception based on noisy spiking neural networks, Front. Neurosci., 17 (2023), 1155362. https://doi.org/10.3389/fnins.2023.1155362 doi: 10.3389/fnins.2023.1155362
|
| [31] | T. A. Soomro, M. Rathi, S. A. Soomro, M. U. Keerio, P. Kumar, E. N. Baro, Image enhancement technique for MRI brain images, in 2024 Global Conference on Wireless and Optical Technologies (GCWOT), (2024), 1–5. https://doi.org/10.1109/GCWOT63882.2024.10805684 |
| [32] |
X. Liu, T. D. Nguyen, Medical images enhancement by integrating CLAHE with wavelet transform and non-local means denoising, Acad. J. Comput. Inf. Sci., 7 (2024), 52–58. https://doi.org/10.25236/AJCIS.2024.070108 doi: 10.25236/AJCIS.2024.070108
|
| [33] | Y. Zhang, T. Zhang, C. Liu, L. Zhang, Low light image enhancement algorithm based on improved retinex, in 2024 9th International Conference on Computer and Communication Systems (ICCCS), (2024), 184–189. https://doi.org/10.1109/ICCCS61882.2024.10602798 |
| [34] |
A. Tanchenko, Visual-PSNR measure of image quality, J. Visual Commun. Image Represent., 25 (2014), 874–878. https://doi.org/10.1016/j.jvcir.2014.01.008 doi: 10.1016/j.jvcir.2014.01.008
|
| [35] |
H. R. Sheikh, A. C. Bovik, Image information and visual quality, IEEE Trans. Image Process., 15 (2006), 430–444. https://doi.org/10.1109/tip.2005.859378 doi: 10.1109/tip.2005.859378
|
Figures(13) / Tables(2)
Di Wang, Yang Wang, Zonglian Wang, Jianhong Huang, Xiaowen Xu. A novel ship image enhancement method based on fusion of parallel-series stochastic resonance model and multi-scale spiking neural networks[J]. Electronic Research Archive, 2025, 33(9): 5638-5660. doi: 10.3934/era.2025251
DownLoad: