DS-TSNet: Depth-Aware Spectral Compensation and Turbidity-Weighted Structural Stabilization with Hybrid DenseNet and Binary WGOA for Robust Underwater Image Classification
DOI:
https://doi.org/10.62411/jcta.18056Keywords:
Binary Weighted Grasshopper Optimization Algorithm, DenseNet201, Depth-Aware Spectral Attenuation Compensation, Feature selection, hybrid deep learning, Turbidity-Weighted Structural Stabilization, Underwater Image Classification, Underwater Image EnhancementAbstract
Underwater image classification remains challenging because wavelength-dependent radiance attenuation and turbidity-induced boundary distortion degrade visual features and compromise classification reliability. To address these challenges, this study proposes the Depth-Aware Spectral-Structural Learning Network (DS-TSNet), an end-to-end framework that integrates Depth-Aware Spectral Attenuation Compensation (DSACM), Turbidity-Weighted Structural Stabilization (TWSSL), hybrid feature learning using DenseNet201 and DenseNet121, feature selection through the Binary Weighted Grasshopper Optimization Algorithm (B-WGOA), and label-smoothed, class-weighted multilayer perceptron (MLP) classification. Specifically, DSACM compensates for spectral attenuation effects, whereas TWSSL enhances structural information by mitigating turbidity-induced boundary distortions. The hybrid DenseNet architecture extracts complementary features, which are subsequently refined through B-WGOA-based feature selection. This binary optimization process identifies informative feature subsets by minimizing a hybrid objective that incorporates four criteria: classification quality, stability, sparsity, and redundancy suppression. Finally, label smoothing and adaptive class weighting are incorporated into the MLP classifier to mitigate overfitting and improve probability calibration. Experimental results demonstrate that DS-TSNet achieves an accuracy of 94.71% on the Underwater Images benchmark, with a macro-F1 score of 0.9471, a balanced accuracy of 0.9471, and a Cohen’s kappa coefficient of 0.9295. In a separate evaluation on the Marine_PULSE SONAR dataset, the framework achieves an accuracy of 97.89% and a Cohen’s kappa coefficient of 0.9679. Furthermore, comparative evaluations against EfficientNet-B3, ResNet-50, ResNet-101, and optimization-based methods reported in the literature provide additional evidence of the framework’s classification performance. Overall, these findings highlight the potential of integrating spectral compensation, structural stabilization, and optimization-guided feature selection for underwater image classification.References
E. Prasetyo, N. Suciati, and C. Fatichah, “Multi-level residual network VGGNet for fish species classification,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 8, pp. 5286–5295, Sep. 2022, doi: 10.1016/j.jksuci.2021.05.015.
Mehrunnisa, M. Leszczuk, D. Juszka, and Y. Zhang, “Improved Binary Classification of Underwater Images Using a Modified ResNet-18 Model,” Electronics, vol. 14, no. 15, p. 2954, Jul. 2025, doi: 10.3390/electronics14152954.
S. Liawatimena, E. Abdurachman, A. Trisetyarso, A. Wibowo, M. K. Ario, and I. S. Edbert, “Fish Classification System Using YOLOv3-ResNet18 Model for Mobile Phones,” CommIT (Communication Inf. Technol. J., vol. 17, no. 1, pp. 71–79, Mar. 2023, doi: 10.21512/commit.v17i1.8107.
P. Pachaiyappan, G. Chidambaram, A. Jahid, and M. H. Alsharif, “Enhancing Underwater Object Detection and Classification Using Advanced Imaging Techniques: A Novel Approach with Diffusion Models,” Sustainability, vol. 16, no. 17, p. 7488, Aug. 2024, doi: 10.3390/su16177488.
H. Xin and L. Li, “Arbitrary Style Transfer With Fused Convolutional Block Attention Modules,” IEEE Access, vol. 11, pp. 44977–44988, 2023, doi: 10.1109/ACCESS.2023.3273949.
H. Zhang, R. He, and W. Fang, “An Underwater Image Enhancement Method Based on Diffusion Model Using Dual-Layer At-tention Mechanism,” Water, vol. 16, no. 13, p. 1813, Jun. 2024, doi: 10.3390/w16131813.
R. Liu, Z. Jiang, S. Yang, and X. Fan, “Twin Adversarial Contrastive Learning for Underwater Image Enhancement and Beyond,” IEEE Trans. Image Process., vol. 31, pp. 4922–4936, 2022, doi: 10.1109/TIP.2022.3190209.
L. Peng, C. Zhu, and L. Bian, “U-Shape Transformer for Underwater Image Enhancement,” IEEE Trans. Image Process., vol. 32, pp. 3066–3079, 2023, doi: 10.1109/TIP.2023.3276332.
X. Wang, G. Xue, S. Huang, and Y. Liu, “Underwater Object Detection Algorithm Based on Adding Channel and Spatial Fusion Attention Mechanism,” J. Mar. Sci. Eng., vol. 11, no. 6, p. 1116, May 2023, doi: 10.3390/jmse11061116.
S. Xie, R. Girshick, P. Dollar, Z. Tu, and K. He, “Aggregated Residual Transformations for Deep Neural Networks,” in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul. 2017, pp. 5987–5995. doi: 10.1109/CVPR.2017.634.
V. Lopez-Vazquez, J. M. Lopez-Guede, D. Chatzievangelou, and J. Aguzzi, “Deep learning based deep-sea automatic image en-hancement and animal species classification,” J. Big Data, vol. 10, no. 1, p. 37, Mar. 2023, doi: 10.1186/s40537-023-00711-w.
S. D et al., “Enhanced deep learning models for automatic fish species identification in underwater imagery,” Heliyon, vol. 10, no. 15, p. e35217, Aug. 2024, doi: 10.1016/j.heliyon.2024.e35217.
S. Kay, K. Adhikari, and B. Tang, “A Nonparametric Data-Driven Classifier Based on the Cumulant Generating Function,” IEEE Trans. Signal Process., vol. 73, pp. 519–533, 2025, doi: 10.1109/TSP.2025.3525951.
Y. Hwang, G. Kim, S. Shin, W. Hong, and Y. Choo, “Attention-Based Complementary Learning for Active Target Classification With Limited Sonar Data,” IEEE Access, vol. 12, pp. 79787–79801, 2024, doi: 10.1109/ACCESS.2024.3409829.
B. Muñoz and G. Troni, “Learning the Ego-Motion of an Underwater Imaging Sonar: A Comparative Experimental Evaluation of Novel CNN and RCNN Approaches,” IEEE Robot. Autom. Lett., vol. 9, no. 3, pp. 2072–2079, Mar. 2024, doi: 10.1109/LRA.2024.3352357.
Z. Feng, P. Zhang, and X. Huo, “Underwater Target Classification Based on Feature Fusion and Gene Encoding of CNN-BIGRU-Attention,” IEEE Access, vol. 11, pp. 139546–139556, 2023, doi: 10.1109/ACCESS.2023.3341499.
J. Liu, S. Liu, S. Xu, and C. Zhou, “Two-Stage Underwater Object Detection Network Using Swin Transformer,” IEEE Access, vol. 10, pp. 117235–117247, 2022, doi: 10.1109/ACCESS.2022.3219592.
S. C. Pravin, G. Rohith, V. Kiruthika, E. Manikandan, S. Methelesh, and A. Manoj, “Underwater Animal Identification and Classi-fication Using a Hybrid Classical-Quantum Algorithm,” IEEE Access, vol. 11, pp. 141902–141914, 2023, doi: 10.1109/ACCESS.2023.3343120.
J. de C. V. Fernandes, N. N. de Moura Junior, and J. M. de Seixas, “Deep Learning Models for Passive Sonar Signal Classification of Military Data,” Remote Sens., vol. 14, no. 11, p. 2648, Jun. 2022, doi: 10.3390/rs14112648.
G. Huo, Z. Wu, and J. Li, “Underwater Object Classification in Sidescan Sonar Images Using Deep Transfer Learning and Sem-isynthetic Training Data,” IEEE Access, vol. 8, pp. 47407–47418, 2020, doi: 10.1109/ACCESS.2020.2978880.
Y. Hwang, G. Kim, W. Hong, and Y. Choo, “Effective Data Augmentation for Active Sonar Classification Using Attention-Based Complementary Learning With Uncertainty Measure,” IEEE Access, vol. 13, pp. 55670–55681, 2025, doi: 10.1109/ACCESS.2025.3555420.
C. Barat and R. Phlypo, “A Fully Automated Method to Detect and Segment a Manufactured Object in an Underwater Color Im-age,” EURASIP J. Adv. Signal Process., vol. 2010, no. 1, p. 568092, Dec. 2010, doi: 10.1155/2010/568092.
M. A. Abdel-Moneim, E.-S. M. El-Rabaie, F. E. A. El-Samie, K. Ramadan, K. F. Ramadan, and N. Abdel-Salam, “CNN-based modulation classification using image processing techniques for OFDM underwater acoustic communication system,” J. Electr. Syst. Inf. Technol., vol. 12, no. 1, p. 70, Sep. 2025, doi: 10.1186/s43067-025-00263-4.
Y. Steiniger, D. Kraus, and T. Meisen, “Survey on deep learning based computer vision for sonar imagery,” Eng. Appl. Artif. Intell., vol. 114, p. 105157, Sep. 2022, doi: 10.1016/j.engappai.2022.105157.
P. Prasenan and C. D. Suriyakala, “Fish species classification using a collaborative technique of firefly algorithm and neural network,” EURASIP J. Adv. Signal Process., vol. 2022, no. 1, p. 116, Dec. 2022, doi: 10.1186/s13634-022-00950-8.
X. Qin, X. Luo, Z. Wu, and J. Shang, “Optimizing the Sediment Classification of Small Side-Scan Sonar Images Based on Deep Learning,” IEEE Access, vol. 9, pp. 29416–29428, 2021, doi: 10.1109/ACCESS.2021.3052206.
N. Ibrahim, “Underwater_Image_Dataset,” Kaggle, 2025. https://www.kaggle.com/datasets/khajaahmed1/underwater-image-dataset
N. Ibrahim, “Marine_Pulse,” Kaggle, 2024. https://www.kaggle.com/datasets/khajaahmed1/marine-pulse
J. Yang, M. Cai, X. Yang, and Z. Zhou, “Underwater Image Classification Algorithm Based on Convolutional Neural Network and Optimized Extreme Learning Machine,” J. Mar. Sci. Eng., vol. 10, no. 12, p. 1841, Dec. 2022, doi: 10.3390/jmse10121841.
Y. Ren, X. Li, X. Yang, and H. Xu, “Development of a Dual-Attention U-Net Model for Sea Ice and Open Water Classification on SAR Images,” IEEE Geosci. Remote Sens. Lett., vol. 19, pp. 1–5, 2022, doi: 10.1109/LGRS.2021.3058049.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Srinadh Maddukuri, J. B. Seventline

This work is licensed under a Creative Commons Attribution 4.0 International License.














