Underwater object recognition presents unique challenges due to varying water conditions, low visibility, and the presence of noise. This research proposes an advanced methodology that combines transfer learning and hybrid optimization techniques to enhance recognition accuracy in underwater environments. Specifically, a pre-trained EfficientNet model is employed for feature extraction, leveraging its capacity to capture diverse features in underwater images. The model is then optimized using a hybrid Particle Swarm Optimization and Genetic Algorithm (PSOGA) to fine-tune hyperparameters such as learning rate, number of layers, and activation functions. This hybrid approach balances exploration and exploitation in the search space, allowing the model to converge on an optimal solution that maximizes accuracy. The model is evaluated against nine existing deep learning models, including ResNet-50, VGG-16, EfficientNet-B0, and MobileNetV2. The proposed PSOGA model achieves a superior accuracy of 98.32%, surpassing the best-performing models like EfficientNet-B0, which reached 95.89%. Furthermore, the model outperforms traditional optimizers like Adam, RMSprop, and AdaGrad, which attained lower accuracies. Precision, recall, and F1-score for the PSOGA model also demonstrate remarkable improvements, highlighting the model's effectiveness in underwater object recognition. The combination of transfer learning and hybrid optimization enables the model to generalize well across diverse underwater environments while maintaining computational efficiency.
Z. Liu, B. Wang, Y. Li, J. He, and Y. Li, “UnitModule: A lightweight joint image enhancement module for underwater object detection,” Pattern Recognition, vol. 151, p. 110435, Jul. 2024, doi: 10.1016/j.patcog.2024.110435.
S. R. Lyernisha, C. Seldev Christopher, and S. R. Fernisha, “Object recognition from enhanced underwater image using optimized deep-CNN,” International Journal of Wavelets, Multiresolution and Information Processing, vol. 21, no. 04, Mar. 2023, doi: 10.1142/s0219691323500078.
X. Hua et al., “Underwater object detection algorithm based on feature enhancement and progressive dynamic aggregation strategy,” Pattern Recognition, vol. 139, p. 109511, Jul. 2023, doi: 10.1016/j.patcog.2023.109511.
H. Zhou et al., “Real-time underwater object detection technology for complex underwater environments based on deep learning,” Ecological Informatics, vol. 82, p. 102680, Sep. 2024, doi: 10.1016/j.ecoinf.2024.102680.
K. G, A. J, S. B, and M. P. M, “RETRACTED ARTICLE: A Deep Learning Approach to Detecting Objects in Underwater Images,” Cybernetics and Systems, pp. 1–16, Jan. 2023, doi: 10.1080/01969722.2023.2166246.
J. Zhang, J. Zhang, K. Zhou, Y. Zhang, H. Chen, and X. Yan, “An Improved YOLOv5-Based Underwater Object-Detection Framework,” Sensors, vol. 23, no. 7, p. 3693, Apr. 2023, doi: 10.3390/s23073693.
G. Chandrashekar, A. Raaza, V. Rajendran, and D. Ravikumar, “Side scan sonar image augmentation for sediment classification using deep learning based transfer learning approach,” Materials Today: Proceedings, vol. 80, pp. 3263–3273, 2023, doi: 10.1016/j.matpr.2021.07.222.
G. Verma, M. Kumar, and S. Raikwar, “F2UIE: feature transfer-based underwater image enhancement using multi-stackcnn,” Multimedia Tools and Applications, vol. 83, no. 17, pp. 50111–50132, Nov. 2023, doi: 10.1007/s11042-023-17180-1.
J. Zhou, T. Xu, W. Guo, W. Zhao, and L. Cai, “Underwater occluded object recognition with two-stage image reconstruction strategy,” Multimedia Tools and Applications, vol. 83, no. 4, pp. 11127–11146, Jun. 2023, doi: 10.1007/s11042-023-15658-6.
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.
X. Liu, Z. Chen, Z. Xu, Z. Zheng, F. Ma, and Y. Wang, “Enhancement of Underwater Images through Parallel Fusion of Transformer and CNN,” Journal of Marine Science and Engineering, vol. 12, no. 9, p. 1467, Aug. 2024, doi: 10.3390/jmse12091467.
J. Gao, Y. Zhang, X. Geng, H. Tang, and U. A. Bhatti, “PE-Transformer: Path enhanced transformer for improving underwater object detection,” Expert Systems with Applications, vol. 246, p. 123253, Jul. 2024, doi: 10.1016/j.eswa.2024.123253.
Y. Zhang, Q. Jiang, P. Liu, S. Gao, X. Pan, and C. Zhang, “Underwater Image Enhancement Using Deep Transfer Learning Based on a Color Restoration Model,” IEEE Journal of Oceanic Engineering, vol. 48, no. 2, pp. 489–514, Apr. 2023, doi: 10.1109/joe.2022.3227393.
H. Yang, W. Peng, J. Yao, and X. Ye, “Effective adversarial transfer learning for underwater image enhancement with hybrid losses,” Signal, Image and Video Processing, vol. 18, no. 10, pp. 6671–6681, Jun. 2024, doi: 10.1007/s11760-024-03343-6.
M. Zhou, L. Cai, J. Jia, and Y. Gao, “Multi-scale aware turbulence network for underwater object recognition,” Frontiers in Marine Science, vol. 11, Mar. 2024, doi: 10.3389/fmars.2024.1301072.
H. Yao, T. Gao, Y. Wang, H. Wang, and X. Chen, “Mobile_ViT: Underwater Acoustic Target Recognition Method Based on Local–Global Feature Fusion,” Journal of Marine Science and Engineering, vol. 12, no. 4, p. 589, Mar. 2024, doi: 10.3390/jmse12040589.
V. Malathi, A. Manikandan, and K. Krishnan, “Optimzied resnet model of convolutional neural network for under sea water object detection and classification,” Multimedia Tools and Applications, vol. 82, no. 24, pp. 37551–37571, Mar. 2023, doi: 10.1007/s11042-023-15041-5.
J. Chen, et al., "Underwater Object Recognition Using Enhanced VGG Network", Electronics, vol. 12, no. 6, pp. 751-763, (2023), DOI: 10.3390/electronics12060751.
Y. Zhao, et al., "EfficientNet-Based Real-Time Underwater Object Detection for Marine Applications," Access, vol. 11, pp. 1401–1412, (2023), DOI: 10.1109/ACCESS.2023.3224017.
P. Liu, et al., "DenseNet-Based Underwater Object Recognition Using Transfer Learning", JoMSE, vol. 11, no. 2, pp. 235-245, (2023), DOI: 10.3390/jmse11020235.
F. Zhang, et al., “InceptionV3-Based Deep Learning Framework for Underwater Object Recognition", Sensors, vol. 23, no. 4, pp. 1289-1299, (2023), DOI: [10.3390/s23041289.
L. He, et al., "Enhanced Xception Model for Underwater Object Detection", Applied Sciences, vol. 14, no. 1, pp. 89-98, (2024), DOI: 10.3390/app14010089.
G. Sun, et al., "MobileNetV2-Based Lightweight Underwater Object Recognition System", TGRS, vol. 61, pp. 123-133, (2023), DOI: 10.1109/TGRS.2023.3244782.
Y. Li, et al., "ShuffleNet-Based Approach for Real-Time Underwater Object Detection", JOE, vol. 59, no. 4, pp. 157-168, (2023), DOI: 10.1016/j.oceaneng.2023.102189.
L. Zhang, et al., "A Deep Learning Approach to Detecting Objects in Underwater Images using AlexNet", IJOMR, vol. 18, pp. 102-113, (2023), DOI: 10.1109/JOMAR.2023.119345.
Acknowledgements
Author(s) thanks to Dr. Jeevanantham Vellaichamy for this research completion and support.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Sujilatha Tada
Department of Computer Science and Engineering, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology, Chennai, Tamil Nadu, India.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Sujilatha Tada and Jeevanantham Vellaichamy, “Enhancing Underwater Object Recognition: Integrating Transfer Learning with Hybrid Optimization Techniques for Improved Detection Accuracy”, Journal of Machine and Computing. doi: 10.53759/7669/jmc202505035.
