A Multi-Step Image Pre-Enhancement Strategy for a Fish Feeding Behavior Analysis Using Efficientnet
Source abstract
Abstract
To enhance the accuracy of lightweight CNN classification models in analyzing fish feeding behavior, this paper addresses the image quality issues caused by external environmental factors and lighting conditions, such as low contrast and uneven illumination, by proposing a Multi-step Image Pre-enhancement Strategy (MIPS). This strategy includes three critical steps: initially, images undergo a preliminary processing using the Multi-Scale Retinex with Color Restoration (MSRCR) algorithm, effectively reducing the impact of water surface reflections and enhancing the visual effect of the images; secondly, the Multi-Metric-Driven Contrast Limited Adaptive Histogram Equalization (mdc) technique is applied to further improve image contrast, especially in areas of low contrast, by adjusting the local contrast levels to enhance the clarity of the image details; finally, Unsharp Masking (UM) technology is employed to sharpen the images, emphasizing their edges to increase the clarity of the image details, thereby significantly improving the overall image quality. Experimental results on a custom dataset have confirmed that this pre-enhancement strategy significantly boosts the accuracy of various CNN-based classification models, particularly for lightweight CNN models, and drastically reduces the time required for model training compared to the use of advanced ResNet models. This research provides an effective technical route for improving the accuracy and efficiency of an image-based analysis of fish feeding behavior in complex environments.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Water Quality Monitoring Technologies · Image Enhancement Techniques · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of Fisheries Information, Ministry of Agriculture and Rural Affairs, Shanghai Ocean University, Hucheng Ring Road 999, Shanghai 201306, China
Funding
Shanghai Science and Technology Innovation Action Planning · Jiang Su Modern Agricultural Industry Key Technology Innovation Planning
References (45)
Show source-provided references
1. Application of Computer Vision in Fish Intelligent Feeding System—A Review10.1111/are.14907 ↗
2. An Acoustic Based Approach to Evaluate the Effect of Different Diet Lengths on Feeding Behavior of Litopenaeus vannamei10.1016/j.aquaeng.2020.102114 ↗
3. Automatic Feeding Control for Dense Aquaculture Fish Tanks10.1109/LSP.2014.2385794 ↗
4. Development of an Intelligent Feeding Controller for Indoor Intensive Culturing of Eel10.1016/j.aquaeng.2004.07.004 ↗
5. The Impact of Fish Feed on Water Quality in Lake Cilala, Bogor Regency, West Java10.1088/1755-1315/716/1/012023 ↗
6. Feed Requirement Determination of Grass Carp (Ctenopharyngodon idella) Using a Hybrid Method of Bioenergetics Factorial Model and Fuzzy Logic Control Technology under Outdoor Pond Culturing Systems10.1016/j.aquaculture.2020.734970 ↗
7. Dynamic Feeding Method for Aquaculture Fish Using Multi-Task Neural Network10.1016/j.aquaculture.2022.737913 ↗
8. Behavioral Spatial-Temporal Characteristics-Based Appetite Assessment for Fish School in Recirculating Aquaculture Systems10.1016/j.aquaculture.2021.737215 ↗
9. Modified Kinetic Energy Feature-Based Graph Convolutional Network for Fish Appetite Grading Using Time-Limited Data in Aquaculture10.3389/fmars.2022.1021688 ↗
10. Near-Infrared Imaging to Quantify the Feeding Behavior of Fish in Aquaculture10.1016/j.compag.2017.02.013 ↗
11. Fish species recognition based on CNN using annotated image10.1007/978-981-10-6451-7_19 ↗
12. Underwater live fish recognition by deep learning10.1007/978-3-319-94211-7_30 ↗
13. Yang, L., Chen, Y., Shen, T., and Li, D. (2023). An FSFS-Net Method for Occluded and Aggregated Fish Segmentation from Fish School Feeding Images. Appl. Sci., 13.10.3390/app13106235 ↗
14. Optimal Swim Speeds for Traversing Velocity Barriers: An Analysis of Volitional High-Speed Swimming Behavior of Migratory Fishes10.1242/jeb.01380 ↗
15. Near Infrared Computer Vision and Neuro-Fuzzy Model-Based Feeding Decision System for Fish in Aquaculture10.1016/j.compag.2018.02.006 ↗
16. ImageNet Classification with Deep Convolutional Neural Networks10.1145/3065386 ↗
17. Evaluation of Fish Feeding Intensity in Aquaculture Using a Convolutional Neural Network and Machine Vision10.1016/j.aquaculture.2019.04.056 ↗
18. A Computer Vision-Based Intelligent Fish Feeding System Using Deep Learning Techniques for Aquaculture10.1109/JSEN.2022.3151777 ↗
19. A Spatiotemporal Attention Network-Based Analysis of Golden Pompano School Feeding Behavior in an Aquaculture Vessel10.1016/j.compag.2022.107610 ↗
20. A dual stream hierarchical transformer for starvation grading of golden pomfret in marine aquaculture10.3389/fmars.2022.1039898 ↗
21. Zheng, K., Yang, R., Li, R., Yang, L., Qin, H., and Sun, M. (2022, January 2–4). A Deep Transformer Model-Based Analysis of Fish School Starvation Degree in Marine Farming Vessels. Proceedings of the 2022 4th International Conference on Control and Robotics (ICCR), Guangzhou, China.10.1109/ICCR55715.2022.10053891 ↗
22. Behavioral Characteristics and Statistics-Based Imaging Techniques in the Assessment and Optimization of Tilapia Feeding in a Recirculating Aquaculture System10.13031/trans.59.11406 ↗
23. Wang, G., Muhammad, A., Liu, C., Du, L., and Li, D. (2021). Automatic Recognition of Fish Behavior with a Fusion of RGB and Optical Flow Data Based on Deep Learning. Animals, 11.10.3390/ani11102774 ↗
24. Shang, H., Yu, Y., and Song, W. (2023, January 10–12). Underwater Fish Image Classification Algorithm Based on Improved ResNet-RS Model. Proceedings of the Jiangsu Annual Conference on Automation (JACA 2023), Changzhou, China.10.1049/icp.2024.0070 ↗
25. Modified Motion Influence Map and Recurrent Neural Network-Based Monitoring of the Local Unusual Behaviors for Fish School in Intensive Aquaculture10.1016/j.aquaculture.2018.04.064 ↗
26. Zhang, B., Xie, F., and Han, F. (2019, January 4–7). Fish Population Status Detection Based on Deep Learning System. Proceedings of the 2019 IEEE International Conference on Mechatronics and Automation (ICMA), Tianjin, China.10.1109/ICMA.2019.8816263 ↗
27. Qi, R., Liu, H., and Liu, S. (2023). Effects of Different Culture Densities on the Acoustic Characteristics of Micropterus Salmoide Feeding. Fishes, 8.10.3390/fishes8030126 ↗
28. Underwater Image Enhancement and Marine Snow Removal for Fishery Based on Integrated Dual-Channel Neural Network10.1016/j.compag.2021.106182 ↗
29. Yang, P., Liu, Q.Y., and Li, Z. (2023). A High-Precision Classification Method for Fish Feeding Behavior Analysis Based on Improved RepVGG. Preprints, 2023091041.10.20944/preprints202309.1041.v1 ↗
30. A MobileNetV2-SENet-Based Method for Identifying Fish School Feeding Behavior10.1016/j.aquaeng.2022.102288 ↗
31. A Dual Attention Network Based on efficientNet-B2 for Short-Term Fish School Feeding Behavior Analysis in Aquaculture10.1016/j.compag.2021.106316 ↗
32. MSIF-MobileNetV3: An Improved MobileNetV3 Based on Multi-Scale Information Fusion for Fish Feeding Behavior Analysis10.1016/j.aquaeng.2023.102338 ↗
33. A Real-Time Feeding Decision Method Based on Density Estimation of Farmed Fish10.3389/fmars.2024.1358209 ↗
34. Zhang, S., Zhu, M., and Meng, K. (2022, January 21–23). An Automated Multi-Scale Retinex for Dim Image Enhancement. Proceedings of the 2022 IEEE 2nd International Conference on Power, Electronics and Computer Applications (ICPECA), Shenyang, China.10.1109/ICPECA53709.2022.9719125 ↗
35. A Multiscale Retinex for Bridging the Gap between Color Images and the Human Observation of Scenes10.1109/83.597272 ↗
36. Image Contrast Enhancement Using Unsharp Masking and Histogram Equalization10.1007/s11042-018-5894-8 ↗
37. An Assistive Computer Vision Tool to Automatically Detect Changes in Fish Behavior in Response to Ambient Odor10.1038/s41598-020-79772-3 ↗
38. Evaluating Fish Feeding Intensity in Aquaculture with Convolutional Neural Networks10.1016/j.aquaeng.2021.102178 ↗
39. Realization of the Contrast Limited Adaptive Histogram Equalization (CLAHE) for Real-Time Image Enhancement10.1023/B:VLSI.0000028532.53893.82 ↗
40. Koonsanit, K., Thongvigitmanee, S., Pongnapang, N., and Thajchayapong, P. (September, January 31). Image Enhancement on Digital X-Ray Images Using N-CLAHE. Proceedings of the 2017 10th Biomedical Engineering International Conference (BMEiCON), Hokkaido, Japan.10.1109/BMEiCON.2017.8229130 ↗
41. An Approach for De-Noising and Contrast Enhancement of Retinal Fundus Image Using CLAHE10.1016/j.optlastec.2018.06.061 ↗
42. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
43. Feeding Intensity Identification Method for Pond Fish School Using Dual-Label and MobileViT-SENet10.1016/j.biosystemseng.2024.03.010 ↗
44. Tan, M., Chen, B., Pang, R., Vasudevan, V., Sandler, M., Howard, A., and Le, Q.V. (2019, January 15–20). MnasNet: Platform-Aware Neural Architecture Search for Mobile. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00293 ↗
45. Manifold Information through Neighbor Embedding Projection for Image Retrieval10.1016/j.patrec.2024.04.022 ↗