Wang Guoying, Shi Bing, Yi Xiaomei, Wu Peng, Kong Linjun, Mo Lufeng
College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, China.
Office of Information Technology, Zhejiang University of Finance & Economics, Hangzhou 310018, China.
Animals (Basel). 2024 Feb 2;14(3):499. doi: 10.3390/ani14030499.
Blurry scenarios, such as light reflections and water ripples, often affect the clarity and signal-to-noise ratio of fish images, posing significant challenges for traditional deep learning models in accurately recognizing fish species. Firstly, deep learning models rely on a large amount of labeled data. However, it is often difficult to label data in blurry scenarios. Secondly, existing deep learning models need to be more effective for the processing of bad, blurry, and otherwise inadequate images, which is an essential reason for their low recognition rate. A method based on the diffusion model and attention mechanism for fish image recognition in blurry scenarios, DiffusionFR, is proposed to solve these problems and improve the performance of species recognition of fish images in blurry scenarios. This paper presents the selection and application of this correcting technique. In the method, DiffusionFR, a two-stage diffusion network model, TSD, is designed to deblur bad, blurry, and otherwise inadequate fish scene pictures to restore clarity, and a learnable attention module, LAM, is intended to improve the accuracy of fish recognition. In addition, a new dataset of fish images in blurry scenarios, BlurryFish, was constructed and used to validate the effectiveness of DiffusionFR, combining bad, blurry, and otherwise inadequate images from the publicly available dataset Fish4Knowledge. The experimental results demonstrate that DiffusionFR achieves outstanding performance on various datasets. On the original dataset, DiffusionFR achieved the highest training accuracy of 97.55%, as well as a Top-1 accuracy test score of 92.02% and a Top-5 accuracy test score of 95.17%. Furthermore, on nine datasets with light reflection noise, the mean values of training accuracy reached a peak at 96.50%, while the mean values of the Top-1 accuracy test and Top-5 accuracy test were at their highest at 90.96% and 94.12%, respectively. Similarly, on three datasets with water ripple noise, the mean values of training accuracy reached a peak at 95.00%, while the mean values of the Top-1 accuracy test and Top-5 accuracy test were at their highest at 89.54% and 92.73%, respectively. These results demonstrate that the method showcases superior accuracy and enhanced robustness in handling original datasets and datasets with light reflection and water ripple noise.
模糊场景，如光反射和水波涟漪，常常影响鱼类图像的清晰度和信噪比，给传统深度学习模型准确识别鱼类物种带来重大挑战。首先，深度学习模型依赖大量标注数据。然而，在模糊场景下标注数据往往很困难。其次，现有的深度学习模型在处理质量差、模糊及其他不充分的图像方面效果欠佳，这是其识别率低的一个重要原因。为了解决这些问题并提高模糊场景下鱼类图像的物种识别性能，提出了一种基于扩散模型和注意力机制的模糊场景鱼类图像识别方法DiffusionFR。本文介绍了这种校正技术的选择与应用。在DiffusionFR方法中，设计了一个两阶段扩散网络模型TSD，用于对质量差、模糊及其他不充分的鱼类场景图片进行去模糊处理以恢复清晰度，还设计了一个可学习的注意力模块LAM，旨在提高鱼类识别的准确性。此外，构建了一个新的模糊场景鱼类图像数据集BlurryFish，并结合公开可用数据集Fish4Knowledge中的质量差、模糊及其他不充分的图像，用于验证DiffusionFR的有效性。实验结果表明，DiffusionFR在各种数据集上都取得了优异的性能。在原始数据集上，DiffusionFR的训练准确率最高达到97.55%，Top-1准确率测试得分92.02%，Top-5准确率测试得分95.17%。此外，在九个存在光反射噪声的数据集上，训练准确率的平均值在96.57%时达到峰值，而Top-1准确率测试和Top-5准确率测试的平均值分别在90.96%和94.12%时达到最高。同样，在三个存在水波涟漪噪声的数据集上，训练准确率的平均值在95.00%时达到峰值，而Top-1准确率测试和Top-5准确率测试的平均值分别在89.54%和92.73%时达到最高。这些结果表明，该方法在处理原始数据集以及存在光反射和水波涟漪噪声的数据集时，展现出了卓越的准确性和更强的鲁棒性。
