用深度学习自动识别有害藻类，准确率达96.97%。
Recognition of Harmful Phytoplankton from Microscopic Images using Deep Learning
- 采用ResNet-50与微调策略，从显微图像中分类11种有害藻类。
- 模型在11类藻类上达到96.97%准确率，但对形态相似种类区分困难。
- 适用于环境监测、生态预警，尤其适合需要快速分析的场景。
监测浮游生物分布，尤其是有害藻类，对保护水生生态系统、调节全球气候和保障环境安全至关重要。传统监测方法通常耗时长、成本高、易出错，且不适用于大规模应用，亟需高效精准的自动化系统。本研究评估了多种先进CNN模型（包括ResNet、ResNeXt、DenseNet和EfficientNet），结合三种迁移学习方法（线性探测、微调及组合方法），从显微图像中分类11种有害藻类属。最佳结果由使用微调策略的ResNet-50模型实现，准确率达96.97%。结果还表明，模型在区分四类形态特征相似的有害藻类时表现较差。
原文摘要 · Abstract (English)
Monitoring plankton distribution, particularly harmful phytoplankton, is vital for preserving aquatic ecosystems, regulating the global climate, and ensuring environmental protection. Traditional methods for monitoring are often time-consuming, expensive, error-prone, and unsuitable for large-scale applications, highlighting the need for accurate and efficient automated systems. In this study, we evaluate several state-of-the-art CNN models, including ResNet, ResNeXt, DenseNet, and EfficientNet, using three transfer learning approaches: linear probing, fine-tuning, and a combined approach, to classify eleven harmful phytoplankton genera from microscopic images. The best performance was achieved by ResNet-50 using the fine-tuning approach, with an accuracy of 96.97%. The results also revealed that the models struggled to differentiate between four harmful phytoplankton types with similar morphological features.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。