用深度学习识别尼泊尔60种草药，手机就能用。
Local Herb Identification Using Transfer Learning: A CNN-Powered Mobile Application for Nepalese Flora
- 用迁移学习+CNN从1.2万张图训练分类模型
- DenseNet121表现最佳，准确率超95%
- 适合植物学家和本地农户用手机识别草药
草药分类在生物多样性丰富的地区如尼泊尔面临重大挑战。本研究提出一种新型深度学习方法，利用卷积神经网络（CNN）与迁移学习技术对60种不同草药进行分类。基于人工整理的12,000张草药图像数据集，我们构建了鲁棒的机器学习模型，解决了现有草药识别方法的局限性。研究对比了多种模型架构，包括DenseNet121、50层残差网络（ResNet50）、16层视觉几何组网络（VGG16）、InceptionV3、EfficientNetV2和视觉变换器（VIT），最终DenseNet121表现最优。通过数据增强与正则化技术缓解过拟合，提升模型泛化能力。该工作推动了草药分类技术发展，有助于保护传统植物知识并促进草药可持续利用。
原文摘要 · Abstract (English)
Herb classification presents a critical challenge in botanical research, particularly in regions with rich biodiversity such as Nepal. This study introduces a novel deep learning approach for classifying 60 different herb species using Convolutional Neural Networks (CNNs) and transfer learning techniques. Using a manually curated dataset of 12,000 herb images, we developed a robust machine learning model that addresses existing limitations in herb recognition methodologies. Our research employed multiple model architectures, including DenseNet121, 50-layer Residual Network (ResNet50), 16-layer Visual Geometry Group Network (VGG16), InceptionV3, EfficientNetV2, and Vision Transformer (VIT), with DenseNet121 ultimately demonstrating superior performance. Data augmentation and regularization techniques were applied to mitigate overfitting and enhance the generalizability of the model. This work advances herb classification techniques, preserving traditional botanical knowledge and promoting sustainable herb utilization.
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。