Local Herb Identification Using Transfer Learning: A CNN-Powered Mobile Application for Nepalese Flora

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.

@article{thapa2025_2505.02147,
  title={ Local Herb Identification Using Transfer Learning: A CNN-Powered Mobile Application for Nepalese Flora },
  author={ Prajwal Thapa and Mridul Sharma and Jinu Nyachhyon and Yagya Raj Pandeya },
  journal={arXiv preprint arXiv:2505.02147},
  year={ 2025 }
}