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

TL;DR

This paper presents a transfer learning-based CNN model for accurate herb identification in Nepal, utilizing a curated dataset and multiple architectures to improve botanical research and conservation efforts.

Contribution

It introduces a novel deep learning approach with transfer learning for classifying Nepalese herbs, outperforming existing methods and aiding botanical preservation.

Findings

DenseNet121 achieved the highest accuracy

Data augmentation improved model robustness

Transfer learning enhanced herb classification performance

Abstract

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.