Leaf Identification Using a Deep Convolutional Neural Network
This work addresses plant species identification for botanical or agricultural applications, but it is incremental as it applies standard techniques like data augmentation and transfer learning to small datasets.
The authors tackled leaf identification by proposing a nine-layer convolutional neural network (CNN) applied to the Flavia and Foliage datasets, achieving recognition rates above 99% and slightly outperforming current methods.
Convolutional neural networks (CNNs) have become popular especially in computer vision in the last few years because they achieved outstanding performance on different tasks, such as image classifications. We propose a nine-layer CNN for leaf identification using the famous Flavia and Foliage datasets. Usually the supervised learning of deep CNNs requires huge datasets for training. However, the used datasets contain only a few examples per plant species. Therefore, we apply data augmentation and transfer learning to prevent our network from overfitting. The trained CNNs achieve recognition rates above 99% on the Flavia and Foliage datasets, and slightly outperform current methods for leaf classification.