Tree Species Identification from Bark Images Using Convolutional Neural Networks
This work addresses a domain-specific problem for forestry by providing a dataset and baseline results, but it is incremental as it applies existing deep learning methods to a new dataset.
The authors tackled tree species identification from bark images by creating a new dataset, BarkNet 1.0, and achieved accuracies of 93.88% on single crops and 97.81% using majority voting.
Tree species identification using bark images is a challenging problem that could prove useful for many forestry related tasks. However, while the recent progress in deep learning showed impressive results on standard vision problems, a lack of datasets prevented its use on tree bark species classification. In this work, we present, and make publicly available, a novel dataset called BarkNet 1.0 containing more than 23,000 high-resolution bark images from 23 different tree species over a wide range of tree diameters. With it, we demonstrate the feasibility of species recognition through bark images, using deep learning. More specifically, we obtain an accuracy of 93.88% on single crop, and an accuracy of 97.81% using a majority voting approach on all of the images of a tree. We also empirically demonstrate that, for a fixed number of images, it is better to maximize the number of tree individuals in the training database, thus directing future data collection efforts.