Tree Species Identification from Bark Images Using Convolutional Neural Networks

Tree species identification using images of the bark is a challenging problem that could help in tasks such as drone navigation in forest environment and autonomous forest inventory management. It also brings more value to harvesting operations as it leads to greater market values of trees. While the recent progress in deep learning showed its effectiveness for visual classification, it cannot currently be used for bark classification due to a lack of dataset. In this work, we present a novel dataset containing more than 23 000 high-resolution bark images from 23 different species and establish a benchmark using deep learning. We obtain an accuracy of 93.88% and show the possibility of using a majority voting approach on all the images of a tree to obtain 97.81% accuracy. We also perform experiments indicating that it is more important to collect a large amount of trees over a large quantity of image and that images of a single tree should be taken at different locations.