Tree Species Identification from Bark Images Using Convolutional Neural Networks

Mathieu Carpentier, Philippe Giguère, Jonathan Gaudreault
3/2/2018
cs.CV

Official code: ulaval-damas/tree-bark-classification (28 stars, MIT, last commit 2025-02-28).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

ulaval-damas/tree-bark-classificationOfficial100%
MIT
287PythonJul 25, 20181 years agoMIT

Similar Papers

BarkXAI: A Lightweight Post-Hoc Explainable Method for Tree Species Classification with Quantifiable Concepts

89% match2025

Lidar-based Norwegian tree species detection using deep learning

87% match2023

Deep Learning methodology for the identification of wood species using high-resolution macroscopic images

87% match1 repo12024

Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K dataset

86% match2 repos142024

Enhancing Tree Species Classification: Insights from YOLOv8 and Explainable AI Applied to TLS Point Cloud Projections

86% match2025

Mining Field Data for Tree Species Recognition at Scale

85% match2024

Cite this paper

@article{carpentier2018tree,
  title  = {Tree Species Identification from Bark Images Using Convolutional Neural Networks},
  author = {Mathieu Carpentier and Philippe Giguère and Jonathan Gaudreault},
  year   = {2018},
  eprint = {1803.00949},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1803.00949}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1803.00949.svg)](https://codeofpaper.com/paper/1803.00949)

Discussion