# Tree bark re-identification using a deep-learning feature descriptor

arXiv: https://arxiv.org/abs/1912.03221 · HTML: https://mlsanity.com/paper/1912.03221/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2019.

## Built on by (most cited first, 3 of 3)

- [BarkXAI: A Lightweight Post-Hoc Explainable Method for Tree Species Classification with Quantifiable Concepts](https://mlsanity.com/paper/2502.18844/) (2025)
- [SilvaScenes: Tree Detection and Species Classification from Under-Canopy Images in Natural Forests](https://mlsanity.com/paper/2510.09458/) (2025)
- [BarkNet-Lite: A Lightweight Texture and Colour Network with the BarkBD Benchmark for Bark-Based Tree Species Recognition in Bangladesh](https://mlsanity.com/paper/2609.07600/) (2026)

## Abstract (arXiv)

The ability to visually re-identify objects is a fundamental capability in vision systems. Oftentimes, it relies on collections of visual signatures based on descriptors, such as SIFT or SURF. However, these traditional descriptors were designed for a certain domain of surface appearances and geometries (limited relief). Consequently, highly-textured surfaces such as tree bark pose a challenge to them. In turn, this makes it more difficult to use trees as identifiable landmarks for navigational purposes (robotics) or to track felled lumber along a supply chain (logistics). We thus propose to use data-driven descriptors trained on bark images for tree surface re-identification. To this effect, we collected a large dataset containing 2,400 bark images with strong illumination changes, annotated by surface and with the ability to pixel-align them. We used this dataset to sample from more than 2 million 64x64 pixel patches to train our novel local descriptors DeepBark and SqueezeBark. Our DeepBark method has shown a clear advantage against the hand-crafted descriptors SIFT and SURF. For instance, we demonstrated that DeepBark can reach a mAP of 87.2% when retrieving 11 relevant bark images, i.e. corresponding to the same physical surface, to a bark query against 7,900 images. Our work thus suggests that re-identifying tree surfaces in a challenging illuminations context is possible. We also make public our dataset, which can be used to benchmark surface re-identification techniques.