CS-TRD: a Cross Sections Tree Ring Detection method

TL;DR

CS-TRD is an automated method for detecting and connecting tree growth rings in cross-sectional images, achieving high accuracy without specialized hardware, useful for dendrochronology and forestry research.

Contribution

It introduces a fully automated tree ring detection technique that combines edge detection and pith localization, improving accuracy and usability over previous methods.

Findings

Achieves 89% F-Score on UruDendro dataset

Achieves 97% F-Score on Kennel dataset

No specialized hardware needed

Abstract

This work describes a Tree Ring Detection method for complete Cross-Sections of Trees (CS-TRD) that detects, processes and connects edges corresponding to the tree's growth rings. The method depends on the parameters for the Canny Devernay edge detector (sigma), a resize factor, the number of rays, and the pith location. The first five are fixed by default. The pith location can be marked manually or using an automatic pith detection algorithm. Besides the pith localization, CS-TRD is fully automated and achieves an F-Score of 89% in the UruDendro dataset (of Pinus taeda) and 97% in the Kennel dataset (of Abies alba) without specialized hardware requirements.