# A spontaneous keypoints connection algorithm for leafy plants skeletonization and phenotypes extraction

## TL;DR

This paper introduces a label-free and training-free method for creating leaf skeletons and extracting plant phenotypes, reducing manual effort and enabling high-throughput analysis.

## Contribution

A novel, training-free algorithm for leaf skeletonization that works without manual labeling and adapts to both random and regular leaf morphologies.

## Key findings

- The method achieved an average curvature fitting error of 0.12 and 92% leaf recall on orchid images.
- Five phenotypic parameters were accurately extracted from leaf skeletons in orchids.
- The approach generalized well to maize, showing cross-species applicability.

## Abstract

Leaf phenotypes are key indicators of plant growth status. Existing deep learning–based leaf skeletonization typically requires extensive manual labeling, long training, and predefined keypoints, which limits scalability. We developed a training-free and label-free approach that connects spontaneously detected keypoints to generate leaf skeletons for leafy plants.

The method comprises random seed-point generation and adaptive keypoint connection. For plants with random leaf morphology, we determine a threshold for the angle difference among any three consecutive adjacent points and iteratively identify keypoints within circular search neighborhoods to trace leaf skeletons. For plants with regular leaf morphology, we fit the skeleton trajectory by minimizing curvature. We validated the approach on vertical and front-view images of orchids (covering random and regular morphological cases) and extracted five phenotypic parameters from the resulting skeletons. Generalization was further assessed on a maize image dataset.

On orchid images, the proposed approach achieved an average curvature fitting error of 0.12 and an average leaf recall of 92%. Five orchid phenotypic parameters were accurately derived from the skeletons. The method also showed effective skeletonization on maize, indicating cross-species applicability.

By eliminating manual labels and training, this approach reduces annotation effort and computational overhead while enabling precise geometric phenotype calculation from skeleton-based keypoints. Its effectiveness on both randomly distributed and regularly shaped leafy plants suggests suitability for high-throughput plant phenotyping workflows.