LAESI: Leaf Area Estimation with Synthetic Imagery

TL;DR

LAESI introduces a large synthetic leaf dataset for training machine learning models to accurately estimate leaf surface area and segmentation, validated on real images, with potential applications in agriculture and biology.

Contribution

The paper presents LAESI, a synthetic dataset of 100,000 leaf images with labels, and demonstrates its effectiveness for training models on real leaf images, integrating generative AI and procedural modeling.

Findings

Models trained on LAESI achieve human-level accuracy in leaf surface area estimation.

Synthetic data improves model performance and generalization on real images.

Filtering based on annotation consistency enhances dataset quality and model accuracy.

Abstract

We introduce LAESI, a Synthetic Leaf Dataset of 100,000 synthetic leaf images on millimeter paper, each with semantic masks and surface area labels. This dataset provides a resource for leaf morphology analysis primarily aimed at beech and oak leaves. We evaluate the applicability of the dataset by training machine learning models for leaf surface area prediction and semantic segmentation, using real images for validation. Our validation shows that these models can be trained to predict leaf surface area with a relative error not greater than an average human annotator. LAESI also provides an efficient framework based on 3D procedural models and generative AI for the large-scale, controllable generation of data with potential further applications in agriculture and biology. We evaluate the inclusion of generative AI in our procedural data generation pipeline and show how data filtering based on annotation consistency results in datasets which allow training the highest performing vision models.