LAESI: Leaf Area Estimation with Synthetic Imagery
This provides a resource for leaf analysis in agriculture and biology, but it is incremental as it builds on existing procedural and generative methods for data creation.
The authors tackled the problem of leaf morphology analysis by creating LAESI, a synthetic leaf dataset of 100,000 images with masks and area labels, and showed that models trained on it can predict leaf surface area with relative error comparable to human annotators.
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.