LAESI: Leaf Area Estimation with Synthetic Imagery

arXiv:2404.00593v1 Announce Type: cross
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 …

abstract analysis arxiv cs.ai cs.cv cs.gr cs.lg dataset images labels masks oak paper semantic surface synthetic training type