Automated segmentation of individual leaves of a plant in an image is a prerequisite to measure more complex phenotypic traits in high-throughput phenotyping. Applying state-of-the-art machine learning approaches to tackle leaf instance segmentation requires a large amount of manually annotated training data. Currently, the benchmark datasets for leaf segmentation contain only a few hundred labeled training images. In this paper, we propose a framework for leaf instance segmentation by augmenting real plant datasets with generated synthetic images of plants inspired by domain randomisation. We train a state-of-the-art deep learning segmentation architecture (Mask-RCNN) with a combination of real and synthetic images of Arabidopsis plants. Our proposed approach achieves 90% leaf segmentation score on the A1 test set outperforming the-state-of-the-art approaches for the CVPPP Leaf Segmentation Challenge (LSC). Our approach also achieves 81% mean performance over all five test datasets.
@article{arxiv.1807.10931,
title = {Deep Leaf Segmentation Using Synthetic Data},
author = {Daniel Ward and Peyman Moghadam and Nicolas Hudson},
journal= {arXiv preprint arXiv:1807.10931},
year = {2019}
}
Comments
British Machine Vision Conference (BMVC) 2018 Proceedings. CVPPP Workshop at BMVC 2018. Dataset available for download at: https://research.csiro.au/robotics/databases/synthetic-arabidopsis-dataset/