Deep Leaf Segmentation Using Synthetic Data

Abstract

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.

Plant phenotyping relevance

植物画像から個葉を自動セグメンテーションする手法を開発・評価しており、植物表現型抽出のための方法が中心的です。

Code and data availability

The paper's authors publicly released their generated synthetic Arabidopsis dataset (10,000 top-down images with 2D segmentation labels) used for training their leaf segmentation models, hosted on the CSIRO robotics databases page. The Matterport Mask_RCNN repository is a generic third-party library, and the CodaLab L5