AI-Based Plant Microscopy and Plant Phenotyping (In MOONSHOT Goal 3)
Deep learning-based analysis of plant microscopic images for stomatal, root, leaf, and growth phenotyping. A topic of MOONSHOT Goal 3.
Overview
This is a topic in MOONSHOT Goal 3 (Pioneering Science through the Creative Co-evolution of Humans and AI Robots) under the cooperation of Nagoya University and Tohoku University.
The research topic aims to extract quantitative phenotypic information from microscopic and scanner-based plant images, including stomatal morphology, root architecture, leaf structure, and plant growth.
Research Topics
- Plant image analysis
- Microscopic image analysis
- Stomatal segmentation
- Stomatal phenotype measurement
- Root detection and segmentation
- Root length measurement
- Leaf-based growth analysis
- Automated plant phenotyping
- Plant growth monitoring
- Deep learning for plant biology
Research Period
2021–2025
Collaborations
- Nagoya University
- Tohoku University
Representative Publications
- Edge-aware Deep Learning Framework for Automatic Stomatal Segmentation and Phenotype Measurement for Microscopic Image, CVMI Workshop, 2022.
- Deep Learning-based Automatic Plant Root Detection for the Measurement of Plant Root Using Images from Scanner, IAPB Congress, 2023.
- Development of a Deep Learning-Based Automatic Root Length Measurement Tool for Automated Monitoring of Plant Growth, Botanical Society of Japan, 2023.
- SMART: Stoma Measurement, Analysis, Report Tool for Microscope Image and Its Application in Plant Phenotyping, ICWAPR, 2024.
- Leaf Navigated Plant Growth Measurement for Automated Plant Cultivation System, ICWAPR, 2024.
Representative Software
- SMART: a software used to generate experimental report (with findings) from microscopy images of stomata.
- RAPID: a software used to generate experimental report (no findings) from scanner images of root.
Keywords
Plant Image Analysis, Microscopic Image Analysis, Bioimaging, Plant Phenotyping, Stomatal Analysis, Root Image Analysis, Deep Learning