Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Super-resolution Fluorescence Microscopy

Super-resolution Fluorescence Microscopy

Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Remote Sensing of Endogenous Pigmentation by Inducible Synthetic Circuits in Grasses.

Plant biotechnology journal·2025

Same author

Mutualism, herbivory, and invasive ants as seasonally dependent drivers of root surface area in a foundational savanna ant-plant.

The New phytologist·2025

Same author

Toward a general framework for AI-enabled prediction in crop improvement.

TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik·2025

Same author

Spectral ecophysiology: hyperspectral pressure-volume curves to estimate leaf turgor loss.

The New phytologist·2024

Same author

Data science competition for cross-site individual tree species identification from airborne remote sensing data.

PeerJ·2023

Same author

Jointly Optimized Spatial Histogram UNET Architecture (JOSHUA) for Adipose Tissue Segmentation.

BME frontiers·2023

Same journal

Leveraging target enrichment and genome skimming (Hyb-Seq) of herbarium collections to unlock timber DNA barcoding.

Applications in plant sciences·2026

Same journal

Detecting cryptic ghost lineage introgression in four-taxon genomic datasets.

Applications in plant sciences·2026

Same journal

HapAsmbl: A reference-aided pipeline for assembling haplotypes in Nanopore amplicon sequence data of polymorphic populations.

Applications in plant sciences·2026

Same journal

HybSuite: An integrated pipeline for hybrid capture phylogenomics from reads to trees.

Applications in plant sciences·2026

Same journal

Detecting introgression from phylogenetic invariant site patterns using machine learning.

Applications in plant sciences·2026

Same journal

tanggle: An R package for the visualization of phylogenetic networks.

Applications in plant sciences·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 12, 2025

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

Super resolution for root imaging.

Jose F Ruiz-Munoz¹, Jyothier K Nimmagadda², Tyler G Dowd³

¹Department of Electrical and Computer Engineering University of Florida Gainesville Florida USA.

Applications in Plant Sciences

|August 9, 2020

Summary

This summary is machine-generated.

Super-resolution (SR) algorithms enhance low-resolution plant root images, improving phenotyping. Deep learning models effectively boost image quality and subsequent machine learning performance for root analysis.

Keywords:

convolutional neural networks generative adversarial networks plant phenotyping root phenotyping super resolution

More Related Videos

Using Flatbed Scanners to Collect High-resolution Time-lapsed Images of the Arabidopsis Root Gravitropic Response

Using Flatbed Scanners to Collect High-resolution Time-lapsed Images of the Arabidopsis Root Gravitropic Response

Published on: January 25, 2014

Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform

Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform

Published on: August 15, 2017

Related Experiment Videos

Last Updated: Dec 12, 2025

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols

Published on: August 8, 2017

Using Flatbed Scanners to Collect High-resolution Time-lapsed Images of the Arabidopsis Root Gravitropic Response

Using Flatbed Scanners to Collect High-resolution Time-lapsed Images of the Arabidopsis Root Gravitropic Response

Published on: January 25, 2014

Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform

Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform

Published on: August 15, 2017

Area of Science:

Plant Science
Computer Vision
Machine Learning

Background:

High-resolution imaging is crucial for plant phenotyping, enabling detailed analysis of above-ground attributes.
Acquiring high-resolution images of plant roots is technically challenging compared to above-ground data.
Effective super-resolution (SR) algorithms are needed to overcome sensor limitations and improve root image analysis.

Purpose of the Study:

To develop and evaluate a super-resolution (SR) framework for enhancing low-resolution plant root images using deep learning.
To compare different training strategies for SR models, including training on non-root and root datasets.
To assess the impact of SR on the performance of subsequent machine learning tasks, such as root segmentation.

Main Methods:

Proposed an SR framework utilizing convolutional neural networks for plant root image enhancement.
Compared three training approaches: non-plant-root images, plant-root images, and pretraining/fine-tuning.
Employed state-of-the-art deep learning architectures: fast SR convolutional neural network and SR generative adversarial network.

Main Results:

SR models significantly improved the signal-to-noise ratio of low-resolution plant root images.
Demonstrated that SR models outperform basic bicubic interpolation on unseen data.
Showcased improved performance of machine learning systems for root segmentation after SR preprocessing.

Conclusions:

Deep learning-based SR models effectively enhance the quality of low-resolution plant root images.
SR preprocessing demonstrably boosts the performance of machine learning systems for root segmentation.
Achieving high segmentation performance is possible irrespective of the signal-to-noise ratio, highlighting application-specific needs for image enhancement quality.