Pollen image manipulation and projection using latent space
Pollen image manipulation and projection using latent space
Understanding the structure of pollen grains is crucial for the identification of plant taxa and the understanding of plant evolution. We employ a deep learning technique known as style transfer to investigate the manipulation of microscope images of these pollens to change the size and shape of pollen grain images. This methodology unveils the potential to identify distinctive structural features of pollen grains and decipher correlations, whilst the ability to generate images of pollen can enhance our capacity to analyse a larger variety of pollen types, thereby broadening our understanding of plant ecology. This could potentially lead to advancements in fields such as agriculture, botany, and climate science.
deep learning, evolution, imaging, latent space, pollen
Mills, Ben
05f1886e-96ef-420f-b856-4115f4ab36d0
Zervas, Michalis N.
1840a474-dd50-4a55-ab74-6f086aa3f701
Grant-Jacob, James A.
c5d144d8-3c43-4195-8e80-edd96bfda91b
28 February 2025
Mills, Ben
05f1886e-96ef-420f-b856-4115f4ab36d0
Zervas, Michalis N.
1840a474-dd50-4a55-ab74-6f086aa3f701
Grant-Jacob, James A.
c5d144d8-3c43-4195-8e80-edd96bfda91b
Mills, Ben, Zervas, Michalis N. and Grant-Jacob, James A.
(2025)
Pollen image manipulation and projection using latent space.
Frontiers in Plant Science, 16, [1539128].
(doi:10.3389/fpls.2025.1539128).
Abstract
Understanding the structure of pollen grains is crucial for the identification of plant taxa and the understanding of plant evolution. We employ a deep learning technique known as style transfer to investigate the manipulation of microscope images of these pollens to change the size and shape of pollen grain images. This methodology unveils the potential to identify distinctive structural features of pollen grains and decipher correlations, whilst the ability to generate images of pollen can enhance our capacity to analyse a larger variety of pollen types, thereby broadening our understanding of plant ecology. This could potentially lead to advancements in fields such as agriculture, botany, and climate science.
Text
Frontiers_Plant_Science_PollenGAN_Accepted
- Accepted Manuscript
Text
fpls-1-1539128 (1)
- Version of Record
More information
Accepted/In Press date: 6 February 2025
Published date: 28 February 2025
Keywords:
deep learning, evolution, imaging, latent space, pollen
Identifiers
Local EPrints ID: 499338
URI: http://eprints.soton.ac.uk/id/eprint/499338
ISSN: 1664-462X
PURE UUID: c3b1bb06-4991-40ce-a706-059960310132
Catalogue record
Date deposited: 17 Mar 2025 17:43
Last modified: 21 Aug 2025 02:05
Export record
Altmetrics
Contributors
Author:
Ben Mills
Author:
Michalis N. Zervas
Author:
James A. Grant-Jacob
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics