Automated generation of ground truth images of greenhouse-grown plant shoots using a GAN approach

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14740%2F25%3A00143307" target="_blank" >RIV/00216224:14740/25:00143307 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1186/s13007-025-01441-1" target="_blank" >https://link.springer.com/article/10.1186/s13007-025-01441-1</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1186/s13007-025-01441-1" target="_blank" >10.1186/s13007-025-01441-1</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Automated generation of ground truth images of greenhouse-grown plant shoots using a GAN approach

Popis výsledku v původním jazyce

The generation of a large amount of ground truth data is an essential bottleneck for the application of deep learning-based approaches to plant image analysis. In particular, the generation of accurately labeled images of various plant types at different developmental stages from multiple renderings is a laborious task that substantially extends the time required for AI model development and adaptation to new data. Here, generative adversarial networks (GANs) can potentially offer a solution by enabling widely automated synthesis of realistic images of plant and background structures. In this study, we present a two-stage GAN-based approach to generation of pairs of RGB and binary-segmented images of greenhouse-grown plant shoots. In the first stage, FastGAN is applied to augment original RGB images of greenhouse-grown plants using intensity and texture transformations. The augmented data were then employed as additional test sets for a Pix2Pix model trained on a limited set of 2D RGB images and their corresponding binary ground truth segmentation. This two-step approach was evaluated on unseen images of different greenhouse-grown plants. Our experimental results show that the accuracy of GAN predicted binary segmentation ranges between 0.88 and 0.95 in terms of the Dice coefficient. Among several loss functions tested, Sigmoid Loss enables the most efficient model convergence during the training achieving the highest average Dice Coefficient scores of 0.94 and 0.95 for Arabidopsis and maize images. This underscores the advantages of employing tailored loss functions for the optimization of model performance.

Název v anglickém jazyce

Automated generation of ground truth images of greenhouse-grown plant shoots using a GAN approach

Popis výsledku anglicky

The generation of a large amount of ground truth data is an essential bottleneck for the application of deep learning-based approaches to plant image analysis. In particular, the generation of accurately labeled images of various plant types at different developmental stages from multiple renderings is a laborious task that substantially extends the time required for AI model development and adaptation to new data. Here, generative adversarial networks (GANs) can potentially offer a solution by enabling widely automated synthesis of realistic images of plant and background structures. In this study, we present a two-stage GAN-based approach to generation of pairs of RGB and binary-segmented images of greenhouse-grown plant shoots. In the first stage, FastGAN is applied to augment original RGB images of greenhouse-grown plants using intensity and texture transformations. The augmented data were then employed as additional test sets for a Pix2Pix model trained on a limited set of 2D RGB images and their corresponding binary ground truth segmentation. This two-step approach was evaluated on unseen images of different greenhouse-grown plants. Our experimental results show that the accuracy of GAN predicted binary segmentation ranges between 0.88 and 0.95 in terms of the Dice coefficient. Among several loss functions tested, Sigmoid Loss enables the most efficient model convergence during the training achieving the highest average Dice Coefficient scores of 0.94 and 0.95 for Arabidopsis and maize images. This underscores the advantages of employing tailored loss functions for the optimization of model performance.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10611 - Plant sciences, botany

Projekt

<a href="/cs/project/EH22_008%2F0004581" target="_blank" >EH22_008/0004581: Nové poznatky pro plodiny nové generace</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

PLANT METHODS

ISSN

1746-4811

e-ISSN

1746-4811

Svazek periodika

21

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

14

Strana od-do

1-14

Kód UT WoS článku

001586463800001

EID výsledku v databázi Scopus

2-s2.0-105018222198