Semi-Automated Ground Truth Segmentation and Phenotyping of Plant Structures Using k-Means Clustering of Eigen-Colors (kmSeg)

<b>Background</b>. Efficient analysis of large image data produced in greenhouse phenotyping experiments is often challenged by a large variability of optical plant and background appearance which requires advanced classification model methods and reliable ground truth data for their tra...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Michael Henke, Kerstin Neumann, Thomas Altmann, Evgeny Gladilin
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/8645665951a24244b33fd01dc725232f
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:8645665951a24244b33fd01dc725232f
record_format dspace
spelling oai:doaj.org-article:8645665951a24244b33fd01dc725232f2021-11-25T15:59:07ZSemi-Automated Ground Truth Segmentation and Phenotyping of Plant Structures Using k-Means Clustering of Eigen-Colors (kmSeg)10.3390/agriculture111110982077-0472https://doaj.org/article/8645665951a24244b33fd01dc725232f2021-11-01T00:00:00Zhttps://www.mdpi.com/2077-0472/11/11/1098https://doaj.org/toc/2077-0472<b>Background</b>. Efficient analysis of large image data produced in greenhouse phenotyping experiments is often challenged by a large variability of optical plant and background appearance which requires advanced classification model methods and reliable ground truth data for their training. In the absence of appropriate computational tools, generation of ground truth data has to be performed manually, which represents a time-consuming task. <b>Methods</b>. Here, we present a efficient GUI-based software solution which reduces the task of plant image segmentation to manual annotation of a small number of image regions automatically pre-segmented using k-means clustering of Eigen-colors (kmSeg). <b>Results</b>. Our experimental results show that in contrast to other supervised clustering techniques k-means enables a computationally efficient pre-segmentation of large plant images in their original resolution. Thereby, the binary segmentation of plant images in fore- and background regions is performed within a few minutes with the average accuracy of 96–99% validated by a direct comparison with ground truth data. <b>Conclusions</b>. Primarily developed for efficient ground truth segmentation and phenotyping of greenhouse-grown plants, the kmSeg tool can be applied for efficient labeling and quantitative analysis of arbitrary images exhibiting distinctive differences between colors of fore- and background structures.Michael HenkeKerstin NeumannThomas AltmannEvgeny GladilinMDPI AGarticleplant image segmentationplant phenotypingground truth data generationcolor spacesprinciple component analysisunsupervised data clusteringAgriculture (General)S1-972ENAgriculture, Vol 11, Iss 1098, p 1098 (2021)
institution DOAJ
collection DOAJ
language EN
topic plant image segmentation
plant phenotyping
ground truth data generation
color spaces
principle component analysis
unsupervised data clustering
Agriculture (General)
S1-972
spellingShingle plant image segmentation
plant phenotyping
ground truth data generation
color spaces
principle component analysis
unsupervised data clustering
Agriculture (General)
S1-972
Michael Henke
Kerstin Neumann
Thomas Altmann
Evgeny Gladilin
Semi-Automated Ground Truth Segmentation and Phenotyping of Plant Structures Using k-Means Clustering of Eigen-Colors (kmSeg)
description <b>Background</b>. Efficient analysis of large image data produced in greenhouse phenotyping experiments is often challenged by a large variability of optical plant and background appearance which requires advanced classification model methods and reliable ground truth data for their training. In the absence of appropriate computational tools, generation of ground truth data has to be performed manually, which represents a time-consuming task. <b>Methods</b>. Here, we present a efficient GUI-based software solution which reduces the task of plant image segmentation to manual annotation of a small number of image regions automatically pre-segmented using k-means clustering of Eigen-colors (kmSeg). <b>Results</b>. Our experimental results show that in contrast to other supervised clustering techniques k-means enables a computationally efficient pre-segmentation of large plant images in their original resolution. Thereby, the binary segmentation of plant images in fore- and background regions is performed within a few minutes with the average accuracy of 96–99% validated by a direct comparison with ground truth data. <b>Conclusions</b>. Primarily developed for efficient ground truth segmentation and phenotyping of greenhouse-grown plants, the kmSeg tool can be applied for efficient labeling and quantitative analysis of arbitrary images exhibiting distinctive differences between colors of fore- and background structures.
format article
author Michael Henke
Kerstin Neumann
Thomas Altmann
Evgeny Gladilin
author_facet Michael Henke
Kerstin Neumann
Thomas Altmann
Evgeny Gladilin
author_sort Michael Henke
title Semi-Automated Ground Truth Segmentation and Phenotyping of Plant Structures Using k-Means Clustering of Eigen-Colors (kmSeg)
title_short Semi-Automated Ground Truth Segmentation and Phenotyping of Plant Structures Using k-Means Clustering of Eigen-Colors (kmSeg)
title_full Semi-Automated Ground Truth Segmentation and Phenotyping of Plant Structures Using k-Means Clustering of Eigen-Colors (kmSeg)
title_fullStr Semi-Automated Ground Truth Segmentation and Phenotyping of Plant Structures Using k-Means Clustering of Eigen-Colors (kmSeg)
title_full_unstemmed Semi-Automated Ground Truth Segmentation and Phenotyping of Plant Structures Using k-Means Clustering of Eigen-Colors (kmSeg)
title_sort semi-automated ground truth segmentation and phenotyping of plant structures using k-means clustering of eigen-colors (kmseg)
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/8645665951a24244b33fd01dc725232f
work_keys_str_mv AT michaelhenke semiautomatedgroundtruthsegmentationandphenotypingofplantstructuresusingkmeansclusteringofeigencolorskmseg
AT kerstinneumann semiautomatedgroundtruthsegmentationandphenotypingofplantstructuresusingkmeansclusteringofeigencolorskmseg
AT thomasaltmann semiautomatedgroundtruthsegmentationandphenotypingofplantstructuresusingkmeansclusteringofeigencolorskmseg
AT evgenygladilin semiautomatedgroundtruthsegmentationandphenotypingofplantstructuresusingkmeansclusteringofeigencolorskmseg
_version_ 1718413390386298880