Image Harvest: An open-source platform for high-throughput plant image processing and analysis

Avi C. Knecht, Malachy T. Campbell, Adam Caprez, David R. Swanson, Harkamal Walia

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

High-throughput plant phenotyping is an effective approach to bridge the genotype-to-phenotype gap in crops. Phenomics experiments typically result in large-scale image datasets, which are not amenable for processing on desktop computers, thus creating a bottleneck in the image-analysis pipeline. Here, we present an open-source, flexible image-analysis framework, called Image Harvest (IH), for processing images originating from high-throughput plant phenotyping platforms. Image Harvest is developed to perform parallel processing on computing grids and provides an integrated feature for metadata extraction from large-scale file organization. Moreover, the integration of IH with the Open Science Grid provides academic researchers with the computational resources required for processing large image datasets at no cost. Image Harvest also offers functionalities to extract digital traits from images to interpret plant architecture-related characteristics. To demonstrate the applications of these digital traits, a rice (Oryza sativa) diversity panel was phenotyped and genome-wide association mapping was performed using digital traits that are used to describe different plant ideotypes. Three major quantitative trait loci were identified on rice chromosomes 4 and 6, which co-localize with quantitative trait loci known to regulate agronomically important traits in rice. Image Harvest is an open-source software for high-throughput image processing that requires a minimal learning curve for plant biologists to analyzephenomics datasets.

Original languageEnglish (US)
Pages (from-to)3587-3599
Number of pages13
JournalJournal of experimental botany
Volume67
Issue number11
DOIs
StatePublished - May 28 2016

Fingerprint

image analysis
phenotype
rice
Quantitative Trait Loci
quantitative trait loci
ideotypes
plant architecture
Chromosomes, Human, Pair 4
Chromosomes, Human, Pair 6
Learning Curve
chromosome mapping
biologists
Oryza sativa
learning
researchers
chromosomes
Software
Genotype
genome
Research Personnel

Keywords

  • High throughput computing
  • Open Science Grid
  • OpenCV
  • image analysis
  • image processing
  • large-scale biology
  • open-source software
  • phenomics

ASJC Scopus subject areas

  • Physiology
  • Plant Science

Cite this

Image Harvest : An open-source platform for high-throughput plant image processing and analysis. / Knecht, Avi C.; Campbell, Malachy T.; Caprez, Adam; Swanson, David R.; Walia, Harkamal.

In: Journal of experimental botany, Vol. 67, No. 11, 28.05.2016, p. 3587-3599.

Research output: Contribution to journalArticle

Knecht, Avi C. ; Campbell, Malachy T. ; Caprez, Adam ; Swanson, David R. ; Walia, Harkamal. / Image Harvest : An open-source platform for high-throughput plant image processing and analysis. In: Journal of experimental botany. 2016 ; Vol. 67, No. 11. pp. 3587-3599.
@article{69db6f03c66845b788e39acbc8b0f147,
title = "Image Harvest: An open-source platform for high-throughput plant image processing and analysis",
abstract = "High-throughput plant phenotyping is an effective approach to bridge the genotype-to-phenotype gap in crops. Phenomics experiments typically result in large-scale image datasets, which are not amenable for processing on desktop computers, thus creating a bottleneck in the image-analysis pipeline. Here, we present an open-source, flexible image-analysis framework, called Image Harvest (IH), for processing images originating from high-throughput plant phenotyping platforms. Image Harvest is developed to perform parallel processing on computing grids and provides an integrated feature for metadata extraction from large-scale file organization. Moreover, the integration of IH with the Open Science Grid provides academic researchers with the computational resources required for processing large image datasets at no cost. Image Harvest also offers functionalities to extract digital traits from images to interpret plant architecture-related characteristics. To demonstrate the applications of these digital traits, a rice (Oryza sativa) diversity panel was phenotyped and genome-wide association mapping was performed using digital traits that are used to describe different plant ideotypes. Three major quantitative trait loci were identified on rice chromosomes 4 and 6, which co-localize with quantitative trait loci known to regulate agronomically important traits in rice. Image Harvest is an open-source software for high-throughput image processing that requires a minimal learning curve for plant biologists to analyzephenomics datasets.",
keywords = "High throughput computing, Open Science Grid, OpenCV, image analysis, image processing, large-scale biology, open-source software, phenomics",
author = "Knecht, {Avi C.} and Campbell, {Malachy T.} and Adam Caprez and Swanson, {David R.} and Harkamal Walia",
year = "2016",
month = "5",
day = "28",
doi = "10.1093/jxb/erw176",
language = "English (US)",
volume = "67",
pages = "3587--3599",
journal = "Journal of Experimental Botany",
issn = "0022-0957",
publisher = "Oxford University Press",
number = "11",

}

TY - JOUR

T1 - Image Harvest

T2 - An open-source platform for high-throughput plant image processing and analysis

AU - Knecht, Avi C.

AU - Campbell, Malachy T.

AU - Caprez, Adam

AU - Swanson, David R.

AU - Walia, Harkamal

PY - 2016/5/28

Y1 - 2016/5/28

N2 - High-throughput plant phenotyping is an effective approach to bridge the genotype-to-phenotype gap in crops. Phenomics experiments typically result in large-scale image datasets, which are not amenable for processing on desktop computers, thus creating a bottleneck in the image-analysis pipeline. Here, we present an open-source, flexible image-analysis framework, called Image Harvest (IH), for processing images originating from high-throughput plant phenotyping platforms. Image Harvest is developed to perform parallel processing on computing grids and provides an integrated feature for metadata extraction from large-scale file organization. Moreover, the integration of IH with the Open Science Grid provides academic researchers with the computational resources required for processing large image datasets at no cost. Image Harvest also offers functionalities to extract digital traits from images to interpret plant architecture-related characteristics. To demonstrate the applications of these digital traits, a rice (Oryza sativa) diversity panel was phenotyped and genome-wide association mapping was performed using digital traits that are used to describe different plant ideotypes. Three major quantitative trait loci were identified on rice chromosomes 4 and 6, which co-localize with quantitative trait loci known to regulate agronomically important traits in rice. Image Harvest is an open-source software for high-throughput image processing that requires a minimal learning curve for plant biologists to analyzephenomics datasets.

AB - High-throughput plant phenotyping is an effective approach to bridge the genotype-to-phenotype gap in crops. Phenomics experiments typically result in large-scale image datasets, which are not amenable for processing on desktop computers, thus creating a bottleneck in the image-analysis pipeline. Here, we present an open-source, flexible image-analysis framework, called Image Harvest (IH), for processing images originating from high-throughput plant phenotyping platforms. Image Harvest is developed to perform parallel processing on computing grids and provides an integrated feature for metadata extraction from large-scale file organization. Moreover, the integration of IH with the Open Science Grid provides academic researchers with the computational resources required for processing large image datasets at no cost. Image Harvest also offers functionalities to extract digital traits from images to interpret plant architecture-related characteristics. To demonstrate the applications of these digital traits, a rice (Oryza sativa) diversity panel was phenotyped and genome-wide association mapping was performed using digital traits that are used to describe different plant ideotypes. Three major quantitative trait loci were identified on rice chromosomes 4 and 6, which co-localize with quantitative trait loci known to regulate agronomically important traits in rice. Image Harvest is an open-source software for high-throughput image processing that requires a minimal learning curve for plant biologists to analyzephenomics datasets.

KW - High throughput computing

KW - Open Science Grid

KW - OpenCV

KW - image analysis

KW - image processing

KW - large-scale biology

KW - open-source software

KW - phenomics

UR - http://www.scopus.com/inward/record.url?scp=84973580319&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973580319&partnerID=8YFLogxK

U2 - 10.1093/jxb/erw176

DO - 10.1093/jxb/erw176

M3 - Article

C2 - 27141917

AN - SCOPUS:84973580319

VL - 67

SP - 3587

EP - 3599

JO - Journal of Experimental Botany

JF - Journal of Experimental Botany

SN - 0022-0957

IS - 11

ER -