An online database for plant image analysis software tools

Lobet, Guillaume; Draye, Xavier; Périlleux, Claire

doi:10.1186/1746-4811-9-38

Cited by 187 publications

(173 citation statements)

References 18 publications

Supporting

Mentioning

170

Contrasting

Unclassified

Order By: Relevance

“…The user can iteratively refine the results till the desired outcome is obtained. Our software tool and its source code are publicly available online 2,3 (as a Matlab application, listed also in the Plant Image Analysis database [20]) and will be integrated with iPlant, a web and cloud based infrastructure for plant biology.…”

Section: Resultsmentioning

confidence: 99%

An interactive tool for semi-automated leaf annotation

Minervini¹,

Giuffrida²,

Tsaftaris³

2015

Procedings of the Proceedings of the Computer Vision Problems in Plant Phenotyping Workshop 2015

View full text Add to dashboard Cite

High throughput plant phenotyping is emerging as a necessary step towards meeting agricultural demands of the future. Central to its success is the development of robust computer vision algorithms that analyze images and extract phenotyping information to be associated with genotypes and environmental conditions for identifying traits suitable for further development. Obtaining leaf level quantitative data is important towards understanding better this interaction. While certain efforts have been made to obtain such information in an automated fashion, further innovations are necessary. In this paper we present an annotation tool that can be used to semi-automatically segment leaves in images of rosette plants. This tool, which is designed to exist in a stand-alone fashion but also in cloud based environments, can be used to annotate data directly for the study of plant and leaf growth or to provide annotated datasets for learning-based approaches to extracting phenotypes from images. It relies on an interactive graph-based segmentation algorithm to propagate expert provided priors (in the form of pixels) to the rest of the image, using the random walk formulation to find a good per-leaf segmentation. To evaluate the tool we use standardized datasets available from the LSC and LCC 2015 challenges, achieving an average leaf segmentation accuracy of almost 97% using scribbles as annotations. The tool and source code are publicly available at http://www.phenotiki.com and as a GitHub repository at https://github.com/phenotiki/LeafAnnotationTool.

show abstract

Section: Resultsmentioning

confidence: 99%

An interactive tool for semi-automated leaf annotation

Minervini¹,

Giuffrida²,

Tsaftaris³

2015

Procedings of the Proceedings of the Computer Vision Problems in Plant Phenotyping Workshop 2015

View full text Add to dashboard Cite

show abstract

“…In this scenario, enhancing the genetic capacity of the plant to acquire soil resources (water and nutrients) is a primary target and can be accomplished by including the crop root system in the list of traits of interest for plant breeders (Lobet et al, 2013). From a methodological standpoint, phenotyping roots of crops is highly cost effective for evaluating hundreds of genotypes as required in QTL discovery studies (Maccaferri et al, 2016).…”

Section: Discussionmentioning

confidence: 99%

Detection of consensus genomic regions associated with root architecture of bread wheat on groups 2 and 3 chromosomes using QTL meta–analysis

Darzi-Ramandi¹,

Shariati²,

Tavakol³

et al. 2017

Aust J Crop Sci

View full text Add to dashboard Cite

Root architecture is an important bread wheat phenomenon that highly influences its production and adaptation to environmental stresses, in particular drought stress. Several QTL studies have been conducted to ascertain chromosomal regions associated with root morphology resulting in identification of various loci depending on evaluated population types and experimental conditions. In order to identify the most consistent and reliable QTLs involved in various root morphological traits in bread wheat, a meta-QTL (MQTL) analysis was performed using 106 QTLs derived from 12 different populations under both normal and drought stress conditions. Among them, 125 QTLs related to root traits were successfully projected onto the reference map and further metaanalysis was focused on chromosomes of homeologous groups 2 and 3 with most assigned QTLs. Consequently, a total of seven MQTLs were identified on chromosomes 2A, 2B, 3A and 3B originated from 2 to 17 initial QTLs with a confidence interval (CI) of 5.3-6.6 to 39.5-55.0 cM. Three MQTLs located on 2A, 3A and 3B derived from 7 to 17 QTLs related to different root morphological traits pointed out the most important chromosomal regions. A reduction in the average 95% confidence interval from 20.8 cM to 6.4 cM was observed when comparing the individual QTL to the MQTL. Further analysis on investigation of candidate genes located in these genomic regions resulted in identification of some genes mainly associated with lignin catabolic process, potassium transporters and leucine-rich repeats receptor-like kinases (LRR-RLKs). These results provid fundamental information on most important genomic regions and candidate genes related to root morphology in bread wheat.

show abstract

“…Lobet and coworkers (Lobet et al 2013) show that their database has software that performs bioimage informatics from the canopy level through leaf, root and shoot right through to cellular analysis. Algorithms range from cell wall segmentation (Roeder et al 2010) and cell tracing (Lichius et al 2013) to leaf disease identification, species identification, root network mapping and canopy coverage.…”

Section: Bioimage Informatics In the Plant Sciencesmentioning

confidence: 99%

“…Such groups aim to help collaboration and development of a wide range of high-quality tools for analysis, inference, management and prediction amongst the plant sciences. Further, online collections of bioimage informatics tools are being created to help plant scientists find the appropriate tools without having to sift through a plentitude of academic journals (Lobet et al 2013). …”

Section: Bioimage Informatics In the Plant Sciencesmentioning

confidence: 99%

Blobs and curves: object-based colocalisation for plant cells

Nelson

Duckney

Hawkins

et al. 2015

Functional Plant Biol.

View full text Add to dashboard Cite

Quantifying the colocalisation of labels is a major application of fluorescent microscopy in plant biology. Pixel-based, i.e. Pearson's coefficient, quantification of colocalisation is a limited tool that gives limited information for further analysis. We show how applying bioimage informatics tools to a commonplace experiment allows further quantifiable results to be extracted. We use our object-based colocalisation technique to extract distance information, show temporal changes and demonstrate the advantages, and pitfalls, of using bioimage informatics for plant science.

show abstract

An online database for plant image analysis software tools

Cited by 187 publications

References 18 publications

An interactive tool for semi-automated leaf annotation

An interactive tool for semi-automated leaf annotation

Detection of consensus genomic regions associated with root architecture of bread wheat on groups 2 and 3 chromosomes using QTL meta–analysis

Blobs and curves: object-based colocalisation for plant cells

Contact Info

Product

Resources

About