Super Resolution for Root Imaging

High-resolution cameras have become very helpful for plant phenotyping by providing a mechanism for tasks such as target versus background discrimination, and the measurement and analysis of fine-above-ground plant attributes. However, the acquisition of high-resolution (HR) imagery of plant roots i...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2020-05
Hauptverfasser: Ruiz-Munoz, Jose F, Nimmagadda, Jyothier K, Dowd, Tyler G, Baciak, James E, Zare, Alina
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Ruiz-Munoz, Jose F
Nimmagadda, Jyothier K
Dowd, Tyler G
Baciak, James E
Zare, Alina
description High-resolution cameras have become very helpful for plant phenotyping by providing a mechanism for tasks such as target versus background discrimination, and the measurement and analysis of fine-above-ground plant attributes. However, the acquisition of high-resolution (HR) imagery of plant roots is more challenging than above-ground data collection. Thus, an effective super-resolution (SR) algorithm is desired for overcoming resolution limitations of sensors, reducing storage space requirements, and boosting the performance of later analysis, such as automatic segmentation. We propose a SR framework for enhancing images of plant roots by using convolutional neural networks (CNNs). We compare three alternatives for training the SR model: i) training with non-plant-root images, ii) training with plant-root images, and iii) pretraining the model with non-plant-root images and fine-tuning with plant-root images. We demonstrate on a collection of publicly available datasets that the SR models outperform the basic bicubic interpolation even when trained with non-root datasets. Also, our segmentation experiments show that high performance on this task can be achieved independently of the SNR. Therefore, we conclude that the quality of the image enhancement depends on the application.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2384650130</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2384650130</sourcerecordid><originalsourceid>FETCH-proquest_journals_23846501303</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRQDC4tSC1SCEotzs8pLcnMz1NIywdy8_NLFDxzE9Mz89J5GFjTEnOKU3mhNDeDsptriLOHbkFRfmFpanFJfFZ-aVEeUCreyNjCxMzUwNDYwJg4VQAjEi1Q</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2384650130</pqid></control><display><type>article</type><title>Super Resolution for Root Imaging</title><source>Free E- Journals</source><creator>Ruiz-Munoz, Jose F ; Nimmagadda, Jyothier K ; Dowd, Tyler G ; Baciak, James E ; Zare, Alina</creator><creatorcontrib>Ruiz-Munoz, Jose F ; Nimmagadda, Jyothier K ; Dowd, Tyler G ; Baciak, James E ; Zare, Alina</creatorcontrib><description>High-resolution cameras have become very helpful for plant phenotyping by providing a mechanism for tasks such as target versus background discrimination, and the measurement and analysis of fine-above-ground plant attributes. However, the acquisition of high-resolution (HR) imagery of plant roots is more challenging than above-ground data collection. Thus, an effective super-resolution (SR) algorithm is desired for overcoming resolution limitations of sensors, reducing storage space requirements, and boosting the performance of later analysis, such as automatic segmentation. We propose a SR framework for enhancing images of plant roots by using convolutional neural networks (CNNs). We compare three alternatives for training the SR model: i) training with non-plant-root images, ii) training with plant-root images, and iii) pretraining the model with non-plant-root images and fine-tuning with plant-root images. We demonstrate on a collection of publicly available datasets that the SR models outperform the basic bicubic interpolation even when trained with non-root datasets. Also, our segmentation experiments show that high performance on this task can be achieved independently of the SNR. Therefore, we conclude that the quality of the image enhancement depends on the application.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Backscattering ; High resolution ; Image acquisition ; Image quality ; Image resolution ; Machine learning ; Neural networks ; Performance evaluation ; Plant roots ; Signal to noise ratio ; Training</subject><ispartof>arXiv.org, 2020-05</ispartof><rights>2020. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Ruiz-Munoz, Jose F</creatorcontrib><creatorcontrib>Nimmagadda, Jyothier K</creatorcontrib><creatorcontrib>Dowd, Tyler G</creatorcontrib><creatorcontrib>Baciak, James E</creatorcontrib><creatorcontrib>Zare, Alina</creatorcontrib><title>Super Resolution for Root Imaging</title><title>arXiv.org</title><description>High-resolution cameras have become very helpful for plant phenotyping by providing a mechanism for tasks such as target versus background discrimination, and the measurement and analysis of fine-above-ground plant attributes. However, the acquisition of high-resolution (HR) imagery of plant roots is more challenging than above-ground data collection. Thus, an effective super-resolution (SR) algorithm is desired for overcoming resolution limitations of sensors, reducing storage space requirements, and boosting the performance of later analysis, such as automatic segmentation. We propose a SR framework for enhancing images of plant roots by using convolutional neural networks (CNNs). We compare three alternatives for training the SR model: i) training with non-plant-root images, ii) training with plant-root images, and iii) pretraining the model with non-plant-root images and fine-tuning with plant-root images. We demonstrate on a collection of publicly available datasets that the SR models outperform the basic bicubic interpolation even when trained with non-root datasets. Also, our segmentation experiments show that high performance on this task can be achieved independently of the SNR. Therefore, we conclude that the quality of the image enhancement depends on the application.</description><subject>Artificial neural networks</subject><subject>Backscattering</subject><subject>High resolution</subject><subject>Image acquisition</subject><subject>Image quality</subject><subject>Image resolution</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Performance evaluation</subject><subject>Plant roots</subject><subject>Signal to noise ratio</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRQDC4tSC1SCEotzs8pLcnMz1NIywdy8_NLFDxzE9Mz89J5GFjTEnOKU3mhNDeDsptriLOHbkFRfmFpanFJfFZ-aVEeUCreyNjCxMzUwNDYwJg4VQAjEi1Q</recordid><startdate>20200505</startdate><enddate>20200505</enddate><creator>Ruiz-Munoz, Jose F</creator><creator>Nimmagadda, Jyothier K</creator><creator>Dowd, Tyler G</creator><creator>Baciak, James E</creator><creator>Zare, Alina</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20200505</creationdate><title>Super Resolution for Root Imaging</title><author>Ruiz-Munoz, Jose F ; Nimmagadda, Jyothier K ; Dowd, Tyler G ; Baciak, James E ; Zare, Alina</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_23846501303</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Artificial neural networks</topic><topic>Backscattering</topic><topic>High resolution</topic><topic>Image acquisition</topic><topic>Image quality</topic><topic>Image resolution</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Performance evaluation</topic><topic>Plant roots</topic><topic>Signal to noise ratio</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Ruiz-Munoz, Jose F</creatorcontrib><creatorcontrib>Nimmagadda, Jyothier K</creatorcontrib><creatorcontrib>Dowd, Tyler G</creatorcontrib><creatorcontrib>Baciak, James E</creatorcontrib><creatorcontrib>Zare, Alina</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ruiz-Munoz, Jose F</au><au>Nimmagadda, Jyothier K</au><au>Dowd, Tyler G</au><au>Baciak, James E</au><au>Zare, Alina</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Super Resolution for Root Imaging</atitle><jtitle>arXiv.org</jtitle><date>2020-05-05</date><risdate>2020</risdate><eissn>2331-8422</eissn><abstract>High-resolution cameras have become very helpful for plant phenotyping by providing a mechanism for tasks such as target versus background discrimination, and the measurement and analysis of fine-above-ground plant attributes. However, the acquisition of high-resolution (HR) imagery of plant roots is more challenging than above-ground data collection. Thus, an effective super-resolution (SR) algorithm is desired for overcoming resolution limitations of sensors, reducing storage space requirements, and boosting the performance of later analysis, such as automatic segmentation. We propose a SR framework for enhancing images of plant roots by using convolutional neural networks (CNNs). We compare three alternatives for training the SR model: i) training with non-plant-root images, ii) training with plant-root images, and iii) pretraining the model with non-plant-root images and fine-tuning with plant-root images. We demonstrate on a collection of publicly available datasets that the SR models outperform the basic bicubic interpolation even when trained with non-root datasets. Also, our segmentation experiments show that high performance on this task can be achieved independently of the SNR. Therefore, we conclude that the quality of the image enhancement depends on the application.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2020-05
issn 2331-8422
language eng
recordid cdi_proquest_journals_2384650130
source Free E- Journals
subjects Artificial neural networks
Backscattering
High resolution
Image acquisition
Image quality
Image resolution
Machine learning
Neural networks
Performance evaluation
Plant roots
Signal to noise ratio
Training
title Super Resolution for Root Imaging
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T15%3A53%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Super%20Resolution%20for%20Root%20Imaging&rft.jtitle=arXiv.org&rft.au=Ruiz-Munoz,%20Jose%20F&rft.date=2020-05-05&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2384650130%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2384650130&rft_id=info:pmid/&rfr_iscdi=true