{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T01:05:59Z","timestamp":1778893559978,"version":"3.51.4"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T00:00:00Z","timestamp":1688601600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Machine learning tasks often require a significant amount of training data for the resultant network to perform suitably for a given problem in any domain. In agriculture, dataset sizes are further limited by phenotypical differences between two plants of the same genotype, often as a result of different growing conditions. Synthetically-augmented datasets have shown promise in improving existing models when real data is not available.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this paper, we employ a contrastive unpaired translation (CUT) generative adversarial network (GAN) and simple image processing techniques to translate indoor plant images to appear as field images. While we train our network to translate an image containing only a single plant, we show that our method is easily extendable to produce multiple-plant field images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Furthermore, we use our synthetic multi-plant images to train several YoloV5 nano object detection models to perform the task of plant detection and measure the accuracy of the model on real field data images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The inclusion of training data generated by the CUT-GAN leads to better plant detection performance compared to a network trained solely on real data.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2023.1200977","type":"journal-article","created":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T14:04:10Z","timestamp":1688652250000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Inside out: transforming images of lab-grown plants for machine learning applications in agriculture"],"prefix":"10.3389","volume":"6","author":[{"given":"Alexander E.","family":"Krosney","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Parsa","family":"Sotoodeh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher J.","family":"Henry","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael A.","family":"Beck","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher P.","family":"Bidinosti","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,7,6]]},"reference":[{"key":"B1","volume-title":"Unsupervised domain adaptation for object counting","author":"Ayalew","year":"2020"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3390\/rs10111690","article-title":"Deep learning with unsupervised data labeling for weed detection in line crops in UAV images","author":"Bah","year":"2018","journal-title":"Remote Sensing"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.06301","article-title":"Improved part segmentation performance by optimising realism of synthetic images using cycle generative adversarial networks","author":"Barth","year":"2018","journal-title":"arXiv preprint arXiv:1803.06301"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e0243923","DOI":"10.1371\/journal.pone.0243923","article-title":"An embedded system for the automated generation of labeled plant images to enable machine learning applications in agriculture","volume":"15","author":"Beck","year":"2020","journal-title":"PLoS ONE"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2108.05789","article-title":"Presenting an extensive lab- and field-image dataset of crops and weeds for computer vision tasks in agriculture","author":"Beck","year":"2021","journal-title":"arXiv preprint arXiv:2108.05789"},{"key":"B6","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.compag.2017.05.018","article-title":"Controlled comparison of machine vision algorithms for Rumex and Urtica detection in Grassland","volume":"140","author":"Binch","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934","article-title":"YOLOV4: optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020","journal-title":"arXiv preprint arXiv:2004.10934"},{"key":"B8","doi-asserted-by":"publisher","first-page":"2950","DOI":"10.1109\/LRA.2018.2848305","article-title":"Analysis of morphology-based features for classification of crop and weeds in precision agriculture","volume":"3","author":"Bosilj","year":"2018","journal-title":"IEEE Robot. Automat. Lett."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1258","DOI":"10.1109\/TASE.2020.3041499","article-title":"Leafgan: An effective data augmentation method for practical plant disease diagnosis","volume":"19","author":"Cap","year":"2022","journal-title":"IEEE Trans. Automat. Sci. Eng."},{"key":"B10","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (VOC) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"Int. J. Comput. Vis."},{"key":"B11","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.pbi.2015.02.006","article-title":"Lights, camera, action: high-throughput plant phenotyping is ready for a close-up","volume":"24","author":"Fahlgren","year":"2015","journal-title":"Curr. Opin. Plant Biol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"505","DOI":"10.3732\/ajb.1700044","article-title":"High-throughput phenotyping","volume":"104","author":"Gehan","year":"2017","journal-title":"Am. J. Bot."},{"key":"B13","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s13007-018-0278-7","article-title":"Citizen crowds and experts: observer variability in image-based plant phenotyping","volume":"14","author":"Giuffrida","year":"2018","journal-title":"Plant Methods"},{"key":"B14","doi-asserted-by":"crossref","first-page":"2064","DOI":"10.1109\/ICCVW.2017.242","article-title":"\u201cArigan: synthetic arabidopsis plants using generative adversarial network,\u201d","volume-title":"2017 IEEE International Conference on Computer Vision Workshops (ICCVW)","author":"Giuffrida","year":"2017"},{"key":"B15","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"B16","author":"Goodfellow","year":"2014"},{"key":"B17","doi-asserted-by":"crossref","first-page":"3202","DOI":"10.1109\/CVPR.2012.6248055","article-title":"\u201cLarge-scale knowledge transfer for object localization in imagenet,\u201d","volume-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition","author":"Guillaumin","year":"2012"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1611.07004","article-title":"Image-to-image translation with conditional adversarial networks","author":"Isola","year":"2016","journal-title":"arXiv preprint arXiv:1611.07004"},{"key":"B19","author":"Jocher","year":"2022","journal-title":"ultralytics\/yolov5: v6.1 - TensorRT, TensorFlow Edge TPU and OpenVINO Export and Inference"},{"key":"B20","doi-asserted-by":"crossref","first-page":"2580","DOI":"10.1109\/CVPRW.2019.00314","article-title":"\u201cData augmentation for leaf segmentation and counting tasks in rosette plants,\u201d","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","author":"Kuznichov","year":"2019"},{"key":"B21","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.3390\/s18082674","article-title":"Machine learning in agriculture: a review","author":"Liakos","year":"2018","journal-title":"Sensors"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014","journal-title":"arXiv preprint arXiv:1405.0312"},{"key":"B24","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1016\/j.tplants.2017.05.002","article-title":"Image analysis in plant sciences: publish then perish","volume":"22","author":"Lobet","year":"2017","journal-title":"Trends Plant Sci."},{"key":"B25","doi-asserted-by":"publisher","first-page":"107208","DOI":"10.1016\/j.compag.2022.107208","article-title":"Generative adversarial networks (GANs) for image augmentation in agriculture: a systematic review","volume":"200","author":"Lu","year":"2022","journal-title":"Comput. Electron. Agric."},{"key":"B26","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.biosystemseng.2019.09.005","article-title":"Generating artificial images of plant seedlings using generative adversarial networks","volume":"187","author":"Madsen","year":"2019","journal-title":"Biosyst. Eng."},{"key":"B27","article-title":"Contrastive learning for unpaired image-to-image translation","author":"Park","year":"2020","journal-title":"arXiv preprint arXiv:2007.15651"},{"key":"B28","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/CVPR.2016.91","article-title":"\u201cYou only look once: unified, real-time object detection,\u201d","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Redmon","year":"2016"},{"key":"B29","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.pbi.2017.05.006","article-title":"High throughput phenotyping to accelerate crop breeding and monitoring of diseases in the field","volume":"38","author":"Shakoor","year":"2017","journal-title":"Curr. Opin. Plant Biol."},{"key":"B30","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.tplants.2015.10.015","article-title":"Machine learning for high-throughput stress phenotyping in plants","volume":"21","author":"Singh","year":"2016","journal-title":"Trends Plant Sci."},{"key":"B31","doi-asserted-by":"publisher","first-page":"R770","DOI":"10.1016\/j.cub.2017.05.055","article-title":"Plant phenomics, from sensors to knowledge","volume":"27","author":"Tardieu","year":"2017","journal-title":"Curr. Biol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"e1005993","DOI":"10.1371\/journal.pcbi.1005993","article-title":"Automated plant species identification-trends and future directions","volume":"14","author":"W\u00e4ldchen","year":"2018","journal-title":"PLoS Comput. Biol."},{"key":"B33","doi-asserted-by":"publisher","first-page":"172882","DOI":"10.1109\/ACCESS.2020.3025196","article-title":"GANs-based data augmentation for citrus disease severity detection using deep learning","volume":"8","author":"Zeng","year":"2020","journal-title":"IEEE Access"},{"key":"B34","doi-asserted-by":"publisher","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","article-title":"Object detection with deep learning: a review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"B35","doi-asserted-by":"publisher","first-page":"105603","DOI":"10.1016\/j.compag.2020.105603","article-title":"Data augmentation using improved CDCGAN for plant vigor rating","volume":"175","author":"Zhu","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1703.10593","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017","journal-title":"arXiv preprint arXiv:1703.10593"},{"key":"B37","article-title":"\u201cData augmentation using conditional generative adversarial networks for leaf counting in arabidopsis plants,\u201d","volume-title":"British Machine Vision Conference","author":"Zhu","year":"2018"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1200977\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,6]],"date-time":"2023-07-06T14:04:21Z","timestamp":1688652261000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2023.1200977\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,6]]},"references-count":37,"alternative-id":["10.3389\/frai.2023.1200977"],"URL":"https:\/\/doi.org\/10.3389\/frai.2023.1200977","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,6]]},"article-number":"1200977"}}