{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/segmentation-of-roots-in-soil-with-u-net","title":"Segmentation of Roots in Soil with U-Net","arxiv_id":"1902.11050","date":"2019-02-28","proceeding":null,"authors":["Abraham George Smith","Jens Petersen","Raghavendra Selvan","Camilla Ruø Rasmussen"],"abstract":"Plant root research can provide a way to attain stress-tolerant crops that\nproduce greater yield in a diverse array of conditions. Phenotyping roots in\nsoil is often challenging due to the roots being difficult to access and the\nuse of time consuming manual methods. Rhizotrons allow visual inspection of\nroot growth through transparent surfaces. Agronomists currently manually label\nphotographs of roots obtained from rhizotrons using a line-intersect method to\nobtain root length density and rooting depth measurements which are essential\nfor their experiments. We investigate the effectiveness of an automated image\nsegmentation method based on the U-Net Convolutional Neural Network (CNN)\narchitecture to enable such measurements. We design a data-set of 50 annotated\nChicory (Cichorium intybus L.) root images which we use to train, validate and\ntest the system and compare against a baseline built using the Frangi\nvesselness filter. We obtain metrics using manual annotations and\nline-intersect counts. Our results on the held out data show our proposed\nautomated segmentation system to be a viable solution for detecting and\nquantifying roots. We evaluate our system using 867 images for which we have\nobtained line-intersect counts, attaining a Spearman rank correlation of 0.9748\nand an $r^2$ of 0.9217. We also achieve an $F_1$ of 0.7 when comparing the\nautomated segmentation to the manual annotations, with our automated\nsegmentation system producing segmentations with higher quality than the manual\nannotations for large portions of the image.","url_abs":"http://arxiv.org/abs/1902.11050v2","url_pdf":"http://arxiv.org/pdf/1902.11050v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"segmentation-of-roots-in-soil-with-u-net","repo_url":"https://github.com/Abe404/segmentation_of_roots_in_soil_with_unet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}