eprintid: 3482 rev_number: 6 eprint_status: archive userid: 69 dir: disk0/00/00/34/82 datestamp: 2016-05-10 09:59:13 lastmod: 2016-05-10 09:59:13 status_changed: 2016-05-10 09:59:13 type: article metadata_visibility: show creators_name: Scharr, Hanno creators_name: Minervini, Massimo creators_name: French, Andrew P. creators_name: Klukas, Christian creators_name: Kramer, David M. creators_name: Liu, Xiaoming creators_name: Luengo, Imanol creators_name: Pape, Jean-Michel creators_name: Polder, Gerrit creators_name: Vukadinovic, Danijela creators_name: Yin, Xi creators_name: Tsaftaris, Sotirios A. creators_id: creators_id: massimo.minervini@imtlucca.it creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: creators_id: sotirios.tsaftaris@imtlucca.it title: Leaf segmentation in plant phenotyping: a collation study ispublished: pub subjects: QA76 subjects: QK divisions: CSA full_text_status: none abstract: Image-based plant phenotyping is a growing application area of computer vision in agriculture. A key task is the segmentation of all individual leaves in images. Here we focus on the most common rosette model plants, Arabidopsis and young tobacco. Although leaves do share appearance and shape characteristics, the presence of occlusions and variability in leaf shape and pose, as well as imaging conditions, render this problem challenging. The aim of this paper is to compare several leaf segmentation solutions on a unique and first-of-its-kind dataset containing images from typical phenotyping experiments. In particular, we report and discuss methods and findings of a collection of submissions for the first Leaf Segmentation Challenge of the Computer Vision Problems in Plant Phenotyping workshop in 2014. Four methods are presented: three segment leaves by processing the distance transform in an unsupervised fashion, and the other via optimal template selection and Chamfer matching. Overall, we find that although separating plant from background can be accomplished with satisfactory accuracy ( $$>$$ > 90 % Dice score), individual leaf segmentation and counting remain challenging when leaves overlap. Additionally, accuracy is lower for younger leaves. We find also that variability in datasets does affect outcomes. Our findings motivate further investigations and development of specialized algorithms for this particular application, and that challenges of this form are ideally suited for advancing the state of the art. Data are publicly available (online at http://www.plant-phenotyping.org/datasets ) to support future challenges beyond segmentation within this application domain. date: 2016 date_type: published publication: Machine Vision and Applications volume: 27 number: 4 publisher: Springer pagerange: 585-606 id_number: 10.1007/s00138-015-0737-3 refereed: TRUE issn: 0932-8092 official_url: http://dx.doi.org/10.1007/s00138-015-0737-3 projects: Grant #256534 of the EU’s FP7/2007-2013 citation: Scharr, Hanno and Minervini, Massimo and French, Andrew P. and Klukas, Christian and Kramer, David M. and Liu, Xiaoming and Luengo, Imanol and Pape, Jean-Michel and Polder, Gerrit and Vukadinovic, Danijela and Yin, Xi and Tsaftaris, Sotirios A. Leaf segmentation in plant phenotyping: a collation study. Machine Vision and Applications, 27 (4). pp. 585-606. ISSN 0932-8092 (2016)