eprintid: 2744
rev_number: 9
eprint_status: archive
userid: 69
dir: disk0/00/00/27/44
datestamp: 2015-09-04 10:24:54
lastmod: 2016-05-05 13:48:56
status_changed: 2015-09-04 10:24:54
type: conference_item
metadata_visibility: show
creators_name: Giuffrida, Mario Valerio
creators_name: Minervini, Massimo
creators_name: Tsaftaris, Sotirios A.
creators_id: valerio.giuffrida@imtlucca.it
creators_id: massimo.minervini@imtlucca.it
creators_id: sotirios.tsaftaris@imtlucca.it
title: Learning to Count Leaves in Rosette Plants
ispublished: pub
subjects: QA75
divisions: CSA
full_text_status: public
pres_type: paper
abstract: Counting the number of leaves in plants is important for plant phenotyping, since it can be used to assess plant growth stages. We propose a learning-based approach for counting leaves in rosette (model) plants. We relate image-based descriptors learned in an unsupervised fashion to leaf counts using a supervised regression model. To take advantage of the circular and coplanar arrangement of leaves and also to introduce scale and rotation invariance, we learn features in a log-polar representation. Image patches extracted in this log-polar domain are provided to K-means, which builds a codebook in a unsupervised manner. Feature codes are obtained by projecting patches on the codebook using the triangle encoding, introducing both sparsity and specifically designed representation. A global, per-plant image descriptor is obtained by pooling local features in specific regions of the image. Finally, we provide the global descriptors to a support vector regression framework to estimate the number of leaves in a plant. We evaluate our method on datasets of the \textit{Leaf Counting Challenge} (LCC), containing images of Arabidopsis and tobacco plants. Experimental results show that on average we reduce absolute counting error by 40% w.r.t. the winner of the 2014 edition of the challenge -a counting via segmentation method. When compared to state-of-the-art density-based approaches to counting, on Arabidopsis image data ~75% less counting errors are observed. Our findings suggest that it is possible to treat leaf counting as a regression problem, requiring as input only the total leaf count per training image.
date: 2016-09
date_type: published
publisher: BMVA Press
pagerange: 1.1-1.13
event_title: Proceedings of the Computer Vision Problems in Plant Phenotyping (CVPPP)
event_location: Swansea, UK
event_dates: 7-10 September, 2015
event_type: conference
id_number: 10.5244/C.29.CVPPP.1
refereed: TRUE
book_title: Proceedings of the Computer Vision Problems in Plant Phenotyping (CVPPP)
official_url: http://www.bmva.org/bmvc/2015/cvppp/papers/paper001/index.html
citation:   Giuffrida, Mario Valerio and Minervini, Massimo and Tsaftaris, Sotirios A.  Learning to Count Leaves in Rosette Plants.  In: Proceedings of the Computer Vision Problems in Plant Phenotyping (CVPPP), 7-10 September, 2015, Swansea, UK 1.1-1.13.        (2016)  
document_url: http://eprints.imtlucca.it/2744/1/paper001.pdf