An Improved Deep Learning Application for Leaf Shape Reconstruction and Damage Estimation

Mateus Silva, Mateus Silva, Servio Ribeiro, Andrea Bianchi, Ricardo Oliveira

Abstract

Leaf damage estimation is an important research method, metric, and topic regarding both agricultural and ecological studies. The majority of previous studies that approach shape reconstruction work with parametric curves, lacking generality when treating leaves with different shapes. Other appliances try to calculate the damage without estimating the original leaf form. In this work, we propose a procedure to predict the original leaf shape and calculate its defoliation based on a Conditional Generative Adversarial Network (Conditional GAN). We trained and validated the algorithm with a dataset with leaf images from 33 different species. Also, we tested the produced model in another dataset, containing images from leaves from 153 different species. The results indicate that this model is better than the literature, and the solution potentially works with different leaf shapes, even from untrained species.

Download


Paper Citation


in Harvard Style

Silva M., Ribeiro S., Bianchi A. and Oliveira R. (2021). An Improved Deep Learning Application for Leaf Shape Reconstruction and Damage Estimation. In Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-509-8, pages 484-495. DOI: 10.5220/0010444204840495


in Bibtex Style

@conference{iceis21,
author={Mateus Silva and Servio Ribeiro and Andrea Bianchi and Ricardo Oliveira},
title={An Improved Deep Learning Application for Leaf Shape Reconstruction and Damage Estimation},
booktitle={Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2021},
pages={484-495},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010444204840495},
isbn={978-989-758-509-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - An Improved Deep Learning Application for Leaf Shape Reconstruction and Damage Estimation
SN - 978-989-758-509-8
AU - Silva M.
AU - Ribeiro S.
AU - Bianchi A.
AU - Oliveira R.
PY - 2021
SP - 484
EP - 495
DO - 10.5220/0010444204840495