Deep Learning-based Method for Classifying and Localizing Potato Blemishes

Sofia Marino, Pierre Beauseroy, André Smolarz

Abstract

In this paper we address the problem of potato blemish classification and localization. A large database with multiple varieties was created containing 6 classes, i.e., healthy, damaged, greening, black dot, common scab and black scurf. A Convolutional Neural Network was trained to classify face potato images and was also used as a filter to select faces where more analysis was required. Then, a combination of autoencoder and SVMs was applied on the selected images to detect damaged and greening defects in a patch-wise manner. The localization results were used to classify the potato according to the severity of the blemish. A final global evaluation of the potato was done where four face images per potato were considered to characterize the entire tuber. Experimental results show a face-wise average precision of 95% and average recall of 93%. For damaged and greening patch-wise localization, we achieve a False Positive Rate of 4.2% and 5.5% and a False Negative Rate of 14.2% and 28.1% respectively. Concerning the final potato-wise classification, we achieved in a test dataset an average precision of 92% and average recall of 91%.

Download


Paper Citation


in Harvard Style

Marino S., Beauseroy P. and Smolarz A. (2019). Deep Learning-based Method for Classifying and Localizing Potato Blemishes.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 107-117. DOI: 10.5220/0007350101070117


in Bibtex Style

@conference{icpram19,
author={Sofia Marino and Pierre Beauseroy and André Smolarz},
title={Deep Learning-based Method for Classifying and Localizing Potato Blemishes},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={107-117},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007350101070117},
isbn={978-989-758-351-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Deep Learning-based Method for Classifying and Localizing Potato Blemishes
SN - 978-989-758-351-3
AU - Marino S.
AU - Beauseroy P.
AU - Smolarz A.
PY - 2019
SP - 107
EP - 117
DO - 10.5220/0007350101070117