Skip to Main content Skip to Navigation
Conference papers

Deep Learning-based Method for Classifying and Localizing Potato Blemishes

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%.
Document type :
Conference papers
Complete list of metadatas
Contributor : Jean-Baptiste Vu Van <>
Submitted on : Monday, October 7, 2019 - 4:37:20 PM
Last modification on : Tuesday, December 1, 2020 - 6:36:01 PM

Links full text





Sofia Marino, Pierre Beauseroy, André Smolarz. Deep Learning-based Method for Classifying and Localizing Potato Blemishes. 8th International Conference on Pattern Recognition Applications and Methods, Feb 2019, Prague, Czech Republic. pp.107-117, ⟨10.5220/0007350101070117⟩. ⟨hal-02307540⟩



Record views