Title: Coffee Grading with Convolutional Neural Networks using Small Datasets with High Variance
Authors: Wallelign, Serawork
Polceanu, Mihai
Jemal, Towfik
Buche, Cédric
Citation: Journal of WSCG. 2019, vol. 27, no. 2, p. 113-120.
Issue Date: 2019
Publisher: Václav Skala - UNION Agency
Document type: článek
URI: http://hdl.handle.net/11025/35595
ISSN: 1213-6964 (on-line)
1213-6972 (print)
1213-6980 (CD-ROM)
Keywords: CNN;hluboké učení;konvoluční neuronové sítě;souborové metody;malý dataset
Keywords in different language: CNN;deep learning;convolutional neural networks;ensemble methods;small dataset
Abstract in different language: Convolutional Neural Networks (CNNs) have been established as a powerful class of models for image recognition problems. Despite their success in other areas, CNNs have been applied only for very limited agricultural applications due to the need for large datasets. The aim of this research is to design a robust CNN model that classifies raw coffee beans into their 12 quality grades using small datasets which have high data variability. The dataset contains images of raw coffee beans acquired in two sets using different acquisition technique under varying illuminations which poses a complex challenge to designing a robust model. To design the model, preprocessing techniques were applied to the input in order to reduce task irrelevant features. But adding the preprocessing techniques did not improve the performance of the CNN model for our dataset. We have also used ensemble methods to solve the high variance that exists in networks when working with small datasets. Finally, we were able to design a model that classifies the beans into their quality grades with an accuracy of 89.01% on the test dataset.
Rights: © Václav Skala - UNION Agency
Appears in Collections:Volume 27, Number 2 (2019)

Files in This Item:
File Description SizeFormat 
Wallelign.pdfPlný text12,04 MBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/35595

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.