Author, as appears in the article.: Borraz-Martinez, Sergio; Simo, Joan; Gras, Anna; Mestre, Mariangela; Boque, Ricard; Tarres, Francesc;
Department: Química Analítica i Química Orgànica
URV's Author/s: Boqué Martí, Ricard
Keywords: Varietal mixture Nursery plant Identification Deep learning Convolutional neural network Computer vision
Abstract: Varietal control to avoid unwanted varietal mixtures is an important objective for the nursery plant industry. In this study, we have developed and analyzed the capabilities of a computer vision system based on deep learning for the control of plant varieties in the nursery plant industry and for evaluating its capabilities. For this purpose, three datasets of nursery plant images were compared. The datasets came from two varieties of almond trees (Prunus dulcis) named Soleta and Pentacebas. Each dataset contained images with three different scales: whole plant, leaf, and venation. The Gradient-weighted Class Activation Mapping (Grad-CAM) technique was used to unveil the most important features to discriminate between both varieties. The three datasets provided classification accuracies above 97% in the test set, being the leaf dataset, with a 98.8% accuracy, the one providing the best results. Concerning the most important features of the plants, the Grad-CAM showed that they are located in the center of the leaf, that is, the venation. In conclusion, we have shown that computer vision is a promising technique for the control of plant varietal mixtures.
Thematic Areas: Statistics & probability Química Mathematics, interdisciplinary applications Matemática / probabilidade e estatística Interdisciplinar Instruments & instrumentation Engenharias iv Engenharias iii Engenharias ii Computer science, artificial intelligence Ciências agrárias i Ciência da computação Chemistry, analytical Biotecnología Biodiversidade Automation & control systems Astronomia / física Applied mathematics Analytical chemistry
licence for use: https://creativecommons.org/licenses/by/3.0/es/
Author's mail: ricard.boque@urv.cat
Author identifier: 0000-0001-7311-4824
Record's date: 2024-09-07
Papper version: info:eu-repo/semantics/publishedVersion
Licence document URL: https://repositori.urv.cat/ca/proteccio-de-dades/
Papper original source: Journal Of Chemometrics. 36 (2):
APA: Borraz-Martinez, Sergio; Simo, Joan; Gras, Anna; Mestre, Mariangela; Boque, Ricard; Tarres, Francesc; (2022). Combining computer vision and deep learning to classify varieties of Prunus dulcis for the nursery plant industry. Journal Of Chemometrics, 36(2), -. DOI: 10.1002/cem.3388
Entity: Universitat Rovira i Virgili
Journal publication year: 2022
Publication Type: Journal Publications
Repositori URV