Show simple item record

dc.contributor.authorPourdarbani, Razieh
dc.contributor.authorSabzi, Sajad
dc.contributor.authorHernández Hernández, Mario
dc.contributor.authorHernández-Hernández, José Luis
dc.contributor.authorGarcía_Mateos, Ginés
dc.contributor.authorKalantari, Davood
dc.contributor.authorMolina Martínez, José Miguel
dc.creatorPourdarbani, Razieh;#0000-0003-0766-8305
dc.creatorSabzi, Sajad;#0000-0003-2439-5329
dc.creatorHernández Hernández, Mario;#0000-0001-8330-4779
dc.creatorHernández-Hernández, José Luis;#0000-0003-0231-2019
dc.creatorGarcía_Mateos, Ginés;#0000-0003-2521-4454
dc.creatorKalantari, Davood;#0000-0002-4118-2918
dc.creatorMolina Martínez, José Miguel;#0000-0001-8122-5487
dc.date.accessioned2023-03-23T16:46:54Z
dc.date.available2023-03-23T16:46:54Z
dc.date.issued2019-10
dc.identifier.issndoi:10.3390/rs11212546
dc.identifier.urihttp://ri.uagro.mx/handle/uagro/3531
dc.description.abstractColor segmentation is one of the most thoroughly studied problems in agricultural applications of remote image capture systems, since it is the key step in several different tasks, such as crop harvesting, site specific spraying, and targeted disease control under natural light. This paper studies and compares five methods to segment plum fruit images under ambient conditions at 12 different light intensities, and an ensemble method combining them. In these methods, several color features in different color spaces are first extracted for each pixel, and then the most e ective features are selected using a hybrid approach of artificial neural networks and the cultural algorithm (ANN-CA). The features selected among the 38 defined channels were the b* channel of L*a*b*, and the color purity index, C*, from L*C*h. Next, fruit/background segmentation is performed using five classifiers: artificial neural network-imperialist competitive algorithm (ANN-ICA); hybrid artificial neural network-harmony search (ANN-HS); support vector machines (SVM); k nearest neighbors (kNN); and linear discriminant analysis (LDA). In the ensemble method, the final class for each pixel is determined using the majority voting method. The experiments showed that the correct classification rate for the majority voting method excluding LDA was 98.59%, outperforming the results of the constituent methods.
dc.formatpdf
dc.language.isoeng
dc.publisherRemote Sens
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0
dc.subjectremote sensing in agriculture
dc.subjectartificial neural network hybridization
dc.subjectenvironmental conditions
dc.subjectmajority voting
dc.subjectplum segmentation
dc.subject.classificationINGENIERÍA Y TECNOLOGÍA::CIENCIAS TECNOLÓGICAS::TECNOLOGÍA DE LOS ALIMENTOS
dc.titleComparison of Different Classifiers and the Majority Voting Rule for the Detection of Plum Fruits in Garden Conditions.
dc.typeArtículo
dc.type.conacytarticle
dc.rights.accesopenAccess
dc.audiencegeneralPublic
dc.identificator7||33||3309
dc.format.digitalOriginBorn digital
dc.thesis.degreelevelDoctorado
dc.thesis.degreenameDoctorado en Innovación y Cultura Digital
dc.thesis.degreegrantorUniversidad Autónoma de Guerrero
dc.thesis.degreedepartmentFacultad de Ingeniería
dc.thesis.degreedisciplineIngeniería y Tecnología
dc.identifier.cvuagro11228


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

http://creativecommons.org/licenses/by-nc-nd/4.0
Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by-nc-nd/4.0