Detection of citrus diseases using a fuzzy neural network

The objective is to use AI techniques to build a citrus image recognition system and to produce an integrated program that will assist plant protection professionals in determining whether the disease is infected and early detection for the purpose of taking the necessary preventive measures and red...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Huda Taher, Baydaa Khaleel
Formato:	article
Lenguaje:	AR EN
Publicado:	College of Education for Pure Sciences 2021
Materias:	fuzzy c-means,, ,،,؛artificial neural networks,, ,،,؛rbf,, ,،,؛feature extraction,, ,،,؛texture feature Education L Science (General) Q1-390
Acceso en línea:	https://doaj.org/article/499960532ae24e25b782095ca869f819
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:499960532ae24e25b782095ca869f819
record_format	dspace
spelling	oai:doaj.org-article:499960532ae24e25b782095ca869f8192021-12-01T14:54:26ZDetection of citrus diseases using a fuzzy neural network1812-125X2664-253010.33899/edusj.2021.130928.1179https://doaj.org/article/499960532ae24e25b782095ca869f8192021-12-01T00:00:00Zhttps://edusj.mosuljournals.com/article_169102_8b3aed4297f8b0c76e3f599c3a5fc4f0.pdfhttps://doaj.org/toc/1812-125Xhttps://doaj.org/toc/2664-2530The objective is to use AI techniques to build a citrus image recognition system and to produce an integrated program that will assist plant protection professionals in determining whether the disease is infected and early detection for the purpose of taking the necessary preventive measures and reducing its spread to other plants. In this research, the RBF and FRBF networks were used and applied to 830 images, to detect whether citrus fruits were healthy or ill. At first, the preprocessing of these images was done, and they were reduced to 250 x 250 pixels, and the features were extracted from them using the co-occurrence matrix method (GLCM) after setting the gray level at 8 gradients and 1 pixel distance, 21 statistical features were derived, and then these features were introduced to RBF after determine the number of input layer nodes by 21 , 20 for the hidden layer and 1 node for output layer, the centers were randomly selected from the training data and the weights were also randomly selected and trained using the Pseudo Inverse method. The RBF network was hybridized with the fuzzy logic using the FCM method, the fuzziness parameter = 2.3 was selected, and a new network called FRBF was acquired. These networks were trained and tested in training data (660 images) and testing (170 images) for citrus fruits. The detection rate was then calculated, and the results showed that the (FRBF) had a higher accuracy of 98.24% compared to RBF of 94.71%.Huda TaherBaydaa KhaleelCollege of Education for Pure Sciencesarticlefuzzy c-means,,,،,؛artificial neural networks,,,،,؛rbf,,,،,؛feature extraction,,,،,؛texture featureEducationLScience (General)Q1-390ARENمجلة التربية والعلم, Vol 30, Iss 5, Pp 125-135 (2021)
institution	DOAJ
collection	DOAJ
language	AR EN
topic	fuzzy c-means,, ,،,؛artificial neural networks,, ,،,؛rbf,, ,،,؛feature extraction,, ,،,؛texture feature Education L Science (General) Q1-390
spellingShingle	fuzzy c-means,, ,،,؛artificial neural networks,, ,،,؛rbf,, ,،,؛feature extraction,, ,،,؛texture feature Education L Science (General) Q1-390 Huda Taher Baydaa Khaleel Detection of citrus diseases using a fuzzy neural network
description	The objective is to use AI techniques to build a citrus image recognition system and to produce an integrated program that will assist plant protection professionals in determining whether the disease is infected and early detection for the purpose of taking the necessary preventive measures and reducing its spread to other plants. In this research, the RBF and FRBF networks were used and applied to 830 images, to detect whether citrus fruits were healthy or ill. At first, the preprocessing of these images was done, and they were reduced to 250 x 250 pixels, and the features were extracted from them using the co-occurrence matrix method (GLCM) after setting the gray level at 8 gradients and 1 pixel distance, 21 statistical features were derived, and then these features were introduced to RBF after determine the number of input layer nodes by 21 , 20 for the hidden layer and 1 node for output layer, the centers were randomly selected from the training data and the weights were also randomly selected and trained using the Pseudo Inverse method. The RBF network was hybridized with the fuzzy logic using the FCM method, the fuzziness parameter = 2.3 was selected, and a new network called FRBF was acquired. These networks were trained and tested in training data (660 images) and testing (170 images) for citrus fruits. The detection rate was then calculated, and the results showed that the (FRBF) had a higher accuracy of 98.24% compared to RBF of 94.71%.
format	article
author	Huda Taher Baydaa Khaleel
author_facet	Huda Taher Baydaa Khaleel
author_sort	Huda Taher
title	Detection of citrus diseases using a fuzzy neural network
title_short	Detection of citrus diseases using a fuzzy neural network
title_full	Detection of citrus diseases using a fuzzy neural network
title_fullStr	Detection of citrus diseases using a fuzzy neural network
title_full_unstemmed	Detection of citrus diseases using a fuzzy neural network
title_sort	detection of citrus diseases using a fuzzy neural network
publisher	College of Education for Pure Sciences
publishDate	2021
url	https://doaj.org/article/499960532ae24e25b782095ca869f819
work_keys_str_mv	AT hudataher detectionofcitrusdiseasesusingafuzzyneuralnetwork AT baydaakhaleel detectionofcitrusdiseasesusingafuzzyneuralnetwork
_version_	1718404867898212352

Detection of citrus diseases using a fuzzy neural network

Ejemplares similares