Computer Vision and Transfer Learning for Grading of Egyptian Cotton Fibres

Egyptian cotton fibres have worldwide recognition due to their distinct quality and luxurious textile products known by the “Egyptian Cotton“ label. However, cotton fibre trading in Egypt still depends on human grading of cotton quality, which is resource-intensive and faces challenges in terms of s...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmed Rady, Oliver Fisher, Aly A. A. El-Banna, Haitham H. Emasih, Nicholas J. Watson
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:AgriEngineering
Subjects:
Online Access:https://www.mdpi.com/2624-7402/7/5/127
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327487762300928
author Ahmed Rady
Oliver Fisher
Aly A. A. El-Banna
Haitham H. Emasih
Nicholas J. Watson
author_facet Ahmed Rady
Oliver Fisher
Aly A. A. El-Banna
Haitham H. Emasih
Nicholas J. Watson
author_sort Ahmed Rady
collection DOAJ
description Egyptian cotton fibres have worldwide recognition due to their distinct quality and luxurious textile products known by the “Egyptian Cotton“ label. However, cotton fibre trading in Egypt still depends on human grading of cotton quality, which is resource-intensive and faces challenges in terms of subjectivity and expertise requirements. This study investigates colour vision and transfer learning to classify the grade of five long (Giza 86, Giza 90, and Giza 94) and extra-long (Giza 87 and Giza 96) staple cotton cultivars. Five Convolutional Neural networks (CNNs)—AlexNet, GoogleNet, SqueezeNet, VGG16, and VGG19—were fine-tuned, optimised, and tested on independent datasets. The highest classifications were 75.7%, 85.0%, 80.0%, 77.1%, and 90.0% for Giza 86, Giza 87, Giza 90, Giza 94, and Giza 96, respectively, with F1-Scores ranging from 51.9–100%, 66.7–100%, 42.9–100%, 40.0–100%, and 80.0–100%. Among the CNNs, AlexNet, GoogleNet, and VGG19 outperformed the others. Fused CNN models further improved classification accuracy by up to 7.2% for all cultivars except Giza 87. These results demonstrate the feasibility of developing a fast, low-cost, and low-skilled vision system that overcomes the inconsistencies and limitations of manual grading in the early stages of cotton fibre trading in Egypt.
format Article
id doaj-art-51b43e7357e948599b335ebb2d716f15
institution Kabale University
issn 2624-7402
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series AgriEngineering
spelling doaj-art-51b43e7357e948599b335ebb2d716f152025-08-20T03:47:52ZengMDPI AGAgriEngineering2624-74022025-04-017512710.3390/agriengineering7050127Computer Vision and Transfer Learning for Grading of Egyptian Cotton FibresAhmed Rady0Oliver Fisher1Aly A. A. El-Banna2Haitham H. Emasih3Nicholas J. Watson4Teagasc Food Research Centre, Ashtown, D15 KN3K Dublin, IrelandFood, Water, Waste Research Group, Faculty of Engineering, University of Nottingham, Nottingham NG7 2RD, UKDepartment of Plant Production, Faculty of Agriculture, Saba Basha, Alexandria University, Alexandria 21613, EgyptDepartment of Soils and Agricultural Chemistry, Faculty of Agriculture, Saba Basha, Alexandria University, Alexandria 21613, EgyptSchool of Food Science and Nutrition, University of Leeds, Leeds LS2 9LU, UKEgyptian cotton fibres have worldwide recognition due to their distinct quality and luxurious textile products known by the “Egyptian Cotton“ label. However, cotton fibre trading in Egypt still depends on human grading of cotton quality, which is resource-intensive and faces challenges in terms of subjectivity and expertise requirements. This study investigates colour vision and transfer learning to classify the grade of five long (Giza 86, Giza 90, and Giza 94) and extra-long (Giza 87 and Giza 96) staple cotton cultivars. Five Convolutional Neural networks (CNNs)—AlexNet, GoogleNet, SqueezeNet, VGG16, and VGG19—were fine-tuned, optimised, and tested on independent datasets. The highest classifications were 75.7%, 85.0%, 80.0%, 77.1%, and 90.0% for Giza 86, Giza 87, Giza 90, Giza 94, and Giza 96, respectively, with F1-Scores ranging from 51.9–100%, 66.7–100%, 42.9–100%, 40.0–100%, and 80.0–100%. Among the CNNs, AlexNet, GoogleNet, and VGG19 outperformed the others. Fused CNN models further improved classification accuracy by up to 7.2% for all cultivars except Giza 87. These results demonstrate the feasibility of developing a fast, low-cost, and low-skilled vision system that overcomes the inconsistencies and limitations of manual grading in the early stages of cotton fibre trading in Egypt.https://www.mdpi.com/2624-7402/7/5/127Egyptian cottontransfer learningpre-trained CNNcomputer visionAlexNetGoogleNet
spellingShingle Ahmed Rady
Oliver Fisher
Aly A. A. El-Banna
Haitham H. Emasih
Nicholas J. Watson
Computer Vision and Transfer Learning for Grading of Egyptian Cotton Fibres
AgriEngineering
Egyptian cotton
transfer learning
pre-trained CNN
computer vision
AlexNet
GoogleNet
title Computer Vision and Transfer Learning for Grading of Egyptian Cotton Fibres
title_full Computer Vision and Transfer Learning for Grading of Egyptian Cotton Fibres
title_fullStr Computer Vision and Transfer Learning for Grading of Egyptian Cotton Fibres
title_full_unstemmed Computer Vision and Transfer Learning for Grading of Egyptian Cotton Fibres
title_short Computer Vision and Transfer Learning for Grading of Egyptian Cotton Fibres
title_sort computer vision and transfer learning for grading of egyptian cotton fibres
topic Egyptian cotton
transfer learning
pre-trained CNN
computer vision
AlexNet
GoogleNet
url https://www.mdpi.com/2624-7402/7/5/127
work_keys_str_mv AT ahmedrady computervisionandtransferlearningforgradingofegyptiancottonfibres
AT oliverfisher computervisionandtransferlearningforgradingofegyptiancottonfibres
AT alyaaelbanna computervisionandtransferlearningforgradingofegyptiancottonfibres
AT haithamhemasih computervisionandtransferlearningforgradingofegyptiancottonfibres
AT nicholasjwatson computervisionandtransferlearningforgradingofegyptiancottonfibres