An image processing and machine learning solution to automate Egyptian cotton lint grading

Egyptian cotton is one of the most important commodities for the Egyptian economy and is renowned globally for its quality, which is largely assessed and graded by manual inspection. This grading has several drawbacks, including significant labor requirements, low inspection efficiency, and influenc...

Full description

Saved in:
Bibliographic Details
Published in:Textile research journal Vol. 93; no. 11-12; pp. 2558 - 2575
Main Authors: Fisher, Oliver J, Rady, Ahmed, El-Banna, Aly AA, Watson, Nicholas J, Emaish, Haitham H
Format: Journal Article
Language:English
Published: London, England SAGE Publications 01.06.2023
Sage Publications Ltd
Subjects:
Algorithms
Artificial neural networks
cameras
Charge coupled devices
Classification
Cluster analysis
Clustering
color
Cotton
Evaluation
fabrics
Gossypium hirsutum
Human error
humans
Image processing
Inspection
Labeling
labor
Learning algorithms
lint cotton
Machine learning
Model accuracy
Neural networks
Probabilistic models
Quality assessment
Sample variance
Staples
Supervised learning
Support vector machines
Unsupervised learning
variance
Vector quantization
Industry 4.0
cotton lint
industrial crop
machine learning
Digital manufacturing
optical imaging
ISSN:0040-5175, 1746-7748, 1746-7748
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Egyptian cotton is one of the most important commodities for the Egyptian economy and is renowned globally for its quality, which is largely assessed and graded by manual inspection. This grading has several drawbacks, including significant labor requirements, low inspection efficiency, and influence from inspection conditions such as light and human subjectivity. This work proposes a low-cost solution to replace manual inspection with classification models to grade Egyptian cotton lint using images captured by a charge-coupled device camera. While this method has been evaluated for classifying US and Chinese upland cotton staples, it has not been tested on Egyptian cotton, which has unique characteristics and grading requirements. Furthermore, the methodology to develop these classification models has been expanded to include image processing techniques that remove the influence of trash on color measurements and extract features that capture the intra-sample variance of the cotton samples. Three different supervised machine learning algorithms were evaluated: artificial neural networks; random forest; and support vector machines. The highest accuracy models (82.13–90.21%) used a random forest algorithm. The models’ accuracy was limited by the human error associated with labeling the cotton samples used to develop the classification models. Unsupervised machine learning methods, including k-means clustering, hierarchical clustering, and Gaussian mixture models, were used to indicate where labeling errors occurred.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0040-5175
1746-7748
1746-7748
DOI:10.1177/00405175221145571