Evaluating CNN Models and Optimization Techniques for Quality Classification of Dried Chili Peppers (Capsicum annuum L.)

This paper analyzes Convolutional Neural Network (CNN) models for classifying dried chili pepper quality. The models categorize images into five categories: “Extra”, “First Class”, “Second Class”, “Trash”, and “Empty”, each representing different qualities and scenarios in a sorting machine. We comp...

Full description

Saved in:
Bibliographic Details
Published inInternational Journal of Combinatorial Optimization Problems and Informatics Vol. 15; no. 2; pp. 13 - 25
Main Authors Lopez-Betancur, Daniela, Saucedo-Anaya, Tonatiuh, Guerrero-Mendez, Carlos, Navarro-Solís, David, Silva-Acosta, Luis, Robles-Guerrero, Antonio, Gomez-Jimenez, Salvador
Format Journal Article
LanguageEnglish
Published Jiutepec International Journal of Combinatorial Optimization Problems & Informatics 12.06.2024
Subjects
Accuracy
Agriculture
Artificial intelligence
Artificial neural networks
Automation
Classification
Correlation coefficients
Datasets
Deep learning
Feature extraction
Food
Image quality
Informatics
Machine learning
Neural networks
Optimization algorithms
Optimization techniques
Peppers
Performance evaluation
Smartphones
Online AccessGet full text

Cover

More Information
Summary:This paper analyzes Convolutional Neural Network (CNN) models for classifying dried chili pepper quality. The models categorize images into five categories: “Extra”, “First Class”, “Second Class”, “Trash”, and “Empty”, each representing different qualities and scenarios in a sorting machine. We compared architectures from the Torchvision library, including ResNet, ResNeXt, Wide_ResNet, and RegNet using Transfer Learning (TL) in a feature extraction approach. All models employ residual blocks, an innovative technique enhancing deep learning performance. The models were evaluated using crossvalidation and metrics such as Precision, Recall, Specificity, F1-score, Geometric_mean, Index of Balanced Accuracy, and the Matthews Correlation Coefficient. They were trained using SGD, Adagrad, and Adam optimizers. Our findings suggest that ResNet-152, trained with the Adagrad optimizer, achieved the highest mean validation accuracy of 96.62%. The selected model can assist agricultural producers in classifying their products according to international standards.
ISSN:2007-1558
2007-1558
DOI:10.61467/2007.1558.2024.v15i2.462