An intelligent system for quality measurement of Golden Bleached raisins using two comparative machine learning algorithms

Navab Karimi, Ramin Ranjbarzadeh Kondrood, Tohid Alizadeh

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this research, an expert system is provided for measuring and recognizing the quality and purity of mixed (pure-impure) raisins using bulk raisins’ images. For this purpose, by utilizing a machine vision setup 1400 images of the raisins were captured in the several ranges of mixture (from 5 to 50%). Then, totally 146 textural features were obtained using four methods of gray-level histograms, gray level co-occurrence matrix (GLCM), gray level run-length (GLRM) matrix, and local binary pattern (LBP). Principal Components Analysis (PCA) was used in order to find the optimum features from the extracted features. Accordingly, Artificial Neural Network (ANN) and Support Vector Machine (SVM) were used for classifying the mixtures. In comparison to ANN, using top 50 features, SVM classifier had more efficient and accurate classification results (averagely 92.71%). The results of the proposed approach can be used in designing a system for purity and quality measuring of raisins.

Original languageEnglish
Pages (from-to)68-76
Number of pages9
JournalMeasurement: Journal of the International Measurement Confederation
Volume107
DOIs
Publication statusPublished - Sep 1 2017

Fingerprint

machine learning
Intelligent systems
Intelligent Systems
Learning algorithms
Support vector machines
Artificial Neural Network
Learning systems
Learning Algorithm
Support Vector Machine
Machine Learning
Gray Level Co-occurrence Matrix
Neural networks
neural network
Run Length
Machine Vision
purity
Expert System
Principal component analysis
Expert systems
Histogram

Keywords

  • Artificial Neural Network
  • Bulk textures
  • Golden Bleached Raisin (GBR)
  • Image processing
  • Support Vector Machine
  • Textural features

ASJC Scopus subject areas

  • Statistics and Probability
  • Education
  • Condensed Matter Physics
  • Applied Mathematics

Cite this

@article{b79f06e48b8a40d8b8b379020283476b,
title = "An intelligent system for quality measurement of Golden Bleached raisins using two comparative machine learning algorithms",
abstract = "In this research, an expert system is provided for measuring and recognizing the quality and purity of mixed (pure-impure) raisins using bulk raisins’ images. For this purpose, by utilizing a machine vision setup 1400 images of the raisins were captured in the several ranges of mixture (from 5 to 50{\%}). Then, totally 146 textural features were obtained using four methods of gray-level histograms, gray level co-occurrence matrix (GLCM), gray level run-length (GLRM) matrix, and local binary pattern (LBP). Principal Components Analysis (PCA) was used in order to find the optimum features from the extracted features. Accordingly, Artificial Neural Network (ANN) and Support Vector Machine (SVM) were used for classifying the mixtures. In comparison to ANN, using top 50 features, SVM classifier had more efficient and accurate classification results (averagely 92.71{\%}). The results of the proposed approach can be used in designing a system for purity and quality measuring of raisins.",
keywords = "Artificial Neural Network, Bulk textures, Golden Bleached Raisin (GBR), Image processing, Support Vector Machine, Textural features",
author = "Navab Karimi and {Ranjbarzadeh Kondrood}, Ramin and Tohid Alizadeh",
year = "2017",
month = "9",
day = "1",
doi = "10.1016/j.measurement.2017.05.009",
language = "English",
volume = "107",
pages = "68--76",
journal = "Measurement",
issn = "1536-6367",
publisher = "Elsevier",

}

TY - JOUR

T1 - An intelligent system for quality measurement of Golden Bleached raisins using two comparative machine learning algorithms

AU - Karimi, Navab

AU - Ranjbarzadeh Kondrood, Ramin

AU - Alizadeh, Tohid

PY - 2017/9/1

Y1 - 2017/9/1

N2 - In this research, an expert system is provided for measuring and recognizing the quality and purity of mixed (pure-impure) raisins using bulk raisins’ images. For this purpose, by utilizing a machine vision setup 1400 images of the raisins were captured in the several ranges of mixture (from 5 to 50%). Then, totally 146 textural features were obtained using four methods of gray-level histograms, gray level co-occurrence matrix (GLCM), gray level run-length (GLRM) matrix, and local binary pattern (LBP). Principal Components Analysis (PCA) was used in order to find the optimum features from the extracted features. Accordingly, Artificial Neural Network (ANN) and Support Vector Machine (SVM) were used for classifying the mixtures. In comparison to ANN, using top 50 features, SVM classifier had more efficient and accurate classification results (averagely 92.71%). The results of the proposed approach can be used in designing a system for purity and quality measuring of raisins.

AB - In this research, an expert system is provided for measuring and recognizing the quality and purity of mixed (pure-impure) raisins using bulk raisins’ images. For this purpose, by utilizing a machine vision setup 1400 images of the raisins were captured in the several ranges of mixture (from 5 to 50%). Then, totally 146 textural features were obtained using four methods of gray-level histograms, gray level co-occurrence matrix (GLCM), gray level run-length (GLRM) matrix, and local binary pattern (LBP). Principal Components Analysis (PCA) was used in order to find the optimum features from the extracted features. Accordingly, Artificial Neural Network (ANN) and Support Vector Machine (SVM) were used for classifying the mixtures. In comparison to ANN, using top 50 features, SVM classifier had more efficient and accurate classification results (averagely 92.71%). The results of the proposed approach can be used in designing a system for purity and quality measuring of raisins.

KW - Artificial Neural Network

KW - Bulk textures

KW - Golden Bleached Raisin (GBR)

KW - Image processing

KW - Support Vector Machine

KW - Textural features

UR - http://www.scopus.com/inward/record.url?scp=85019130693&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019130693&partnerID=8YFLogxK

U2 - 10.1016/j.measurement.2017.05.009

DO - 10.1016/j.measurement.2017.05.009

M3 - Article

AN - SCOPUS:85019130693

VL - 107

SP - 68

EP - 76

JO - Measurement

JF - Measurement

SN - 1536-6367

ER -