- You are here:
-
-
All publications
- CLASSIFICATION OF ALMONDS DEFECTS USING MACHINE VISION AND SUPPORT VECTOR MACHINE
All publications from your selection
CLASSIFICATION OF ALMONDS DEFECTS USING MACHINE VISION AND SUPPORT VECTOR MACHINE
Authors: HIREN SANATHARA, CHANDRA B SINGH, SANG-HEON LEE, WILMER ARIZA RAMIREZ
Identifier: CSBE22197
Download file:
Published in: CSBE-SCGAB Technical Conferences » AGM Charlottetown 2022
Download RAW file:
DOI:
Description: An algorithm was developed in MATLAB to grade Australian almonds based on 10 quality parameters namely good kernel, chip, mold, shell, shrivel, broken, split, and foreign materials (almond hull, stone and stick) using color machine vision. Images of almonds were derived and image processing techniques were used to eliminate background noise and shadow. 12 morphological, 8 color and 5 textural features (using gray level co-occurrence matrix) were derived and 500 samples of each class were used to train support vector machine (SVM) classifier. Principle component analysis (PCA) method was carried out to determine number of significant features and different 10 tests were performed using all 53 features using ‘rotating data set’. Overall accuracy of the model achieved was 95.9% and later Precision, Recall and F1-Score of the resultant model was computed.
Keywords: : Support Vector Machine (SVM), Machine Vision, Almond Quality
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2022-07-24
Technical field:
Conference name: CSBE/SCGAB 2022 Annual Conference, Charlottetow, PEI, 24-27 July 2022.
Session name: Food and Bioprocessing7
Other information:
Type: Text.Abstract
Format:
Publication type: Presentation
Source:
Relation:
Coverage: Canada
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files:
DOI:
Description: An algorithm was developed in MATLAB to grade Australian almonds based on 10 quality parameters namely good kernel, chip, mold, shell, shrivel, broken, split, and foreign materials (almond hull, stone and stick) using color machine vision. Images of almonds were derived and image processing techniques were used to eliminate background noise and shadow. 12 morphological, 8 color and 5 textural features (using gray level co-occurrence matrix) were derived and 500 samples of each class were used to train support vector machine (SVM) classifier. Principle component analysis (PCA) method was carried out to determine number of significant features and different 10 tests were performed using all 53 features using ‘rotating data set’. Overall accuracy of the model achieved was 95.9% and later Precision, Recall and F1-Score of the resultant model was computed.
Keywords: : Support Vector Machine (SVM), Machine Vision, Almond Quality
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2022-07-24
Technical field:
Conference name: CSBE/SCGAB 2022 Annual Conference, Charlottetow, PEI, 24-27 July 2022.
Session name: Food and Bioprocessing7
Other information:
Type: Text.Abstract
Format:
Publication type: Presentation
Source:
Relation:
Coverage: Canada
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files:
©
2024
CSBE-SCGAB