- You are here:
-
-
All publications
- RGB imaging system for the identification of common bean varieties using support-vector-machine (SVM) classifier
All publications from your selection
RGB imaging system for the identification of common bean varieties using support-vector-machine (SVM) classifier
Authors: Sindhu LNU, Manickavasagan Annamalai
Identifier: CSBE21699
Download file:
Published in: CSBE-SCGAB Technical Conferences » 5th CIGR and AGM Quebec City 2021 » Regular Sessions
Download RAW file:
DOI:
Description: The objective of this research was to develop an algorithm for the identification and classification of four types of Ontario grown common beans: black turtle beans, white navy beans, red kidney beans and cranberry beans. For this purpose, 100 images were taken for four treatment combinations. Each treatment contained a total of 10 beans (mixture of different common beans) taken in a definite ratio. The images were acquired using an RGB camera (Imaging Source DFK 33UX178 with a resolution of 3072?2048, 60 frames per second). The camera was fitted on a vertical column at a height of 25 cm from the sample. The incandescent bulbs (40 Watts) were used to illuminate the samples. The watershed transformation was used to segment the images from the background. The highest value of Jaccard similarity index was 0.76 for the treatment with the combination that had more white navy beans in the mixture. In case of individual bean type, the highest Jaccard value was 0.98 for the black turtle beans mixture. The SVM classification was carried out by the Computer Vision Toolbox? functions for image category classification in MATLAB software. The SVM classifier showed an overall average accuracy of 88% and 75% for the training set and the testing set, respectively.
Keywords:
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2021-06-11
Technical field:
Conference name: 5th CIGR International Conference and CSBE-SCGAB AGM 2021, Quebec City,QC, 11-14 May 2021.
Session name: Monitoring, Control and Data Analysis 1
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: The objective of this research was to develop an algorithm for the identification and classification of four types of Ontario grown common beans: black turtle beans, white navy beans, red kidney beans and cranberry beans. For this purpose, 100 images were taken for four treatment combinations. Each treatment contained a total of 10 beans (mixture of different common beans) taken in a definite ratio. The images were acquired using an RGB camera (Imaging Source DFK 33UX178 with a resolution of 3072?2048, 60 frames per second). The camera was fitted on a vertical column at a height of 25 cm from the sample. The incandescent bulbs (40 Watts) were used to illuminate the samples. The watershed transformation was used to segment the images from the background. The highest value of Jaccard similarity index was 0.76 for the treatment with the combination that had more white navy beans in the mixture. In case of individual bean type, the highest Jaccard value was 0.98 for the black turtle beans mixture. The SVM classification was carried out by the Computer Vision Toolbox? functions for image category classification in MATLAB software. The SVM classifier showed an overall average accuracy of 88% and 75% for the training set and the testing set, respectively.
Keywords:
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2021-06-11
Technical field:
Conference name: 5th CIGR International Conference and CSBE-SCGAB AGM 2021, Quebec City,QC, 11-14 May 2021.
Session name: Monitoring, Control and Data Analysis 1
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:
©
2025
CSBE-SCGAB