Applying of Software for Nam Dok Mai Mangoes Classification Using Color Average Technique
DOI:
https://doi.org/10.14456/jare-mju.2024.54Keywords:
mango, image processing, algorithm, color intensityAbstract
The objective of this research was to develop software for sorting mangoes based on color intensity levels. The system operated by analyzing the intensity levels of the red, green, and blue components to classify mangoes by color. The system’s performance was evaluated using a newly developed algorithm tested on six sample image groups, with 10 images per group, totaling 60 images at a resolution of 640x480 pixels. The accuracy of the system was as follows: Group 1 achieved an average accuracy of 80%, Group 2 achieved 80%, Group 3 achieved 90%, Group 4 achieved 90%, Group 5 achieved 90%, and Group 6 achieved 100%. The overall average accuracy was 88.33%. The system required a camera device connected to a computer to capture images directly or to process general images through the software.
The developed system demonstrated high effectiveness, with results indicating its reliability in comparing color intensity levels. The developed algorithm exhibited high precision, consistency, and suitability for applications in mango sorting, with potential for further development in detailed color analysis.
References
Barbin, D.F., C.M. Kaminishikawahara, A.L. Soares, I.Y. Mizubuti, M. Grespan, M. Shimokomaki and E.Y. Hirooka 2015. Prediction of chicken quality attributes by near infrared spectroscopy. Food Chemistry 168: 554-560.
Benedetti, L.P.S., V.B. dos Santos, T.A. Silva, E. Benedetti-Filho, V. L.Martinsc and O. Fatibello–Filhoa. 2015. A digital image analysis method for quantification of sulfite in beverages. Analytical Methods Journal 7: 7568-7573.
Girolami, A., F. Napolitano, D. Faraone and A. Braghieri. 2013. Measurement of meat color using a computer vision system. Meat Science 93: 111-118.
Image Processing. 2012. Image display. [Online]. Avaiable http://www.italpha.msu.ac.th/Car_Park_Space_SystemAnalysis_By_ImageProcessingP.ppt (June 10, 2023).
Lakanthinwong, W. 2023. Biological ripeness index and mango wrappers. [Online]. Available https://www.technologychaoban.Com.marketing/article_62644 (June 10, 2023).
Mancini, R. and M. Hunt. 2005. Current research in meat color. Meat Science 71: 100-121.
Munklang, Y. 2012. Image retrieval using feature vectors of color cluster. [Online]. Available http://www.thaithesis.O7rg/detail.phpd=1714(May 15, 2023).
Nowak, R. 2012. Digital image processing basics. [Online]. Available http://www.cnx.org/content (May 15, 2023).
Pathare, P.B., U.L. Opara and F.A. Al-Said. 2013. Colour measurement and analysis in fresh and processed foods: a review. Food and Bioprocess Technology 6: 36-60
Sornart, N. 2012. Automatic ripeness grading of durian flesh by using color histograms and density. [Online]. Available http://www.thaithesis.org/detail.php (May 15, 2023).
Thaweepol, N. 2012. Accuracy and precission. [Online]. Availbla http://www.foodnetworksolution.com/wiki/word/4290/precision/ (June 10, 2023).
Trinderup, C.H. and Y.H.B. Kim. 2015. Fresh meat color evaluation using a structured light imaging system. Food Research International 71: 100-107.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Journal of Agricultural Research and Extension
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
This article is published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0), which allows others to share the article with proper attribution to the authors and prohibits commercial use or modification. For any other reuse or republication, permission from the journal and the authors is required.
