Comparison of laser backscattering imaging and computer vision system for grading of seedless watermelons
- 12 Downloads
The potential of the computer vision system and backscattering imaging with a laser diode emitting at 658 nm was investigated for evaluating color changes and grading of seedless watermelons. A total of 80 seedless watermelons were selected for predicting color changes of the fruit. The watermelons were stored at 10 °C (85% RH) for 21 days with four storage days interval; Day 0, Day 8, Day 15, and Day 21. Image segmentation process and partial least squares (PLS) regression were conducted for both Red, Green, and Blue (RGB) and backscattering image analysis. Prediction models for color changes were developed based on the RGB and backscattering parameters extracted from the watermelon images. Linear discriminant analysis (LDA) was used to compare the classification models of the computer vision system and backscattering imaging based on the storage days. The results showed that the backscattering imaging classified different storage days better than computer vision system, with the classification accuracy higher than 94%. In conclusion, this work has demonstrated the ability of backscattering imaging coupled with the laser diode as a non-destructive method for color evaluation and grading of seedless watermelons.
KeywordsComputer vision Backscattering imaging Watermelons Color evaluation Grading
The authors are grateful for the support received from the Department of Biological and Agricultural Engineering, Faculty of Engineering, Universiti Putra Malaysia for providing the facilities for this study from the Ministry of Higher Education, Malaysia under a Fundamental Research Grant Scheme (FRGS) (Vot. No.: 5524604).
Compliance with ethical standards
Conflict of interest
The authors declare that no conflict of interest exists.
- 11.N. Hashim, R.B. Janius, R.A. Rahman, A. Osman, Pertanika. J. Sci. Technol. 21(1), 111–118 (2013)Google Scholar
- 21.D.L. Dénes, V. Parrag, J. Felföldi, L. Baranyai, J. Food Phys. 26, 11–16 (2013)Google Scholar
- 22.N. Hashim, R.B. Janius, R. Abdul, A. Osman, M. Shitan, M. Zude, J. Eng. Sci. Technol. 9, 314–325 (2014)Google Scholar
- 28.J.-L. Xu, D.-W. Sun, Int. J. Refrig. 74, 149–162 (2017)Google Scholar
- 30.F. Mendoza, R. Lu, D. Ariana, H. Cen, B. Bailey, Postharvest Biol. Technol. 62(2), 149–160 (2011)Google Scholar