Article | . 2017 Vol. 35, Issue. 6
Strawberry Volume Estimation Using Smartphone Image Processing

Department of Biosystems Engineering, Chungbuk National University1
Department of Horticultural Science, Chungnam National University2

2017.. 707:716


This study was performed to estimate the volume of strawberries using changes in the regularity of seeds on the fruit surface. The pwelch function in MATLAB was applied to images of strawberries and the proposed model was validated through correlation analysis between the calculated volume and the actual volume of strawberry fruits. The volume estimation formula was also used to derive a weight estimation formula. Therefore, an important part of the experiment was to completely remove the background of images of strawberries so that only the seeds remained. The pwelch function was used to determine the periodicity of the strawberry seeds, but the remaining background affected the accuracy of results. As such, random noise and image enhancement were applied to process the images for analysis. The periodicity of the strawberry seeds was calculated for the x- and y-axes, and a positive correlation of y = 1067.9x + 8.2903 (R² = 0.8946) was established between seed periodicity and fruit volume. However, there was a negative correlation of y = −4257.7x + 42.722 (R² = 0.8346) between seed periodicity and the fruit volume. Because the two-dimensional images do not capture the threedimensionality of actual strawberries, the distance between seeds tended to become smaller towards the ends along the y-axis. The calculated volume and the actual volume were compared using correlation formulas for the x-axis, y-axis and the average of the two axes. The coefficient of determination was 0.7439 for the x-axis, 0.8662 for the y-axis and 0.6027 for the average of the two axes. While both the x- and y-axes showed a high correlation between actual volume and estimated volume, the formula in the y-axis showed a negative correlation. Thus, this study concluded that y = 1.7271x − 10.103 (R² = 0.8662) was the most suitable formula in estimating the volume of strawberries.

1. Campillo C, Prieto MH, Daza C, Monino MJ, Garcia MI (2008) Using digital images to characterize canopy coverage and light interception in a processing tomato crop. HortScience 43:1780-1786  

2. Cho NH, Chang DI, Lee SH, Hwang H, Lee YH, Park JR (2006) Development of automatic sorting system for green pepper using machine vision. J Biosyst Eng 31:514-523 (Abstr.). doi:10.5307/JBE.2006.31.6.514  

3. Costa C, Antonucci F, Pallottino F, Aguzzi J, Sun D, Menesatti P (2011) Shape analysis of agricultural products: a review of recent research advances and potential application to computer vision. Food Bioprocess Technol 4:673-692. doi:10.1007/s11947-011-0556-0  

4. Kim SU (2014) An image denoising algorithm for the mobile phone cameras. Electron Commun 9:601-608 (Abstr.). doi:10.13067/ JKIECS.  

5. Omid M, Khojastehnazhand M, Tabatabaeefar A (2010) Estimating volume and mass of citrus fruits by image processing technique. J Food Eng 100:315-321. doi: 10.1016/j.jfoodeng.2010.04.015  

6. Jung DH, Park SH, Han XZ, Kim HJ (2015) Image processing methods for measurement of lettuce fresh weight. J Biosyst Eng 40:89-93. doi:10.5307/JBE.2015.40.1.089  

7. Sayinci B, Ercisli S, Ozturk I, Eryilmaz Z, Demir B (2012) Determination of size and shape in the ‘Moro’ blood orange and ‘Valencia’ sweet orange cultivar and its mutants using image processing. Not Bot Horti Agrobot Cluj Napoca 40:234-242  

8. Xu L, Zhao Y (2010) Automated strawberry grading system based on image processing. Comput Electron Agric 71:32-39.doi:10.1016/j.compag.2009.09