Automatic prediction of brix and acidity in stages of ripeness of strawberries using image processing techniques

In this paper, we propose an automatic prediction system that can predict strawberry harvesting time, sugar content and acidity simultaneously. To do this, we firstly considered a segmentation algorithm using ellipsoid Hough transform that can automatically segment the real strawberry image. Second, we considered HSV color models and histogram - based color features that can be used to classify three stages of maturation of strawberries. Third, we considered the PSL model, which is a statistical analysis method that can be used to predict sugar content and acidity by stages of ripeness of strawberries. Finally, we conducted experiments using various strawberry measurement data observed in Korea's Gangwon - do Highland to evaluate the performance of the proposed prediction system. From the experimental results, it was found that the proposed prediction system can predict the harvest timing, sugar content and acidity of strawberry relatively accurately.