Pomegranate grading based on pH using image processing and artificial intelligence

Pomegranate acidity is one of the important characteristics of this fruit because it determines its uses. By figuring out the pH of the pomegranate, the consumers can choose the fruit appropriate to their needs and tastes. In this study, the pH of 200 pomegranates was measured, and according to the properties extracted from the pomegranates' images, their pH was found to be not destructive. By processing pomegranate images and measured characteristics and using sensitivity analysis, the researchers identified four parameters that had the most effects on pH changes. The properties of pomegranate crown were also used for this purpose. With the help of three algorithms of artificial intelligence—the adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and response surface methodology (RSM)—a model was designed for the estimation of the pH of the pomegranate. The best result was obtained by the ANFIS model, in which the R2 and MSE values were equal to 0.984 and 0.202.