Non-invasive measurement of soluble solid content and pH in Kyoho grapes using a computer vision technique
Abstract
A computer vision technique was used to rapidly and non-invasively assess the soluble solid content (SSC) and pH of Kyoho grapes. A total of 52 colour features were extracted from the mean and standard deviation of the pixel values considering each RGB channel, other colour space (HIS, NTSC, YCbCr, HSV and CMY) images and arithmetically calculated images. The transferred colour space images were HIS, NTSC, YCbCr, HSV, and CMY. The arithmetic images were calculated by the factors of the ratio and normalized operations between the red, green and blue channel images. Partial least-squares regression and multiple linear regression were used for model calibration. RGB colour features were proved to be the most important features for predicting the SSC and pH of grapes. The results revealed the potentiality of using computer vision as an objective and non-destructive method for the SSC and pH assessment of Kyoho grapes in a rapid and low-cost way.