Assessment of Physicochemical attributes and variation in mass volume of Himalayan pears: Computer vision-based modeling

Abstract

The current study attempts to examine the physicochemical properties of Himalayan pears and envision the relationship between mass and volume with various physical properties. These properties are measured using image processing techniques at different storage days (1st day, 4th day, 7th day, 10th day, and 13th day). The study employs both single and multivariable regression models, including linear, quadratic, rational, and exponential models to establish predictive relationships. Among the single variable models, the length-based linear and rational models demonstrated exceptional suitability for envisioning the mass and volume of pears, achieving higher R2 values of 0.92 and 0.90, respectively. For mass and volume prediction considering combined physical properties, the rational and exponential models exhibited the best fit with higher R2 values of 0.94 and 0.91, accompanied by low RMSE values of 0.217 and 0.141. Consequently, the established relationship between the mass and volume of Himalayan pears with its physical attributes contributes to the development of a faster, more authentic, and accurate grading system.