Estimating Volume and Mass of Tomato Fruits by Image Processing Technique

A technique based on image processing was developed to determine volume and mass of tomato fruits. The images of different grades of tomato were attained using a digital camera. A MATLAB based algorithm was developed to enumerate and process these digital images. The geometric characteristics such as axial dimensions, mass, volume, density, sphericity, aspect ratio and ellipsoid ratio were recorded. The size of tomato varied from 30.00-77.62 mm. The bulk density was maximum (0.26 g/cc) for tomato of size 57-66 mm. The aspect ratio was higher than unity for tomatoes of all grades indicating the variation in length with respect to width. The differences between two methods were normally distributed and predictable to lie between M -1.96SD and M + 1.96SD, known as 95% limits of agreement. The paired samples t-test results showed that parameters observed with image processing method was not significantly different from the measured using vernier caliper. A linear relationship between mass of tomato and the projected area, volume and axial dimensions was also developed for calculation of mass using image processing.This information can be used to design and develop sizing systems.