Machine vision and thermographic imaging for determining of grading of tomato on postharvest

Fruits and vegetables market is subject of choice. Thus, it is important for the suppliers to supply high quality commodities to consumers in order to improve competitiveness. Some commercially available fruit sorting and grading system have been introduced, but they are almost expensive for small and medium fruit processing industry. Presently, human experts grade the agriculture goods based on its vision based features that cause the inaccuracy, in consistency and in efficiency on defining the quality of agriculture goods. Integrated of machine vision and thermographic imaging provides one alternative for an automated, non-destructive and cost-effective technique to accomplish these requirements. This study discussed the quality of tomato based on shape, color, weight, and drop injury. An edge detection algorithm was used to estimate the shape, size, and weight of tomato. Color detecting algorithm and thermographic imaging analysis algorithm were used for the ripeness and drop injury determination. Our system included smartphone, simple thermographic camera, darkroom frame, test stand and software. The results showed this system could be used to detect fruit quality. Coefficients of determination (R²) of weight and size prediction mathematical model were more than 0.8 and the accuracy rate of drop injury judgement was more than 90%. Same system can be utilized for other fruits and vegetables also.