Sorting of tomatoes has been an issue faced by producers as well as sellers due to the sheer volumes handled and the\r\ndelicate nature of the fruit. This paper describes the development of a low cost machine vision system using webcams and\r\nimage processing algorithms for defect detection and sorting of tomatoes. In the case of agricultural products, good efforts and\r\nappropriate techniques are necessary to distinguish between defected and good ones when using machine vision for sorting.\r\nTomatoes having two major defects namely Blossom End Rot (BER) and Cracks could be separated from good tomatoes with\r\ncalyx. The sorting decision was based on three features extracted by the image processing algorithms. The color features were\r\nused for detecting the BER from good tomatoes and shape factor combined with the number of green objects was used for\r\ndifferentiating the calyxes from crack defects. Two methods, rule based and neural network approaches, were developed for\r\ndecision based sorting. A control system was developed with a belt conveyor to transport the tomatoes and a cylinder pushrod\r\ncoupled to a solenoid was used to push the defective tomatoes after determining their defect by the algorithms. The color image\r\nthreshold method with shape factor were found efficient for differentiating good and defective tomatoes. The overall accuracy\r\nof defect detection attained by the rule based approach and the neural network method were 84 and 87.5% respectively. The\r\ninspection speed of 180 tomatoes min-1 was achieved by the algorithms and the prototype developed. Comparison of the results\r\nobtained by the rule based and neural network approaches are also presented in this paper.
Loading....