Detection, quantification and classification of ripened tomatoes: a comparative analysis of image processing and machine learning

摘要

In this study, specifically for the detection of ripe/unripe tomatoes with/without defects in the crop field, two distinct methods are described and compared from captured images by a camera mounted on a mobile robot. One is a machine learning approach, known as 'Cascaded Object Detector' (COD) and the other is a composition of traditional customised methods, individually known as 'Colour Transformation': 'Colour Segmentation' and 'Circular Hough Transformation'. The (Viola-Jones) COD generates 'histogram of oriented gradient' (HOG) features to detect tomatoes. For ripeness checking, the RGB mean is calculated with a set of rules. However, for traditional methods, colour thresholding is applied to detect tomatoes either from natural or solid background and RGB colour is adjusted to identify ripened tomatoes. This algorithm is shown to be optimally feasible for any micro-controller based miniature electronic devices in terms of its run time complexity ofO(n(3)) for a traditional method in best and average cases. Comparisons show that the accuracy of the machine learning method is 95%, better than that of the Colour Segmentation Method using MATLAB.