A Machine Vision Technique for Grading of Harvested Mangoes Based on Maturity and Quality

In agricultural and food industry, the proper grading of fruits is very important to increase the profitability. In this paper, a scheme for automated grading of mango (Mangifera Indica L.) according to maturity level in terms of actual-days-to-rot and quality attributes, such as size, shape, and surface defect has been proposed. The proposed scheme works on intelligent machine vision-based techniques for grading of mangoes in four different categories, which are determined on the basis of market distance and market value. In this system, video image is captured by a charge couple device camera placed on the top of a conveyer belt carrying mangoes, thereafter several image processing techniques are applied to collect features, which are sensitive to the maturity and quality. For maturity prediction in terms of actual-days-to-rot, support vector regression has been employed and for the estimation of quality from the quality attributes, multiattribute decision making system has been adopted. Finally, fuzzy incremental learning algorithm has been used for grading based on maturity and quality. The performance accuracy achieved using this proposed system for grading of mango fruit is nearly 87%. Moreover, the repeatability of the proposed system is found to be 100%.