Abstract:

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 like 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 CCD (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 (SVR) has been employed and for estimation of quality from the quality attributes, Multi Attribute Decision Making (MADM) system have 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%.

Block Diagram