Neural Network Model Based on Feature Extraction and Empirical Thresholding for Mango Fruit Quality Grading

Abstract

This work supports a new feature extraction image pre-processing system followed by back propagation-artificial neural networks-based system for class categorization of mango fruit images. For back propagation, scale conjugate gradient (SCG) algorithm is used. The methodology comprises of three parts. First, various external image-based attributes of mango were taken and processed in MATLAB. Size and weight features were also considered as important parameters as only color is not sufficient to judge the quality. Second, features extraction was done at image pre-processing for making the algorithm lighter by focusing only key features. Finally, a single hidden layer BP-ANN (back propagation-artificial neural network) was used with sigmoid activation functions. The result came in terms of a suitable output variable, which is the quality class of the mango, which is chosen A, B, C, and D, respectively. It will also reduce the cost of classification or sorting of the fruits.