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

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

Praveen Tripathi (SGRR University, India) and Sanjay Sharma (SGRR University, India)
Copyright: © 2022 |Pages: 13
DOI: 10.4018/978-1-6684-2443-8.ch011
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

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.
Chapter Preview
Top

Training Types And Matlab

First, this work utilizes SCG algorithm using MATLAB neural network toolbox. There are several training algorithms which have a variety of different computation and storage statistics.(Dara & Devolli, 2016) (Kumari, Dwivedi, et al., 2021) However, no algorithm found as the best suited to all application. Efforts were made to prepare a system by utilizing the SGC algorithm which is most suitable in numerical optimization techniques.(Datt et al., 2015) Detailed literature review shown that SVM based models perform much better with the accuracy from 70.006% to 71.5% when feature selection is used. SVM technique based models widely used for solving classification problems these days.(Bhatt & Pant, 2015)

Complete Chapter List

Search this Book:
Reset