Apple quality identification and classification by image processing based on convolutional neural networks

Yanfei Li,Xianying Feng,Yandong Liu,Xingchang Han

doi:10.1038/s41598-021-96103-2

Yanfei Li, Xianying Feng + Show 2 more

Open Access

https://doi.org/10.1038/s41598-021-96103-2

Copy DOI

Abstract

This work researched apple quality identification and classification from real images containing complicated disturbance information (background was similar to the surface of the apples). This paper proposed a novel model based on convolutional neural networks (CNN) which aimed at accurate and fast grading of apple quality. Specific, complex, and useful image characteristics for detection and classification were captured by the proposed model. Compared with existing methods, the proposed model could better learn high-order features of two adjacent layers that were not in the same channel but were very related. The proposed model was trained and validated, with best training and validation accuracy of 99% and 98.98% at 2590th and 3000th step, respectively. The overall accuracy of the proposed model tested using an independent 300 apple dataset was 95.33%. The results showed that the training accuracy, overall test accuracy and training time of the proposed model were better than Google Inception v3 model and traditional imaging process method based on histogram of oriented gradient (HOG), gray level co-occurrence matrix (GLCM) features merging and support vector machine (SVM) classifier. The proposed model has great potential in Apple’s quality detection and classification.

Highlights

This work researched apple quality identification and classification from real images containing complicated disturbance information
The methods of parameters selection were used in a variety of ways in the literatures of training convolutional neural networks (CNN) model
A novel method based on Convolutional Neural Networks (CNN) was proposed and employed for apple quality classification containing disturbing background

Summary

Introduction

This work researched apple quality identification and classification from real images containing complicated disturbance information (background was similar to the surface of the apples). The results showed that the training accuracy, overall test accuracy and training time of the proposed model were better than Google Inception v3 model and traditional imaging process method based on histogram of oriented gradient (HOG), gray level co-occurrence matrix (GLCM) features merging and support vector machine (SVM) classifier. Bio-molecular sensing technology, hyperspectral imaging techniques, multispectral imaging, and traditional machine vision technology are effective detection methods for detecting quality fruits. Due to the rich data information, hyperspectral imaging technology has developed into the effective method for quality identification of fruit. Zhang et al.[14] proposed image recognition method to inspect damage, insect damage, bruises, decay apples by multispectral imaging with overall detection accuracy of 91.4%. The uneven brightness exists in the hyperspectral image, which still interfered with the detection of apple surface defects

Objectives

Methods

Results

Conclusion