A Shallow Convolutional Neural Network for Apple Classification

Jinquan Li,Hongwen Liu,Zhe Chen,Shanshan Xie,Zixuan Fan,Jia Kang,Wenjie Li

doi:10.1109/access.2020.3002882

Abstract

In the automatic apple sorting task, it is necessary to automatically classify certain apple species. A shallow convolutional neural network (CNN) architecture is proposed for this purpose. After collecting a certain number of apple images and labelling them, training data is obtained through a series of data augmentation operations, and then training and parameter optimization are carried out through the Caffe framework. The feasibility of the method is verified by experiments which are divided into two cases. In the case of no occlusion, the classification accuracy of apple images reaches approximately 92% in our test set. Besides, block voting is used to aid the proposed method and a good result can be achieved in our test set in the case of part occlusion caused by branches and leaves, rotten spots, and other kinds of apples. The proposed shallow network is characterized by a small number of parameters and shows resistance to overfitting with a limited dataset. Such a network presents an alternative for classification related tasks in smart visual Internet of Things and brings attention to reducing the complexity of deep neural networks while maintaining their strength.

Highlights

In the agricultural field, various agricultural applications and their degree of automation keep increasing continuously due to progress made in image recognition and classification technology
In the field of image recognition, deep learning methods have achieved countless outstanding results. It shows that the use of deep convolutional neural networks can make progress in image classification methods [15]
THE PROPOSED METHOD we describe a novel apple image classification method

Summary

INTRODUCTION

Various agricultural applications and their degree of automation keep increasing continuously due to progress made in image recognition and classification technology. In the field of image recognition, deep learning methods have achieved countless outstanding results It shows that the use of deep convolutional neural networks can make progress in image classification methods [15]. The identification of apple classification under the visual IoT is a real-time classifier for the obtained apple images from local area network-connected cameras, which further guides the robot to sort different apples and for statistical analysis. As described in this manuscript, the proposed machine learning-based classification method is characterized by fewer parameters to be trained, speeding up the training and testing procedures and holding the promise for real-time object detection, real-time visual tracking, etc.

RELATED WORK

DATASETS AND EVALUATION STANDARD

EXPERIMENTAL DESIGN

Findings

CONCLUSIONS