el 22(23): e4

Research Article

Recognition system for fruit classification based on 8-layer convolutional neural network

Download638 downloads
  • @ARTICLE{10.4108/eai.17-2-2022.173455,
        author={Jia-Ji Wang},
        title={Recognition system for fruit classification based on 8-layer convolutional neural network},
        journal={EAI Endorsed Transactions on e-Learning},
        volume={7},
        number={23},
        publisher={EAI},
        journal_a={EL},
        year={2022},
        month={2},
        keywords={fruit classification, deep learning, convolutional neural network, RMSProp},
        doi={10.4108/eai.17-2-2022.173455}
    }
    
  • Jia-Ji Wang
    Year: 2022
    Recognition system for fruit classification based on 8-layer convolutional neural network
    EL
    EAI
    DOI: 10.4108/eai.17-2-2022.173455
Jia-Ji Wang1,*
  • 1: School of Math and Information Technology, Jiangsu Second Normal University, Nanjing, Jiangsu 210016, P R China
*Contact email: wongjiaji@126.com

Abstract

INTRODUCTION: Automatic fruit classification is a challenging task. The types, shapes, and colors of fruits are all essential factors affecting classification.

OBJECTIVES: This paper aimed to use deep learning methods to improve the overall accuracy of fruit classification, thereby improving the sorting efficiency of the fruit factory.

METHODS: In this study, our recognition system is based on an 8-layer convolutional neural network (CNN) combined with the RMSProp optimization algorithm to classify fruits. It is verified through 10 times 10-fold crossover validation.

CONCLUSION: Our method achieves an accuracy of 91.63%, which is superior to the other four state-of-the-art methods.