Research on classification and recognition of fruit and vegetable based on lightweight ResNet-50

Xin Hong; LiFeng Qian; Ying Wang; Zhikai Huang; Xiaokang Yu; Xiaohua Zeng

doi:10.1117/12.2636624

8 May 2022 Research on classification and recognition of fruit and vegetable based on lightweight ResNet-50

Xin Hong, LiFeng Qian, Ying Wang, Zhikai Huang, Xiaokang Yu, Xiaohua Zeng

Proceedings Volume 12249, 2nd International Conference on Internet of Things and Smart City (IoTSC 2022）; 1224914 (2022) https://doi.org/10.1117/12.2636624
Event: 2022 2nd International Conference on Internet of Things and Smart City (IoTSC 2022）, 2022, Xiamen, China

Abstract

With the rise of smart cities, classification and identification of fruits and vegetables in unmanned supermarkets has become a hot spot in recent years. In order to improve the efficiency of fruit and vegetable classification and recognition in practical applications, this paper proposes a lightweight ResNet-50 fruit and vegetable recognition method, which integrates a deep separable convolution module into the residual module of the ResNet-50 network, which makes the classification model more lightweight, improves the recognition efficiency, and is better applied to mobile devices or in a microcomputer. At the same time, the network model is fine-tuned and optimized to ensure that the classification model still maintains a high accuracy rate after being lightweight. In the end, under the premise of ensuring high recognition precision, the recognition speed of this method is increased from 6.4s to 5.2s. Compared with the original network, the recognition speed is increased by 19.19%, and the model weight file size is reduced by 57.8%.

Citation Download Citation

Xin Hong, LiFeng Qian, Ying Wang, Zhikai Huang, Xiaokang Yu, and Xiaohua Zeng "Research on classification and recognition of fruit and vegetable based on lightweight ResNet-50", Proc. SPIE 12249, 2nd International Conference on Internet of Things and Smart City (IoTSC 2022）, 1224914 (8 May 2022); https://doi.org/10.1117/12.2636624

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Convolution

Data modeling

Classification systems

Systems modeling

Instrument modeling

Convolutional neural networks

Image classification

Show All Keywords

Keywords/Phrases

Search In:

Publication Years