Vegetable Recognition and Classification Based on Improved VGG Deep Learning Network Model

Authors

Zhenbo Li^{1, 2, 3}, Fei Li^{1, 2, 3, *,} , Ling Zhu^{1, 2}, Jun Yue⁴

¹College of Information and Electrical Engineering, China Agricultural University, No. 17 Tsinghua East Road, Haidian District, Beijing, 100083, China

²Computer Version Group, Key Laboratory of Agricultural Information Acquisition Technology, No. 17 Tsinghua East Road, Haidian District, Beijing, 100083, China

³Beijing Engineering and Technology Research Center for Internet of Things in Agriculture, No. 17 Tsinghua East Road, Haidian District, Beijing, 100083, China

⁴College of Information and Electrical Engineering, LuDong University, 186 Hongqi W Road, Zhifu District, Yantai, 264025, China

^*Corresponding author. Email: leefly072@126.com

DOI

10.2991/ijcis.d.200425.001How to use a DOI?

Keywords

Vegetable recognition and classification; Deep learning; VGG-nets; Framework of caffe

Abstract

To improve the accuracy of automatic recognition and classification of vegetables, this paper presents a method of recognition and classification of vegetable image based on deep learning, using the open source deep learning framework of Caffe, the improved VGG network model was used to train the vegetable image data set. We propose to combine the output feature of the first two fully connected layers (VGG-M). The Batch Normalization layers are added to the VGG-M network to improve the convergence speed and accuracy of the network (VGG-M-BN). The experimental verification, this paper method in the test data set on the classification of recognition accuracy rate as high as 96.5%, compared with VGG network (92.1%) and AlexNet network (86.3%), the accuracy rate has been greatly improved. At the same time, increasing the Batch Normalization layers make the network convergence speed nearly tripled. Improve the generalization ability of the model by expanding the scale of the training data set. Using VGG-M-BN network to train different number of vegetable image data sets, the experimental results show that the recognition accuracy decreases as the number of data sets decreases. By contrasting the activation functions, it is verified that the Rectified Linear Unit (ReLU) activation function is better than the traditional Sigmoid and Tanh functions in VGG-M-BN networks. The paper also verifies that the classification accuracy of VGG-M-BN network is improved due to the increase of batch_size.

Copyright

© 2020 The Authors. Published by Atlantis Press SARL.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Zhenbo Li
AU  - Fei Li
AU  - Ling Zhu
AU  - Jun Yue
PY  - 2020
DA  - 2020/06/02
TI  - Vegetable Recognition and Classification Based on Improved VGG Deep Learning Network Model
JO  - International Journal of Computational Intelligence Systems
SP  - 559
EP  - 564
VL  - 13
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.200425.001
DO  - 10.2991/ijcis.d.200425.001
ID  - Li2020
ER  -