Article Details

Abstract

With the rapid development of Artificial Intelligence and Computer Vision technology, image recognition has become particularly important in many fields, and the complexity and diversity of Chinese food have brought great challenges to image classification. ResNet is widely used in many fields due to its efficient information transmission capability. The existing ResNet structure may not adequately cope with the unique characteristics and complexity of Chinese food images. By studying the ResNet structure under the unified conditions, training and comparing different ResNet structures, the most suitable model for Chinese food image recognition is selected, and the network performance is further optimized. The experimental results show that the ResNet structure explored in this experiment has significant advantages in improving the classification accuracy. The research results provide a new technical path and theoretical support for the application of Chinese food image recognition.

Keywords

image recognition; ResNet; Chinese food; Neural Network; Artificial Intelligence

References

1. [1] SUBHI M A，ALI S M. A Deep Convolutional Neural Network for Food Detection and Recognition [C]//2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences(IECBES).Sarawak：IEEE，2018：284-287.
2. [2] Wu Ruoqi, Xu Bing, Qu Zhijian Asian food image classification based on feature fusion [J]. Computer Engineering and Design, 2020, 41 (12): 3464-3471
3. [3] Xu Bing Research on Asian Food Image Classification Method Based on Deep Learning [D]. Zibo: Shandong University of Technology, 2021
4. [4] LECUN Y ，BOTTOU L，BENGIO Y，et al. Gradient-based Learning Applied to Document Recognition [J].Proceedings of the IEEE，1998，86（11）：2278-2324.
5. [5] KRIZHEVSKY A，SUTSKEVER I，HINTON G E. ImageNet Classification with Deep Convolutional Neural Networks [J].Communications of the ACM，2017，60（6）：84-90.
6. [6] SIMONYAN K，ZISSERMAN A. Very Deep Convolutional Networks for Large-scale Image Recognition [J/OL].arXiv:1409.1556 [cs.CV].（2014-09-04）.https://arxiv.org/abs/1409.1556.
7. [7] SZEGEDY C，LIU W，JIA Y Q，et al. Going Deeper with Convolutions [J/OL].arXiv:1409.4842 [cs.CV].（2014-09-17）.https://arxiv.org/abs/1409.4842.
8. [8] HE K M，ZHANG X Y，REN S Q，et al. Deep Residual Learning for Image Recognition [C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas：IEEE，2016：770-778.
9. [9] Zhou Jie, Ma Mingdong Facial expression recognition based on improved ResNet network [J]. Computer Technology and Development, 2022, 32 (1): 25-29
10. [10] Zhang Wenyue, Jia Ziyan, Li Qing, etc Gastric cancer pathological image diagnosis system based on ResNet and UNet [J]. Journal of Hebei University: Natural Science Edition, 2024, 44 (4): 433-440
11. [11] Deng Hui, Zhang Jie Melanoma classification method based on improved ResNet50 network [J]. Computer Technology and Development, 2023, 33 (2): 64-70
12. [12] Xie Junbo, Gu Shibo, Xu Weilong A coaxial cable open circuit fault location method based on M-LSTM and Resnet parallel network [J]. Mechanical and Electrical Engineering Technology, 2024, 53 (6): 221-226
13. [13] Luo Fugui, Song Qian, Qin Yunchu, etc Research on the Application of Convolutional Neural Networks in Image Recognition [J]. Computer and Information Technology, 2024, 32 (3): 51-54
14. [14] OLSTON C，NAJORK M. Web Crawling [J].Foundations and Trends in Information Retrieval，2010，4（3）：175-246.

Funding

Shanghai College Students Innovation and Entrepreneurship Training Program (S202310251138)

About the authors

Shi Chenwei (2003-), male, Han ethnicity, from Shangyu, Zhejiang Province, is currently pursuing a bachelor's degree with a research focus on neural networks and deep learning.