Image recognition and nutritional assessment of dishes is a research field that has received wide attention in recent years. With the improvement of people's living standards and the demand for a healthy diet, the development of image-based dish recognition and nutritional assessment methods is therefore of great practical importance. This paper reviews the research on dish image recognition and nutritional assessment in terms of recognition types, learning methods, and nutritional assessment models and their application areas. First, this paper introduces different types of dish image recognition, including manual feature-based dish image recognition and deep feature-based image recognition. Second, this paper discusses the commonly used learning methods, including transfer learning and small sample learning. Then, this paper discusses the relationship between dish image recognition and nutritional assessment and introduces some commonly used assessment methods, such as multimodal and pre-trained RNN(Recurrent Neural Network ). Finally, this paper summarizes the application areas of dish image recognition and nutritional assessment methods, including smart catering, health management, and food safety. This paper will help researchers gain a deeper understanding of the latest advances in dish image recognition and nutritional assessment, and provide references for research and applications in related fields.

Chen Xieyu, Tang Na. A Review of Deep Learning Method for Image Recognition and Nutritional Assessment of Dishes. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 11: 40-45. https://doi.org/10.25236/AJCIS.2023.061106.

[1] Lukas Bossard, Matthieu Guillaumin, Luc Van Gool. food-101 - mining discriminative components with random forests//Proceedings of the European Conference on Computer Vision. Zurich, Switzerland, 2014: 446-461

[2] Liao Enhong, Li Huifang, Wang Hua, Pang Xiongwen. Image Recognition of Dishes Based on Convolutional Neural Networks. Journal of South China Normal University (Natural Science Edition), 2019, 51(4): 113-119

[3] Du Meijun, Ye Chunyang, Chen Dongxiao, et al. Image recognition of dishes based on texture features and multi-classification support vector machine[J]. Computer Engineering and Applications, 2017, 53(22): 130-134.

[4] Zhou, Y., Xu, X., Yang, X., & Liao, W. (2019). Deep learning-based automatic food recognition: a review. journal of food engineering, 270, 10-20. 

[5] Zhu F, Bosch M, Schap T R, et al. Segmentation assisted food classification for dietary assessment// Proceedings of the International Society for Segmentation assisted food classification for dietary assessment// Proceedings of the International Society for Optical Engineering. San Francisco, USA, 2011: 78730B

[6] Kong F, Tan J. Dietcam: Regular shape food recognition with a camera phone//Proceedings of the International Conference on Body Sensor Networks. Dallas Dallas, USA, 2011: 127-132

[7] Deng Sifan, Xie Yingli. Research on image classification algorithms based on manual features and integrated learning [J]. Computer Applications and Software, 2020, 9(6): 180-185.

[8] Wang, L., Peng, J., Huang, Q., & Jiang, S. (2018). An effective feature integration framework for image classification. IEEE Transactions on Multimedia, 20(3), 637-647.

[9] Kawano, Y., Yanai, K., & Sumiya, K. (2014). Food image recognition using deep convolutional network with pre-training and fine-tuning. In Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication (pp. 429-433).

[10] Zhao M, Wang G. Research on image recognition model based on pre-training. Electronics and Software Engineering, 2020, 9(5): 102-106.

[11] Li H, Wang C. Research on image recognition of dishes based on fine-tuning. Journal of University of Electronic Science and Technology, 2019, 46(3): 520-526.

[12] Smith, A., et al. Fine-Tuning Pretrained Convolutional Neural Networks for Food Classification. IEEE Transactions on Image Processing, 2017, 26(2): 1059-1073.

[13] Pouladzadeh P, Shirmohammadi S. Mobile multi-food recognition using deep learning. ACM Transactions on Multimedia Computing, Communications, and Applications. 2017, 13(3s): 1-21

[14] Li, H., Zhang, Z., Huang, Z., & Xian, Z. (2018). "Transfer learning for food recognition: an empirical study." Journal of Food Engineering, 218, 14-21.

[15] Deng, C., Li, Y., Yu, E., & Wu, F. (2017). "Food recognition through transfer learning with generative model." IEEE International Conference on Multimedia and Expo, 802-807.

[16] Wu, B., Shang, J., & Zhang, H. (2019). "Adaptive transfer learning for food recognition." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 450-459.

[17] Su, X., Xu, M., & Hu, W. (2018). Densely connected small sample learning for food image recognition. Journal of Visual Communication and Image Representation, 57, 231-239.

[18] Zhuang, F., Tsai, S. S., Kuo, Y. H., & Liao, H. Y. (2017). "Food recognition based on a multi-scale spatial pyramid deep network." Neurocomputing, 249, 70-78.

[19] Wang, Z., Zeng, Y., Hu, J., & Huang, G. (2020). "Few-shot food recognition via contrastive self-supervised learning." Pattern Recognition, 98, 107082.