• Ms. B. Neelima Rani
• Dr M. Sravan Kumar Reddy

Automated food recognition tools are becoming increasingly important in the medical and health fields, as they can be used to track diets, estimate calories, and more. In this research, deep learning-based automatic food classification methods were studied, using the Squeeze Net and VGG-16 convolutional neural networks. When data was added and hyperparameters were adjusted, these networks performed significantly better, making them appropriate for use in real-world health and medical applications. Squeeze Net is a lighter network that is simpler to set up, while VGG-16 achieves a respectable level of accuracy even with fewer parameters. The precision extraction of intricate elements from food photographs allows for the subsequent classification of food images. The suggested VGG-16 network enhances automatic food image classification performance much more. The accuracy of the proposed Squeeze Net has significantly improved due to the increased network depth. Squeeze Net performs better than VGG-16 in the classification of food images. Food item names are categorized with graphics to help with name recognition. Food classification, the Food 101 dataset, deep learning, transfer learning, image processing, CNN, VGG-16, and squeeze net are some of the related terms.

Food Classification, Deep Learning, Transfer Learning, Image processing, CNN, VGG-16, Squeezenet

"Food Category Prediction from Images Using CNN ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 7, page no.g171-g175, July-2023, Available :http://www.jetir.org/papers/JETIR2307626.pdf

"Food Category Prediction from Images Using CNN ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 7, page no. ppg171-g175, July-2023, Available at : http://www.jetir.org/papers/JETIR2307626.pdf