Home / Current Issue / Paper 1715946
Nutrient Net: A Multi-Layered Deep Learning Approach for Calorie and Macro nutrient Estimation from Food Images
Subject area: Science,Engineering and Technology · Area of research: Deep Learning and Health Informatics
DOI: 10.64388/IREV9I10-1715946
Abstract
In order to preserve our dieting habits and lead a healthy lifestyle, it is necessary to calculate the value of calorie content and macro-nutrient(protein, fat, carbohydrates) value of food. For monitoring our daily food consumption, there are some other methods available homemade systems, but sometimes these methods are not very efficient and often result in errors as it takes a lot of time to accomplish the task. To resolve the above-mentioned problem, our advanced approach is Nutrient Net, which is a system used to predict the total calorie content and macro-nutrient content of the food item from the image using a multi-layered deep learning technique. To classify and calculate the food item, this system uses Convolution Neural Networks (CNN). CNN is a deep learning technique which is specifically designed for images, it scans the food image and easily identifies the food item(for example: rice, pizza, apple, etc.) After identifying the food item, Long Short-Term Memory (LSTM) network assists to calculate the portion size(how much food) and nutrient contents(protein, fat, carbohydrate, etc.) of the food item. This app supports both real-time images and saved images from the gallery. Once the food item has been identified, the Nutrient Net System provides information about each food item. With the help of this, we can manage our diet and food habits effectively.
Keywords
Nutrient Net, Deep Learning, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM), Food Image Classification, Portion Size Estimation, , Nutritional Analysis.
References
[1] Guorui Sheng,Weiqing Min,Tao Yao,Jingru Song,Yancun Yang,Lili Wang:Lightweight Food Image Recognition With Global Shuffle Convolution IEEE Transactions on AgriFood Electronics, Vol. 2,pp.392-402, Sept.-Oct. 2024doi: 10.1109/TAFE.2024.3386713.
[2] R. Sombutkaew and O. Chitsobhuk, “Image-based Thai Food Recognition and Calorie Estimation using Machine Learning Techniques,” in Proc. 2023 20th Int. Conf. Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), 2023, pp. 1–4, doi: 10.1109/ECTI-CON58255.2023.10153183.
[3] N. Anggraeni, K. Wanito Wigati, I. L. Wardani, and L. Herawati, “Deep Learning Food Detection and Calories Counter,” in Proc. 2023,IEEEInt.Conf.Computing(ICOCO),2023,doi:10.1109/ICOCO59262.2023.10397620.
[4] R. P. Guru, M. Ayyadurai, T. M. Amirthalakshmi, R. Neelaven, and K. Sujatha, “Calorie Recognition from Food Images Using CNN for Nutritional Analysis,” in Proc. 2023 International Conference on Data Science, Agents and Artificial Intelligence (ICDSAAI), 2023, pp. 2023–2026, doi: 10.1109/ICDSAAI59313.2023.10452481.
[5] E. D. Cherpanath, P. R. Fathima Nasreen, K. Pradeep, M. Menon and V. S. Jayanthi, “Food Image Recognition and Calorie Prediction Using Faster R-CNN and Mask R-CNN,” in Proc. 2023 9th Int. Conf. Smart Computing and Communications (ICSCC), Kochi, Kerala, India, 2023, pp. 83–89, doi: 10.1109/ICSCC59169.2023.10335053.
[6] S. A. Ayon, C. Z. Mashrafi, A. B. Yousuf, F. Hossain, and M. I. Hossain, “FoodieCal: A Convolutional Neural Network Based Food Detection and Calorie Estimation System,” in 2021 National Computing Colleges Conference (NCCC), 2021, pp. 16,doi:10.1109/NCCC49330.2021.9428820.
[7] V. Balaji Kasyap and N. Jayapandian, “Food calorie estimation using convolutional neural network,” in Proc. 2021 3rd International Conference on Signal Processing and Communication (ICSPC), 2021, pp. 666–670, doi: 10.1109/ICSPC51351.2021.9451812.
[8] G. Ramkumar, C. B. Venkatramanan, V. Manonmani, S. Palanivel, N. Sakthisaravanan, and A. K. Kumar, “A Real-time Food Image Recognition System to Predict the Calories by Using Intelligent Deep Learning Strategy,” in Proc. 2023 International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE), Chennai, India, 1–2 Nov. 2023, pp. 1–7, doi: 10.1109/RMKMATE58058.2023.10369431.
[9] T. Ege, Y. Ando, R. Tanno, W. Shimoda, and K. Yanai, “Image-Based Estimation of Real Food Size for Accurate Food Calorie Estimation,” in Proc. 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 2019, pp. 274–279, doi:10.1109/MIPR.2019.00056.
[10] Rewane, R. and Chouragade, P. M., “Food Recognition and Health Monitoring System for Recommending Daily Calorie Intake,” in Proc. 2019 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT), 2019, pp. 1–5, doi: 10.1109/ICECCT.2019.8869088.
How to cite this paper
@article{1715946,
author = {Canosa R Krucy, Enugula Vyshnavi},
title = {Nutrient Net: A Multi-Layered Deep Learning Approach for Calorie and Macro nutrient Estimation from Food Images },
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {10},
pages = {301-309},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1715946.pdf},
abstract = {In order to preserve our dieting habits and lead a healthy lifestyle, it is necessary to calculate the value of calorie content and macro-nutrient(protein, fat, carbohydrates) value of food. For monitoring our daily food consumption, there are some other methods available homemade systems, but sometimes these methods are not very efficient and often result in errors as it takes a lot of time to accomplish the task. To resolve the above-mentioned problem, our advanced approach is Nutrient Net, which is a system used to predict the total calorie content and macro-nutrient content of the food item from the image using a multi-layered deep learning technique. To classify and calculate the food item, this system uses Convolution Neural Networks (CNN). CNN is a deep learning technique which is specifically designed for images, it scans the food image and easily identifies the food item(for example: rice, pizza, apple, etc.) After identifying the food item, Long Short-Term Memory (LSTM) network assists to calculate the portion size(how much food) and nutrient contents(protein, fat, carbohydrate, etc.) of the food item. This app supports both real-time images and saved images from the gallery. Once the food item has been identified, the Nutrient Net System provides information about each food item. With the help of this, we can manage our diet and food habits effectively.},
keywords = {Nutrient Net, Deep Learning, Convolution Neural Networks (CNN), Long Short-Term Memory (LSTM), Food Image Classification, Portion Size Estimation, , Nutritional Analysis.},
month = {April},
doi = {https://doi.org/10.64388/IREV9I10-1715946}
}