Enhanced Food Image Recognition and Nutritional Mapping using CNN with MobileNetV2

DOI

10.2991/978-94-6463-858-5_80How to use a DOI?

Keywords

Convolutional Neural Network (CNN); deep learning; food image recognition; MobileNetV2; transfer learning

Abstract

This paper introduces a new hybrid system for food image recognition and nutrition facts retrieval. A baseline Convolutional Neural Network (CNN) started with 25% classification accuracy. For a significant gain in performance, the system combined Mo-bileNetV2 and transfer learning, and the accuracy was 75%. This demonstrates that MobileNetV2 is useful for food image classification with a high accuracy improvement. The system was trained on a dataset of 24,000 images spanning 34 Indian and Western appetizer categories. By smoothly integrating a nutrition database, the system presents immediate, actionable nutritional insights, thus improving its relevance in healthcare and diet assessment.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sanjana Tanna
AU  - Trisha Bhogawar
AU  - Ria Shah
AU  - Shubha Puthran
PY  - 2025
DA  - 2025/11/04
TI  - Enhanced Food Image Recognition and Nutritional Mapping using CNN with MobileNetV2
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 950
EP  - 965
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_80
DO  - 10.2991/978-94-6463-858-5_80
ID  - Tanna2025
ER  -