Welcome to IJSDR UGC CARE norms ugc approved journal norms IJRTI Research Journal | ISSN : 2455-2631
International Peer Reviewed & Refereed Journals, Open Access Journal
ISSN Approved Journal No: 2455-2631 | Impact factor: 8.15 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.15 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)

Issue: June 2023

Volume 8 | Issue 6

Impact factor: 8.15

Click Here For more Info

Imp Links for Author
Imp Links for Reviewer
Research Area
Subscribe IJSDR
Visitor Counter

Copyright Infringement Claims
Indexing Partner
Published Paper Details
Paper Title: Food Identification and Calorie Tracking using Deep Learning
Authors Name: Amit Reny , Alan Thomas Abraham , Bhavya S , Shabana A G , Nithyananda C R
Unique Id: IJSDR2305271
Published In: Volume 8 Issue 5, May-2023
Abstract: In recent years, there has been a growing interest in leveraging deep learning techniques for food and calorie tracking to support healthier lifestyles and personalized nutrition. This paper proposes an innovative approach that utilizes the EfficientNetB0 pretrained model, a state-of-the-art convolutional neural network (CNN), for accurate and efficient food and calorie tracking. The EfficientNetB0 model, known for its excellent balance between accuracy and computational efficiency, is fine-tuned on a large-scale food image dataset to learn specific food features and their corresponding calorie values. The dataset is carefully curated, comprising diverse food categories and portion sizes to capture the wide range of dietary choices and variations encountered in real-world scenarios. To ensure seamless integration with popular food tracking applications, we develop an end-to-end pipeline that includes image preprocessing, feature extraction using EfficientNetB0, and a calorie estimation module. The pipeline is trained and evaluated on a comprehensive benchmark dataset, consisting of annotated food images and corresponding ground truth calorie information.Experimental results demonstrate the superior performance of the proposed model, achieving high accuracy in food identification and accurate calorie estimation. The EfficientNetB0-based model outperforms existing deep learning architectures while maintaining computational efficiency, making it suitable for real-time food and calorie tracking applications on resource-constrained devices. Furthermore, we provide insights into the interpretability of the model's predictions by employing gradient-based methods to generate heatmaps highlighting regions of interest in food images. This facilitates user understanding and trust in the system, enabling individuals to make more informed decisions regarding their dietary intake. Overall, this research presents a novel deep learning framework that harnesses the power of the EfficientNetB0 pretrained model for efficient and accurate food and calorie tracking. The proposed approach has the potential to significantly impact personal nutrition management, promoting healthier lifestyles and aiding individuals in achieving their dietary goals
Keywords: Food Identification and Calorie Tracking using Deep Learning, Food , Image Recognition , Deep Learning, Computer Vision
Cite Article: "Food Identification and Calorie Tracking using Deep Learning", International Journal of Science & Engineering Development Research (www.ijsdr.org), ISSN:2455-2631, Vol.8, Issue 5, page no.1733 - 1736, May-2023, Available :http://www.ijsdr.org/papers/IJSDR2305271.pdf
Downloads: 000223216
Publication Details: Published Paper ID: IJSDR2305271
Registration ID:206713
Published In: Volume 8 Issue 5, May-2023
DOI (Digital Object Identifier):
Page No: 1733 - 1736
Publisher: IJSDR | www.ijsdr.org
ISSN Number: 2455-2631

Click Here to Download This Article

Article Preview

Click here for Article Preview

Major Indexing from www.ijsdr.org
Google Scholar ResearcherID Thomson Reuters Mendeley : reference manager Academia.edu
arXiv.org : cornell university library Research Gate CiteSeerX DOAJ : Directory of Open Access Journals
DRJI Index Copernicus International Scribd DocStoc

Track Paper
Important Links
Conference Proposal
DOI (A digital object identifier)

Providing A digital object identifier by DOI
How to GET DOI and Hard Copy Related
Open Access License Policy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Creative Commons License
This material is Open Knowledge
This material is Open Data
This material is Open Content
Social Media

Indexing Partner