EfficientNetB0-Based Food Image Recognition for a Smart Diet Tracking Application

Author(s)	Mr. Pachikora Yuvaraju, Ms. Yenneti Akshaya Deepika, Mr. Namala Srinu, Ms. Sandrani Sonia, Prof. Kalavala Atchut Vardhan
Country	India
Abstract	Food image recognition is an important component of smart diet tracking systems. Existing approaches often rely on benchmark datasets dominated by Western cuisines and lack real-world deployment. This paper presents an EfficientNetB0-based food recognition system focused on South Indian cuisine using a custom dataset of approximately 8,000 images across 30 food categories. Data augmentation techniques are applied to improve generalization and address class imbalance during training. The proposed model achieves a validation accuracy of about 84% for single food item classification. To demonstrate practical applicability, the trained model is integrated into an Android-based diet tracking application that enables food identification and basic nutritional estimation. The results highlight the feasibility of an end-to-end, region-specific food recognition solution for real-world dietary monitoring and smart health management.
Keywords	Food Recognition, EfficientNetB0, Deep Learning, South Indian Cuisine, Diet Tracking, Calories Estimation.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-04-08

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research