Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{195086,
        author = {PODILAPU AMULYA and PEDDADA RAJU and Makireddy Durga Eswara Tejesh and SUNKARA DILEEP},
        title = {Food Calorie Prediction and Diet Recommendation System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {7557-7562},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195086},
        abstract = {Accurate dietary monitoring is a critical challenge in preventive healthcare, with rising incidences of lifestyle-related diseases such as obesity, diabetes, and cardiovascular disorders highlighting the need for accessible nutritional assessment tools. This paper presents a web-based Food Calorie Prediction and Diet Recommendation System that integrates Convolutional Neural Network (CNN) based image classification, OpenCV contour analysis for portion size estimation, and a structured nutrition dataset to deliver real-time calorie prediction and personalized dietary guidance. Unlike depth-sensor-dependent systems, the proposed approach processes a single uploaded food image through a Flask-based application, eliminating specialized hardware requirements. A fuzzy string-matching module ensures robust mapping between predicted food labels and nutrition database entries. Nutritional values — calories, protein, and total fat — are dynamically scaled according to the estimated food area derived from image contour detection. A rule-based diet recommendation engine further generates context-aware dietary suggestions based on calorie density, macronutrient composition, and food category. Experimental results demonstrate CNN classification accuracy above 85% for most food categories, with end-to-end processing times under five seconds. The system successfully handles ten designed test cases covering valid inputs, error conditions, and concurrent usage scenarios. This work demonstrates the practical feasibility of combining deep learning and image processing within a lightweight, platform-independent nutritional intelligence application.},
        keywords = {Convolutional Neural Network, Food Calorie Estimation, Diet Recommendation, OpenCV, Image Processing, Flask.},
        month = {March},
        }