A Deep Learning Model for Classifying Bangladeshi Food and Estimating Calories

Abstract

Accurate food calorie estimation is essential for managing dietary intake, particularly forindividuals with diabetes. This project presents an end-to-end system for food classification,weight estimation, and calorie calculation from a single food image without requiringa reference object. The system integrates deep learning techniques including convolutionalneural networks (CNNs) for food classification, YOLO and Segment AnythingModel (SAM) for food segmentation and MiDaS for depth estimation. The DeshiFoodBDdataset consisting of 19 food classes such as bakorkhani, beguni, and kala bhuna isused for food classification. To evaluate classification performance multiple deep learningmodels including a basic CNN, EfficientNetB0, ResNet50, MobileNetV2 and InceptionV3have been compared. The segmented food region is processed using depth mapsto estimate its volume which is then converted to weight based on standard nutritionalvalues. Finally, the estimated weight is used to compute calorie content. By leveragingadvanced computer vision techniques, this method aims to provide an automated andpractical approach for dietary monitoring, enhancing convenience and accuracy in foodintake assessment.