FoodBD: A Smartphone-Captured Meal Image Dataset of Bangladeshi Cuisine
Published: 7 July 2025| Version 1 | DOI: 10.17632/6ttvn3jpkb.1
Contributors:
Benzir Ahmed , , , , , Description
FoodBD dataset, a novel food image dataset comprising 3,603 smartphone-captured meal images of Bangladeshi cuisine. Each image is annotated with polygon-based segmentation of individual food items spanning 142 categories. Additionally, 1,837 images include detailed nutritional information—carbohydrate, protein, fat, fiber, calorie, and glycemic load—estimated by a nutrition expert. FoodBD enables a wide range of tasks including multi-label classification, object detection, semantic segmentation, and nutrition estimation.
Files
Institutions
- United International University
Categories
Nutrition, Image Segmentation, Object Detection, Image Classification, Bangladesh