Manually Segmented Labels Based on the Nutrition5k Dataset

FoodDialogues

FoodDialogues is built from the Nutrition5k dataset, which contains ingredient labels and precise nutrition information, making it unique and suitable for various conversational topics. Specifically, we follow the training and testing splits of the original data set and selected an overhead RGB image and a well-angled (angle A or D) video frame for each sample. Send the sample's ingredient list and detailed nutritional information to GPT-4 in the form of plain text… See the full description on the dataset page: https://huggingface.co/datasets/Yueha0/FoodDialogues.

Food_train_old

## Overview

Food_train_old is a dataset for instance segmentation tasks - it contains Food annotations for 54,350 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

This dataset has been adapted from the PANCAKE project developed by the European Food Safety Authority (EFSA), originally designed for dietary assessment in European populations. It contains 210 low-resolution images (182×136 px), each depicting a single food item with associated weight annotations.

To support the development and evaluation of multitask deep learning models for food classification and weight estimation, each image is labeled with:

A food category identifier

The corresponding food weight in grams

A segmentation mask (PNG) generated using Meta’s Segment Anything Model (SAM), manually refined for pixel-level accuracy

This dataset was used in the article "NutriConv: A Convolutional Approach for Digital Dietary Tracking trained on EFSA’s PANCAKE Dataset". While the original PANCAKE data was not structured for machine learning, this version includes preprocessed, cleaned, and annotated images in a format suitable for deep learning workflows.

Contents:

images/: Cleaned food images

masks/: Segmentation masks in PNG format

labels.csv: File containing image names, food class IDs, and weights in grams

Additionally, we include a subset of the Nutrition5k dataset, reorganized into classes based on unique sets of ingredients, disregarding their quantities. Only combinations appearing in at least ten images were retained, resulting in 896 images grouped into 44 ingredient-based classes. While this class definition introduces visual variability—since different dishes may share ingredients but differ in appearance—it provides a pragmatic approximation aligned with our classification task. This curated subset was used as an external validation set for evaluating the performance of the NutriConv model.

Thames, Q., Karpur, A., Norris, W., Xia, F., Panait, L., Weyand, T., & Sim, J. (2021). Nutrition5k: Towards automatic nutritional understanding of generic food. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 8903-8911).

Global Gastronomic Culinary Dataset

In this work, we propose the food object detection dataset named the Global Gastronomic Culinary Dataset (GGCD). This is a follow-up to our previous work Central Asian Food Scenes Dataset (CAFSD)[1]. The dataset is the extension of our CAFSD dataset with the Nutrition5k dataset[2]. The original Nutrition5k contains images taken from an overhead angle for approximately 3,500 dishes and four different side-angle videos for approximately 1,500… See the full description on the dataset page: https://huggingface.co/datasets/issai/Global_Gastronomic_Culinary_Dataset.

Food_train_new

## Overview

Food_train_new is a dataset for instance segmentation tasks - it contains Food QqZi annotations for 54,350 images.

## Getting Started

You can download this dataset for use within your own projects, or fork it into a workspace on Roboflow to create your own model.

  ## License

  This dataset is available under the [CC BY 4.0 license](https://creativecommons.org/licenses/CC BY 4.0).

The dataset comprises 31 dishes from Nutrition5k with 1356 annotated frames and 11 dishes from V&F with 2308 annotated frames, totaling 42 dishes with 3664 annotated frames. This curated dataset of masks from Nutrition5K and V& F, which we call FoodMask, forms a robust foundation for rigorous testing and validation of our segmentation framework, facilitating accurate assessment across diverse culinary compositions.