Images

1415 images

Explore Dataset

Overview

The object detection process required an annotated pizza dataset sourced from a Kaggle repository [1], comprising approximately 9000 pizza images capturing diverse visual conditions and angles. Around 1500 images were randomly selected and meticulously annotated with 16 ingredient labels, encompassing common pizza components like Cheese, Pepperoni, and Basil. Utilizing RoboFlow, a versatile dataset creation tool, facilitated label management, bounding box creation, and image sorting, streamlining the annotation process. The dataset was split into training, validation, and testing subsets (60%, 20%, and 20% respectively), ensuring a comprehensive evaluation. Augmentations like rotation and blur, applied exclusively to the training set, increased its size to 2544 images, while the validation and testing sets contained 284 and 283 images respectively. This dataset underwent extensive preparation and augmentation, laying the groundwork for subsequent model training and evaluation phases. RoboFlow's visual aids provided valuable insights into dataset characteristics, including label representation and object placement within images.

The following is a list of classes used for annotation:

Arugula
Bacon
Basil
Broccoli
Cheese
Chicken
Corn
Ham
Mushroom
Olives
Onion
Pepperoni
Peppers
Pineapple
Pizza
Tomatoes

[1] M. Bryant, Pizza images with topping labels, https://www.kaggle.com/datasets/michaelbryantds/pizza-images-with-topping- labels/, Jun. 2019.

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.

YOLOv8

This project has a YOLOv8 model checkpoint available for inference with Roboflow Deploy. YOLOv8 is a new state-of-the-art real-time object detection model.

Cite This Project

If you use this dataset in a research paper, please cite it using the following BibTeX:

@misc{
                            pizza-object-detector_dataset,
                            title = { Pizza Object Detector Dataset },
                            type = { Open Source Dataset },
                            author = { Advanced Computer Vision Assignment },
                            howpublished = { \url{ https://universe.roboflow.com/advanced-computer-vision-assignment/pizza-object-detector } },
                            url = { https://universe.roboflow.com/advanced-computer-vision-assignment/pizza-object-detector },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2024 },
                            month = { jan },
                            note = { visited on 2024-05-15 },
                            }