MozzaVID: Mozzarella Volumetric Image Dataset

Pawel Tomasz Pieta, Peter Winkel Rasmussen, Anders Bjorholm Dahl, Jeppe Revall Frisvad, Siavash Arjomand Bigdeli, Carsten Gundlach, Anders Nymark Christensen
Technical University of Denmark, Kgs. Lyngby, Denmark
ArXiv 2024
Data Code arXiv Hugging Face logo HuggingFace
MY ALT TEXT

Mozzarella microstructure in example coarse and fine-grained classes. MozzaVID is a benchmark volumetric (3D) classification dataset containing mozzarella CT images at three dataset splits (sizes) and two classification targets.

Abstract

Influenced by the complexity of volumetric imaging, there is a shortage of established datasets useful for benchmarking volumetric deep-learning models. As a consequence, new and existing models are not easily comparable, limiting the development of architectures optimized specifically for volumetric data. To counteract this trend, we introduce MozzaVID -- a large, clean, and versatile volumetric classification dataset. Our dataset contains X-ray computed tomography (CT) images of mozzarella microstructure and enables the classification of 25 cheese types and 149 cheese samples. We provide data in three different resolutions, resulting in three dataset instances containing from 591 to 37,824 images. While targeted for developing general purpose volumetric algorithms, the dataset also facilitates investigating the properties of mozzarella microstructure. The complex and disordered nature of food structures brings a unique challenge, where a choice of appropriate imaging method, scale, and sample size is not trivial. With this dataset, we aim to address these complexities, contributing to more robust structural analysis models and a deeper understanding of food structure.

Structural analysis

Apart from providing a general benchmark, the dataset is specifically targeted towards developing and evaluating methods for deep learning-based structural analysis. The structure of materials directly influences their functional properties, and structural analysis is an important use case for volumetric images. At the same time, CT imaging has become a common choice for food analysis, where many products, such as meat, bread, pastries, and cheese (e.g. mozzarella) are heavily defined by their structural properties. With 34% of greenhouse gas emissions linked to food, understanding its structural properties is crucial for developing environmentally friendly alternatives to known structured foods that are also pleasant to eat.

>

BibTeX

@misc{pieta2024b,
      title={MozzaVID: Mozzarella Volumetric Image Dataset}, 
      author={Pawel Tomasz Pieta and Peter Winkel Rasmussen and Anders Bjorholm Dahl and Jeppe Revall Frisvad and Siavash Arjomand Bigdeli and Carsten Gundlach and Anders Nymark Christensen},
      year={2024},
      howpublished={arXiv:2412.04880 [cs.CV]},
      eprint={2412.04880},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.04880},
      }