OrigamiSet1.0: Two New Datasets for Origami Classification and Difficulty Estimation

TL;DR

This paper introduces OrigamiSet1.0, two new datasets for origami image classification and difficulty estimation, filling a gap in publicly available data for machine learning research in origami recognition.

Contribution

The creation and public release of two origami datasets, enabling machine learning research on origami classification and difficulty assessment for the first time.

Findings

Established baseline machine learning models on the datasets.

Demonstrated dataset diversity with 16,000 images for classification.

Provided difficulty categories with 1,509 images across three levels.

Abstract

Origami is becoming more and more relevant to research. However, there is no public dataset yet available and there hasn't been any research on this topic in machine learning. We constructed an origami dataset using images from the multimedia commons and other databases. It consists of two subsets: one for classification of origami images and the other for difficulty estimation. We obtained 16000 images for classification (half origami, half other objects) and 1509 for difficulty estimation with $3$ different categories (easy: 764, intermediate: 427, complex: 318). The data can be downloaded at: https://github.com/multimedia-berkeley/OriSet. Finally, we provide machine learning baselines.