English

Augmentor: An Image Augmentation Library for Machine Learning

Computer Vision and Pattern Recognition 2017-08-18 v1 Machine Learning Machine Learning

Abstract

The generation of artificial data based on existing observations, known as data augmentation, is a technique used in machine learning to improve model accuracy, generalisation, and to control overfitting. Augmentor is a software package, available in both Python and Julia versions, that provides a high level API for the expansion of image data using a stochastic, pipeline-based approach which effectively allows for images to be sampled from a distribution of augmented images at runtime. Augmentor provides methods for most standard augmentation practices as well as several advanced features such as label-preserving, randomised elastic distortions, and provides many helper functions for typical augmentation tasks used in machine learning.

Keywords

Cite

@article{arxiv.1708.04680,
  title  = {Augmentor: An Image Augmentation Library for Machine Learning},
  author = {Marcus D. Bloice and Christof Stocker and Andreas Holzinger},
  journal= {arXiv preprint arXiv:1708.04680},
  year   = {2017}
}
R2 v1 2026-06-22T21:15:34.642Z