Augmentor: An Image Augmentation Library for Machine Learning
This provides a practical tool for machine learning practitioners working with image data, but it is incremental as it builds on existing augmentation techniques.
The authors tackled the need for efficient image data augmentation in machine learning by developing Augmentor, a software library that offers a stochastic, pipeline-based API for generating augmented images at runtime, resulting in a tool that supports standard and advanced augmentation practices like label-preserving distortions.
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.