Appearance-based data augmentation for image datasets using contrast preserving sampling

摘要

Data augmentation techniques have been employed to overcome the problem of model over-fitting in deep convolutional neural networks and have consistently shown improvement in classification. Most data augmentation techniques perform affine transformations on the image domain. However these techniques cannot be used when object position is significant in the image. In this work we propose a data augmentation technique based on sampling an representation built by inequality constraints propagated from local binary patterns. We sample nine distinct variations for an image in a manner meant to preserve local structure and differ only in the amount of contrast between pixels. These contrast invariants are then used to augmented the original images. We present evaluations on CIFAR-10 and validate our gains in performance across four criteria, accuracy, precision, recall and Fl-Score; using a 2-layer convolutional neural network with different configuration of filters, and report improvement by about 13%, 9%, 12%, and 22% respectively over the baseline.