Comparison of Different Image Data Augmentation Approaches

Abstract

Convolutional neural networks (CNNs) have gained prominence in the research literature on image classification over the last decade. One shortcoming of CNNs, however, is their lack of generalizability and tendency to overfit when presented with small training sets. Augmentation directly confronts this problem by generating new data points providing additional information. In this paper, we investigate the performance of more than ten different sets of data augmentation methods, with two novel approaches proposed here: one based on the discrete wavelet transform and the other on the constant-Q Gabor transform. Pretrained ResNet50 networks are finetuned on each augmentation method. Combinations of these networks are evaluated and compared across four benchmark data sets of images representing diverse problems and collected by instruments that capture information at different scales: a virus data set, a bark data set, a portrait dataset, and a LIGO glitches data set. Experiments demonstrate the superiority of this approach. The best ensemble proposed in this work achieves state-of-the-art (or comparable) performance across all four data sets. This result shows that varying data augmentation is a feasible way for building an ensemble of classifiers for image classification.

Automated recognition of pain in cats

“…The second step is the vector creation, based on the four regions described above. The last step is data augmentation, at which we generate new landmark samples by noise injection 67 , 68 . Noise injection generates new images by adding certain amount of noise to the training dataset that may lead to a better generalization error and fault tolerance by enhancing the learning capability.…”

Automated Recognition Of Pain In Cats

“…The second step is the vector creation, based on the four regions described above. The last step is data augmentation, at which we generate new landmark samples by noise injection 54,55 . Noise injection generates new images by adding certain amount of noise to the training dataset that may lead to a better generalization error and fault tolerance by enhancing the learning capability.…”

Customized convolutional neural network to detect dental caries from radio visio graphy(RVG) images

“…The dataset size is increased by applying image augmentation techniques [31]. Image augmentation helped to increase the size of the dataset from 1336 images to 13582 images.…”