Table 2 Data augmentation strategy used in AxonDeepSeg.

From: AxonDeepSeg: automatic axon and myelin segmentation from microscopy data using convolutional neural networks

Data augmentation strategy

Description

Shifting

Random horizontal and vertical shifting between 0 and 10% of the patch size, sampled from a uniform distribution.

Rotation

Random rotation, angle between 5 and 89 degrees, sampled from a uniform distribution.

Rescaling

Random rescaling of a randomly sampled factor between 1/1.2 and 1.2

Flipping

Random flipping: vertical flipping or horizontal flipping.

Blurring

Random blurring: gaussian blur with the standard deviation of the gaussian kernel being uniformly sampled between 0 and 4.

Elastic deformation

Random elastic deformation with uniformly sampled deformation coefficient α = [1–8] and fixed standard deviation σ = 4.

  1. Shifting, rotation, rescaling, flipping, blurring and elastic deformation were applied to training patches in order to reduce overfitting and increase variability.
Back to article page