Transformations

The transformations included in the library are:

  1. hflip: horizontal flipping the image
_images/hflip.png
  1. vflip: vertical flipping the image
_images/vflip.png
  1. Affine:carry out the transformation expressed in the operation matrix
_images/affine.png
  1. Rotate:rotate the image by the indicated degrees counterclockwise
_images/rotate.png
  1. Shear: linear map that displaces each point in fixed direction, by an amount proportional to its signed distance from the line that is parallel to that direction and goes through the origin
_images/shear.png
  1. Scale: scale the image by making it smaller or larger (crop equivalent)
_images/scale.png
  1. Translate: moves the image pixels to the positions indicated on each axis
_images/translate.png
  1. Change gamma: adjust image’s gamma (luminance correction) .
_images/gamma.png
  1. Change contrast:: change the image contrast.
_images/contrast.png
  1. Change brightness: change the image brightness
_images/brightness.png
  1. Equalize histogram: equalize the image histogram
_images/equalization.png

12. Inject gaussian noise: gaussian noise is a statistical noise having a probability density function (PDF) equal to that of the normal distribution

_images/gaussian_noise.png
  1. Inject salt and pepper noise: salt-and-pepper noise is a statistical noise compose of white (salt) and black (pepper) pixels
_images/salt_pepper_noise.png

14. Inject spekle noise: Speckle is a granular interference that inherently exists in and degrades the quality of the active radar, synthetic aperture radar (SAR), medical ultrasound and optical coherence tomography images. It is applied by adding the image multiplied by the noise matrix -> img + img * uniform_noise

_images/spekle_noise.png
  1. Inject poisson noise: It is applied by adding Poisson-distributed noise
_images/poisson_noise.png
  1. Blur: blur image.
_images/blur.png
  1. Gaussian blur: blurring an image by a Gaussian function.
_images/gaussian_blur.png