Geometric transformation alters the photo’s geometry, which is done by flipping along the X-axis or Y-axis, cropping, padding, rotating, warping, and translation. Complex augmentation uses these base photo-altering techniques. While working with geometric transformations, the distortion magnitude has to be kept to a safe level, depending on the image topic. Thus, no general formula governing geometric transformation applies to all photos. In the second half of this chapter, the Python coding section, you and Pluto will download real-world image datasets to define the safe level for each image set.
The following techniques are not mutually exclusive. You can combine horizontal flipping with cropping, resizing, padding, rotating, or any combination thereof. The one constraint is the safe level for distortion.
In particular, you will learn the following techniques: