In the first part of this chapter, you and Pluto learn about the image augmentation concepts for classification. Pluto grouped the filters into geometric transformations, photometric transformations, and random erasing to make the image filters more manageable.
When it came to geometric transformations, Pluto covered horizontal and vertical flipping, cropping and padding, rotating, warping, and translation. These filters are suitable for most image datasets, and there are other geometric transformations, such as tilting or skewing. Still, Pluto followed the golden image augmentation rule for selecting a filter that improves prediction accuracy described in a published scholarly paper.
This golden rule is more suitable for photometric transformations because there are about 70 image filters in the Albumentations library and hundreds more available in other image augmentation libraries. This chapter covered the most commonly used photometric transformations cited in published...