Image segmentation consists of the original image and an accompanying mask image. The goal is to determine whether a pixel belongs to a list of objects. For example, an urban photograph consists of streets, street signs, cars, trucks, bicycles, buildings, trees, and pedestrians. Image segmentation’s job is to decide whether this pixel belongs to a car, tree, or other objects.
Image segmentation and image classification share the same transformations. In other words, most geometric transformations, such as flipping, rotating, resizing, cropping, and transposing, work with the original image and mask image in image segmentation. Photometric transformations, such as brightness, contrast, and FancyPCA, can technically be done with Python, but the filter does not alter the mask image. On the other hand, filters such as noise injection and random erasing are unsuitable for segmentation because they add or replace pixels in the original image.
Throughout this chapter...