Why leverage neural networks for image analysis?

In traditional computer vision, we would create a few features for every image before using them as input. Let’s look at a few such features based on the following sample image, in order to appreciate the effort we save by training a neural network:

Figure 3.8: A subset of features that can be generated from an image

Note that we will not walk you through how to get these features, as the intention here is to help you realize why creating features manually is a suboptimal exercise. However, you can familiarize yourself with the different feature extraction methods at https://docs.opencv.org/4.x/d7/da8/tutorial_table_of_content_imgproc.html:

• Histogram feature: For some tasks, such as auto-brightness or night vision, it is important to understand the illumination in the picture: that is, the fraction of pixels that are bright or dark.
• Edges and corners feature: For tasks such as image segmentation...