Localization algorithms are an extension of the materials learned in Chapter 2, Image Classification and Chapter 3, Image Retrieval. In image classification, an image is passed through several layers of a CNN (convolutional neural network). The final layer of CNN outputs the probabilistic value, belonging to each of the labels. This can be extended to localize the objects. We will see these ideas in the following sections.
An intuitive way of localization is to predict several cropped portions of an image with an object. The cropping of the images can be done by moving a window across the image and predicting for every window. The method of moving a smaller window than the image and cropping the image according to window size is called a sliding window. A prediction can be made for every cropped window of the image which is called sliding window object detection.
The prediction can be done by the deep learning model trained for...