From a set of input images, it generates computational models capable of extracting key characteristics such as areas of interest, color detection, pattern recognition, etc.
Vision algorithms allow monitoring of surveillance cameras to capture movements that can escape the human eye.
Once we define what objects we are looking for, with the segmentation of the image we indicate which pixels belong to each of these. In this way we recognize areas of interest on the image.
One of the main applications that computer vision provides is the ability to generate mathematical models designed to classify a set of images using Deep Learning techniques.