The study of how computers can derive deep knowledge from digital images or movies is known as COMPUTER VISION, an interdisciplinary branch of science. It aims to comprehend and automate operations that the human visual system is capable of doing from an engineering standpoint.

In order to create numerical or symbolic information, such as judgments, computer vision tasks involve techniques for gathering, processing, analyzing, and interpreting digital pictures as well as for extracting high-dimensional data from the actual environment. In this application, understanding refers to the process through which visual images—the retina’s input—are converted into descriptions of the outside world that are clear to the mind and can motivate the right behavior. It is possible to think of this kind of image comprehension as the decoupling of symbolic information from visual data using mathematical models developed with the assistance of geometry, physics, statistics, and learning theory.