In the digital age, there is a variety of large-scale visual data available on the Internet. This presents opportunities for the novel processing of visual information that can have commercial advantages. It can be accomplished if this data can be understood, systematically managed, processed and utilized. An interdisciplinary field of science called computer vision deals with enabling computers to gain an understanding of digital images and videos. Its objective is to automate tasks that only the human visual system can achieve. Some of the core tasks of computer vision are acquiring, processing, understanding and analyzing digital images, and extracting high-dimensional data for producing numerical or symbolic information. Image understanding can be thought of as the disentangling of symbolic information from image data with the aid of geometry, learning theory, physics and statistics.