Of the five human senses—vision, hearing, smell, taste, and touch—vision is undoubtedly the major source of input/information to the human brain. Human eyes provide information in a range of megabits per glance. However, much of this information is redundant and several layers of visual cortex compress this information so that higher centers of the brain have to interpret only a small fraction of the input data. The ultimate goal of areas such as computer vision is to use a computer to emulate human vision, including learning and being able to take actions based on visual inputs. A computer vision can be defined as the process of deciphering the physical contents of an image/video by computer/machine. This chapter will focus on a high-level image processing, which is often referred to as computer vision.

A computer vision is a rapidly growing field, partly as a result of both cheaper and more capable cameras...