Computer vision is a computer science field that enables a computer to sees and process images as human do and then provide the proper output. This is the same as assigning human intelligence and instincts to a computer. From the engineering perspective, computer vision seeks to automate tasks that can be done by the human visual system.
Computer vision tasks comprise methods for obtaining, processing, analyzing and understanding digital images. It also includes extraction of high-dimensional data to produce symbolic or numerical information, e.g., in the forms of decisions. In this context, understanding means the transformation of visual images into world’s descriptions that can interface with people’s thought processes.
The goal of a computer vision is not only to see but also to process and offer useful results based on the observation. A computer, for example, could create a 3-D image from a 2-D image, like those in cars. Usually, cars are fitted with computer vision that identifies and distinguish object around and on the road, such as traffic signs, pedestrians, and traffic lines and so on. If there is a sudden obstacle on the road, computer vision could provide inputs to the driver or make the car stop.