Artificial Intelligence (AI) is a very important field of computer science in the present and future eras to realize intelligent computer systems. This field has grown very rapidly in the last 20 years along with the need for smart devices in industry and households. One of the fields in AI that acquires, processes, understands, and takes information/decisions is known as components of artificial intelligence. Computer vision is a constituent of artificial intelligence. In this case, artificial intelligence in computer vision can imitate the ability of human intelligence and behavior.

According to Forsyth and Ponece, Computer Vision is “Extracting descriptions of the world from pictures or sequences of pictures.” Computer vision is defined as a branch of science that studies how computers can recognize observed objects. This branch of science together with artificial intelligence will be able to produce a visual intelligence system. Another opinion says computer vision is an automated process that integrates a large number of processes for visual perception, such as image acquisition, image processing, recognition, and decision-making.

Computer vision tries to imitate the workings of the human visual system (human vision) which is very complex, how humans see objects with the sense of sight (eyes), then the image of the object is passed on to the brain for interpretation so that humans understand what objects appear in the eye. Furthermore, the results of this interpretation are used for decision-making. In its application, computer vision applies digital image processing to apply computer algorithms for image processing in digital images.

According to Forsyth and Ponce, computer vision is extracting a description of the world from an image or sequence of images. Computer vision in general is an area that includes methods for capturing, processing, analyzing, and understanding images to produce numerical or symbolic information. Image processing is the process of changing 2D images using Edge detection, Fourier transforms, or enhancement methods to obtain the desired 2D image output.