Computer Vision (CV) is a field of artificial intelligence (AI) that involves teaching computers to recognise, interpret, and understand the visual world.
This implies developing algorithms and models to interpret and understand the visual world in a similar way to how people perceive and process visual information.
The ultimate goal of computer vision is to automate tasks that the human visual system can do. Computer vision, as a field, began to take shape in the 1960s. Initial work focused on basic image processing and pattern recognition tasks. Pioneering efforts in the 1960s and 1970s by researchers like Larry Roberts, who is often credited with the term “computer vision”, laid the groundwork for the field. It evolved significantly in the following decades, especially with advancements in machine learning and deep learning from the 2010s onwards. An example of computer vision is the barcode scanner.