Optometry 2019

Cognitive vision

The term cognitive vision has been introduced in the past few of years to encapsulate an attempt to achieve more robust, resilient, and adaptable computer vision systems by endowing them with a cognitive faculty: the ability to learn, adapt, weigh alternative solutions, and develop new strategies for analysis and interpretation. The key characteristic of a cognitive vision system is its capacity to exhibit robust performance even in circumstances that were not foreseen when it was designed. Furthermore, a cognitive vision system should be able to anticipate events and adapt its operation accordingly. Ideally, a cognitive vision system should be able to recognize and adapt to novel variations in the current visual environment, generalize to new contexts and application domains, interpret the intent of underlying behaviour to predict future configurations of the visual environment, and communicate an understanding of the environment to other systems, including humans.