The artificial vision is a discipline which involves techniques to analyze, process and acquire images of the real-world to generate a piece of information that can be processed by a machine. A simple way to understand this system is to build on our senses. The understanding in the devices is achieved thanks to a decomposition of the image into small fragments (pixels) and in its subsequent study.
The main purpose of the artificial vision is to provide the machine with “eyes” to see what happens in the real world and thus be able to make decisions to automate any process. The system consists mainly of a camera that acts as an eye and an automaton or PLC. The camera sends information to the decision-making system (PLC) that interprets it and allows decision-making.
In addition to what has been mentioned above, auxiliary systems such as external lighting or photoelectric sensors are required. The lighting serves to ensure that the image is captured in a useful and correct way, and the sensors act as a trigger or trigger by providing a signal to the camera to take the image.
A very important point in the subject is the way to illuminate our application because if it is not done correctly, the camera will be unable to “see” anything. For this reason, there are three different lighting modes, direct, indirect and later (or backlight).
By combining these light modalities, the reflections are played, and the best possible visibility is obtained.
We conclude on artificial vision stating that, thanks to its development, a great technological advance has been made in the industrial world. With it, it is possible to solve a wide variety of applications where abundant inspection and measurement components were previously needed.
Some of its most characteristic uses include QA, Classification, Product counting, Positioning, average quantity control, Rotation control, Pick and place, amongst others.