AVICON uses its expertise to build vision systems – control devices equipped with image acquisition heads and software for real-time analysis.
The most efficient image processing system, known as a vision system, is in your head. Your brain constantly identifies, processes, and interprets what you see. What seems natural and easy for you is very difficult to translate into machines.
All constructed vision systems strive to be as good and efficient in their operation as the human brain. Although it is still impossible to create a vision system as universal as the human brain, in a specific application, machines already allow for greater efficiency in visual inspection and ensure greater system stability.
Unlike the human brain, a vision system will not lose focus or get tired after a few or a dozen minutes. A properly constructed vision system is a key element of an Industry 4.0 production line. It ensures high quality of manufactured products in practically every industry. A vision system will work well in both food production and metal component manufacturing. It can check for the presence of elements or perform precise dimensional analysis. 3D measurements and character recognition? Nowadays, it’s more a matter of planning the implementation deadline than developing the technology.
The main elements of a vision system are the camera and the lens. Why are these two elements discussed together? Because they form an integral whole, just like the human eye. The lens corresponds to the cornea, while the camera, or more precisely the heart of the camera, which is the photosensitive sensor, corresponds to the macula.
The photosensitive sensor converts the incident image into an electrical signal proportional to the light intensity. In most vision systems, monochromatic (black and white) cameras are a sufficient and even better solution. They provide better resolution and image sharpness compared to color cameras. Color cameras, however, are suitable where color analysis is important (although this also depends on the application, as this can also be done using a monochromatic camera used in conjunction with optical filters).
Since the matrix only registers the intensity (brightness) of the incident light, to obtain a color image, a matrix of color filters (Bayer filters): green, red, and blue, is mounted on the camera sensor, which cut off other wavelengths, so one pixel registers the intensity of only one component of visible light. Based on the combination of the three components, the resulting color image is created. You can read more about this in our CCD/CMOS article.
Image cameras have a rectangular matrix with sides up to several thousand pixels, and are used to record entire 2D images during a single exposure cycle. These cameras are useful in vision systems where an entire object or feature must be observed and interpreted at once.
Line cameras have a matrix in the shape of a thin line, several pixels wide. Image acquisition with line cameras proceeds line by line; only after combining the lines is the entire object image obtained. Line cameras are useful where objects are moving, e.g., on a conveyor belt, allowing for greater inspection speed and resolution.
In vision systems, cameras primarily utilizing Time-of-Flight (ToF) technology or stereo cameras are used. ToF cameras send a modulated infrared light beam towards the object and measure the time it takes for the beam to travel the camera-object-camera distance. Based on this, a point cloud of the scene in front of the camera is determined.
The lens plays two important roles in a vision system:
• It focuses light rays from the object’s surface onto the matrix plane.
• It limits the amount of light falling on the matrix.
Today, lenses are complex constructions, often matching the camera in price. It is particularly difficult to manufacture large lenses with high accuracy. Therefore, the price of a lens increases very quickly with its size.
Types of Lenses:
Depending on how light rays are guided and the functions offered, lenses can be divided into several basic types:
The most popular solution used in vision systems. As the name suggests, these lenses have a fixed focal length, meaning they do not offer a change in field of view without changing the working distance. These lenses have two adjustment rings: one for focusing, the other for controlling the aperture. Most often, vision systems are designed so that there is no need to change the working distance, making fixed-focal length lenses an ideal compromise between features and price.
The operating principle of zoom lenses is similar to fixed-focal length lenses, with the added ability to change the focal length, i.e., modify the camera’s field of view. Such lenses are more often used, for example, in robotics, especially if they are equipped with electronic control. They will also be a good solution for testing various solutions when constructing a vision system.
Characterized by guiding rays parallel to the optical axis. Due to the absence of perspective error, telecentric lenses are used for precise dimensional analysis. Telecentric lenses can work with both area scan and line scan cameras. Since the field of view of telecentric lenses is equal to the diameter of the lens’s front element, telecentric lenses are more expensive solutions than the two previously presented solutions.
Also known as pericentric lenses. The special design of these lenses allows for simultaneous observation of the front and side surfaces of the object. Depending on the model, these lenses allow, for example, inspection of the inside of a bottle cap and its thread using a single area scan camera. Other solutions enable viewing the entire label placed on the neck of a bottle.
Lighting is crucial in vision systems, with LEDs dominating this area by providing energy efficiency and appropriate light quality. Lighting can take various forms:
They usually have a rectangular shape with various aspect ratios: from a thin rectangle to large squares. These illuminators are used for frontal illumination of objects, from the same side where the camera is positioned. Front illuminators often have lenses on the LEDs that allow light to be focused over larger distances.
Their shape and illumination characteristics resemble front illuminators, but unlike them, they almost always have a matte, light-diffusing diffuser, ensuring high uniformity of the generated light. Backlights are placed behind the object (often directly behind it) and emit light towards the camera. This type of light emphasizes the edges of objects.
They have LEDs arranged in a ring. Ring illuminators are often mounted on the camera, or near the camera so that the camera looks through their opening. Ring illuminators also serve to front-illuminate objects, providing uniform illumination without a specific direction.
Particularly useful for illuminating highly reflective surfaces. Shadowless lighting provides smooth, homogeneous illumination, evenly highlighting object features. Shadowless illuminators can be dome-shaped or tunnel-shaped with an opening for the camera (LEDs located at the base of the housing, the dome/tunnel covered with a rough layer uniformly directing light towards the object) or a flat front illuminator with a camera opening (a dome with an ~infinite radius, operating on a similar principle to front illuminators, but with a centrally placed camera preventing shadows from forming).
They usually have a rectangular shape with LEDs placed at the base and a beam-splitting plate that allows the light source and camera to overlap. This combination effectively highlights irregularities on flat surfaces. Similar to shadowless illuminators, they are a suitable solution for vision systems where glossy objects are observed.
Illuminators dedicated to working in vision systems that use line scan cameras. They feature a very bright, focused, elongated beam of light that precisely illuminates a fragment of the object observed by the camera. Line illuminators have a narrow strip of LEDs, most often combined with a cylindrical lens, so that the light can remain focused over larger working distances.
Small illuminators consisting of one or more LEDs. They are suitable where there is a need to illuminate small surfaces or, for example, as a light source in telecentric lenses with separate coaxial illumination.
Particularly useful for illuminating highly reflective surfaces. Shadowless lighting provides smooth, uniform illumination, evenly highlighting object features. Shadowless illuminators can be dome-shaped or tunnel-shaped with an opening for the camera (LEDs placed at the base of the housing, the dome/tunnel covered with a rough layer evenly directing light towards the object), or a flat front illuminator with a camera opening (a dome with an ‘infinite’ radius, similar operating principle to front illuminators, but with a centrally placed camera preventing shadows from forming).
They emit strong light with specific characteristics, which is then guided by an optical fiber to the inspection area. This type of illuminator is used, among other things, in microscopes or special illuminators that do not have electronics.
