Is a process of rendering a three-dimensional image on a two-dimensional surface by creating the optical illusion of depth. Generally, 3D imaging uses two still or motion camera lenses a slight distance apart to photograph a three-dimensional object. The process effectively duplicates the stereoscopic vision of human eyes. The image is reproduced as two flat images that viewers’ eyes see separately, creating a visual illusion of depth as their brains combine the images into a single on.
Application Programming Interface. Essentially a library of software functions.
Is a turnkey vision system addressing a single specific application (e.g. wafer inspection in the semiconductor industry or solutions of system integrators). The primary product function is performed by vision technology.
Is a color filter array, which is basically a mosaic of tiny color filters placed over the pixel sensors of an image sensor to capture color information. The pattern corresponds to the sensitivity of a human eye; hence it is 25% red, 50% green and 25% blue.
A device converting optical radiation into analog or digital data, which is housed in a body, that allows to precisely connect standard optics and cabling. Cameras differ e.g. in the type of sensor technology used (CCD or CMOS), sensor geometry (Area-Scan or Line-Scan), number of pixels, dynamic range (8 bits – 12 bits per pixel), data rate, data output (analog or digital), data interface (e.g. CCIR, RS 170, Camera Link, IEEE 1394, Gigabit Ethernet).
The CMOS (Complementary metal oxide semiconductor) image sensor is often described as the rival technology for solid-state image sensing. It is newer although the underlying technology is not new. Only the use of CMOS silicon for imaging purposes has seen a lot of progress over the last decade. The basic principle is again the photovoltaic effect. But whereas the CCD holds and moves the charge per pixel to one (or more) output amplifier(s), the CMOS sensor converts the charge to voltage already in the pixel. By crossbar addressing and switching, the voltage can be read out from the sensing area.
denotes the identification of objects using markings on the objects; these are typically standardized bar codes or DataMatrix codes, but can also be custom codes. Typical applications are material flow control and logistics. Internally, methods from all areas of image processing are used, including, for example, edge detection, filtering and positioning techniques.
A vision system which can be used for different of applications (e.g. optical character recognition, dimensional measuring) in various industries or environments. The required application can be implemented by the end-user without writing a source code, e.g. with the help of a graphical user interface. Typical characteristics of Configurable Vision Systems are: scalability, flexibility and often based on PC-technology.
denotes categorization of work pieces as correctly or incorrectly assembled; it checks whether all components are present and in the correct position, often as a pre-condition for passing the work piece on to the next assembly step or as a final check before releasing the work piece to be packed and delivered – or one step later the inspection of the package to be completely filled with products of the right type.
Describes the average intensity of the image. It will use other available (non-manually adjustable) controls to adjust the image.
Programming that is inserted into programmable read-only memory, thus becoming a permanent part of a computing device. Firmware is created and tested like software and can be loaded onto the camera.
A field-programmable gate array (FPGA) is an integrated circuit designed to be configured by the customer or designer after manufacturing—hence "field-programmable". The FPGA configuration is generally specified using a hardware description language (HDL). FPGAs offer massive computational force at low power and reduced costs. Besides that FPGAs offer extremely short reaction time in closed loop control systems. These systems can solve variety of problems in applications which demand high processing power and/or extremely short reaction time. The flexibility of FPGAs also offers integration of other systems in the same chip, eliminating the need for costly and power hungry PCs.
Frames per second.
Is often defined in terms of number of frames per second (FPS) or frequency (Hz). This is the speed at which the camera is streaming images to the host system. It basically defines the interval between consecutive image transfers. The measurement is usually given in frames per second, abbreviated FPS. Frame rate affects the viewing flow: a higher frame rate has smoother movement transitions. It also affects the file size: the more frames, the larger the file. If a file with a high frame rate is played back on a computer that is not powerful enough to handle it, or someone tries to play it online without having the necessary bandwidth, the result may include stuttering, a slowing of the intended frame rate, or the dropping out of some of the frames.
The amount of amplification that is applied to a pixel. An increase in gain can result in a brighter image and an increase in noise.
Is a set of Ethernet standards with a minimum data transfer speed of 1-gigabit per second (gbps). GbE cabling is effective over defined distances, so the length of cable required for a particular LAN might necessitate a specific flavor of GbE. Some laptops and motherboards are already incorporating GbE for built-in capability. GbE has already been surpassed by 10-Gigabit Ethernet (10GbE). This flavor of Ethernet is 10x faster than 1-GbE, and is sometimes referred to as XGbE.
A graphical user interface (GUI) is a type of user interface that allows users to interact with electronic devices with images rather than text commands. A GUI represents the information and actions available to a user through graphical icons. The actions are usually performed through direct manipulation of the graphical elements.
High-definition video or HD video refers to any video system of higher resolution than standard-definition (SD) video, and most commonly involves display resolutions of 1,280×720 pixels (720p) or 1,920×1,080 pixels (1080i/1080p).
While conventional (2D visible light) imaging is most commonly used in machine vision, alternatives include imaging various infrared bands, line scan imaging, 3D imaging of surfaces and X-ray imaging. Key divisions within machine vision 2D visible light imaging are monochromatic vs. color, resolution, and whether or not the imaging process is simultaneous over the entire image, making it suitable for moving processes.
Techniques used in machine vision image processing include: thresholding (converting a grayscale image to black and white, or using separation based on a grayscale value), segmentation, blob extraction, pattern recognition, barcode and data matrix code reading, optical character recognition, gauging (measuring object dimensions), positioning, edge detection, color analysis, filtering (e.g. morphological filtering) and template matching (finding, matching, and/or counting specific patterns).
Is an umbrella term that describes the detail an image holds.
This compression technique reduces the size of an image by discarding details that are typically too insignificant for the human eye to detect. Since the JPEG file format supports 16 million colors, it does a very good job of analyzing what data is the most important to a particular image. The JPEG file format is well suited to digital photography.
A device or set of devices illuminating the scene according to the needs of the very application. Lighting systems differ from each other regarding e.g. light source (e.g. halogen bulb, tungsten lamp, LED or Laser), geometry (line light, panel), operational mode (continuous wave or flashed) and light forming optics.
Machine vision refers the industrial application of vision technology. It describes the understanding and interpretation of technically obtained images for controlling production processes. It has evolved into one of the key technologies in industrial automation, which is used in virtually all manufacturing industries.
Refers to one million pixels, and is commonly used in reference to digital cameras as an indication of resolution capability. A pixel is a tiny square on a computerized display that is so small it appears as a dot. The display screen is a solid grid of these squares or dots, which can be easily seen with a magnifying glass. The more pixels or dots that make up the display screen, the clearer the resolution or image will be. Greater numbers of dots or pixels allow for more refinement of the image, which results in higher, truer image replication. The number of megapixels required to suit your needs depends on what the camera will be used for, and what size prints are desired, if any. The higher the resolution —- or greater the megapixels —- the more flexibility the camera will have in terms of being able to deliver high resolution prints in large sizes, such as 8x10.
denotes identification of objects using characteristic features like shape / geometry, dimensions, color, structure / topology, texture. Object identification includes the distinction of object variants and has many applications, not least as an “auxiliary science” for many other tasks. For example, position recognition or completeness checks may require prior identification of the correct objects in the scene.
A device or set of devices capturing the optical radiation reflected from the scene and projecting a sharp image of this scene on the imaging device in the camera. Standard optics (i.e. lenses) are normally mounted to the camera body. Additional custom optics may be put in front of a standard lens and vary with regard to the application.
Is a device that converts light rays into electronic signals. Similar to a photoresistor, it measures the physical quantity of light and translates it into a form read by the instrument. Usually, the optical sensor is part of a larger system integrating a measuring device, a source of light and the sensor itself. This is generally connected to an electrical trigger, which reacts to a change in the signal within the light sensor.
denotes assignment of some sort of output value (or label) to a given input value (or instance), according to some specific algorithm. Pattern Recognition is a subfield of Artificial Intelligence that applies machine learning methodologies to tackle problems of classifying/clustering patterns or objects into categories or classes, which forms an integral part in most machine intelligence systems for decision making. Pattern recognition stems from the need for automated machine recognition of objects, signals or images, or the need for automated decision-making based on a given set of parameters.
A pixel is generally thought of as the smallest single component of a digital image. The more pixels used to represent an image, the closer the result can resemble the original. The number of pixels in an image is sometimes called the resolution. An image that is 2048 pixels in width and 1536 pixels in height has a total of 2048×1536 = 3,145,728 pixels or 3.1 megapixels. One could refer to it as 2048 by 1536 or a 3.1-megapixel image.
denotes determining position and orientation of an object – or a particular point of an object – in a pre-defined coordinate system, using feature computation and matching methods. Typical features are center of gravity coordinates and orientation angles. An important distinction is the dimensionality that is whether position and orientation have to be determined in 2D or 3D. Typical applications are robot guidance, pick and place operations, insertion machines.
Is any technology that transmits power over an Ethernet cable. PoE is presently deployed in applications where USB is unsuitable and where AC power would be inconvenient, expensive or infeasible to supply. Ethernet technology and cords are universal.
Is one of the more common methods for image acquisition in which different lines of an array are exposed at different moments in time, scanning or »rolling« across the frame. In other words, rows are reset and exposed one at a time.
Used to increase the frame rate by reducing the amount of data transferred from the camera, ROI is a function that minimizes the area of a captured image, to a specified dimension. Once you have set the size and position of that area, only the data inside the area is transferred to the camera.
denotes determination of geometrical quantities with focus on precise and accurate measuring. The importance of this area increases in accordance with rising quality standards as products must meet ever tighter tolerance requirements. Applications can be found wherever work pieces or also tools have to be checked for compliance with nominal dimensions. Due to the required accuracy, these tasks typically impose high demands on sensor equipment as well as on the mechanical construction of the inspection station.
A system on a chip (SoC or SOC) is an integrated circuit (IC) that integrates all components of a computer or other electronic system into a single chip. It may contain digital, analog, mixed-signal, and often radio-frequency functions—all on a single chip substrate. A typical application is in the area of embedded systems.
The contrast with a microcontroller is one of degree. Microcontrollers typically have under 100 kB of RAM (often just a few kilobytes) and often really are single-chip-systems, whereas the term SoC is typically used with more powerful processors, capable of running software such as the desktop versions of Windows and Linux, which need external memory chips (flash, RAM) to be useful, and which are used with various external peripherals.
can be divided into quantitative surface inspection aiming at the determination of topographical features like roughness and qualitative surface inspection where the focus is on the recognition of surface defects, such as dents, scratches, pollution, or deviations from desired surface characteristics, like color or texture. Quantitative measurements of geometrical properties may be required for judging the surface quality.
Universal Serial Bus (USB) is an industry standard developed in the mid-1990s that defines the cables, connectors and communications protocols used in a bus for connection, communication and power supply between computers and electronic devices. Although the USB was developed for the consumer market, it has also been adopted by the industrial market. While USB 1.1 did not have sufficient bandwidth for anything more than a basic Web camera, USB 2.0 has sufficient bandwidth for streaming video. There are many USB 2.0 machine vision cameras in the market.
640x480 pixel resolution
turnkey product based on an image sensor combined with a processor unit integrated in a body and equipped with specific application software. The application is destined for a specific task (e.g. code reading).
a generic software library that can be adapted to many different applications or a dedicated software tool for specific applications (e.g. optical character recognition, robot guidance, surface inspection, dimensional measuring).
(VHSIC hardware description language) is a hardware description language used in electronic design automation to describe digital and mixed-signal systems such as field-programmable gate arrays (FPGAs) and integrated circuits.
still a relatively young discipline, which had its breakthrough in the early 1980s. It deals with images or sequences of images with the objective of manipulating and analysing them in order to a) improve image quality (contrast, colour, etc.), b) restore images (e.g. noise reduction), c) code pictures (data compression, for example) or d) understand and interpret images (image analysis, pattern recognition). Thus vision technology can be applied wherever images are generated and need to be analysed: in biology (counting cells), in medicine (interpreting CT scanning results), in the construction industry (thermographic analysis of buildings) or in security (verification of biometric dimensions). Vision technology is an interdisciplinary technology that combines lighting, optics, electronics, information technology, software and automation technology.