Machine vision is the application of computer vision to factory automation. Just as human inspectors working on assembly lines visually inspect parts to judge the quality of workmanship, so machine vision systems use digital cameras and image processing software to perform similar inspections. A machine vision system is a computer that makes decisions based on the analysis of digital images.

Machine vision systems are programmed to perform narrowly defined tasks such as counting objects on a conveyor, reading serial numbers, and searching for surface defects. Though machine vision systems have neither the intelligence nor the learning capability of human inspectors, they are considered useful in many applications. Manufacturers favor machine vision systems for visual inspections that require high-speed, high-magnification, 24-hour operation, and repeatability of measurements.

Components of a machine vision system

A simple machine vision system will consist of the following:

1. An optical sensor
2. A black-and-white camera
3. Lighting
4. Camera interface card for computer, known as "framegrabber"
5. Computer software to process images
6. Digital signal hardware or a network connection to report results

The optical sensor determines when a part moving on a conveyor is in position to be inspected. The optical sensor triggers the camera to take a picture of the part as it passes beneath the camera and lighting. The lighting used to illuminate the part is designed to highlight features of interest and obscure or minimize the appearance of features that are not of interest.

The camera's image is captured by the framegrabber. A framegrabber is a computer card that converts the output of the camera to digital format and places the image in computer memory so that it may be processed by the machine vision software.

The software will typically take several steps to process an image. Often the image is first manipulated to reduce noise or to convert many shades of gray to a simple combination of black and white. Following the initial simplification, the software will count, measure, and/or identify objects in the image. As a final step, the software passes or fails the part according to programmed criteria. If a part fails, the software signals a robotic device to reject the part; alternately, the system may warn a human worker to fix the production problem that caused the failure.

Though most machine vision systems rely on black-and-white cameras, the use of color cameras is becoming more common.

Also separate computer is not always needed, cameras with built-in embedded computer, "smart cameras", are common nowadays. The use of smart camera eliminates the need of separate computer and interface card making the system more affordable and robust.

Processing methods

Commercial and open source machine vision software packages typically include a number of different image processing techniques such as the following:

• Pixel counting: counts the number of light or dark pixels
• Thresholding: converts an image with gray tones to simply black and white
• Connectivity & segmentation: used to locate and/or count parts by differentiating between light and dark connected regions of pixels
• Barcode reading: decoding of 1D and 2D codes designed to be read or scanned by machines
• Optical character recognition: automated reading of text such as serial numbers
• Gauging: measurement of object dimensions in inches or millimeters
• Edge detection: finding object edges
• Template matching: finding, matching, and/or counting specific patterns
• Robust pattern recognition: location of an object that may be rotated, partially hidden by another object, or varying in size

In most cases, a machine vision system will use a combination of these processing techniques to perform a complete inspection. A system that reads a barcode may also check a surface for scratches and measure the length and width of a machined component.

Applications of machine vision

Machine vision systems are widely used in semiconductor device fabrication; indeed, without machine vision, yields for computer chips would be significantly reduced. Machine vision systems inspect silicon wafers, processor chips, and subcomponents such as resistors and capacitors.

In the automotive industry, machine vision systems are used to guide industrial robots, gauge the fit of stamped metal components, and inspect the surface of the painted vehicle for defects.

Though machine vision techniques were developed for the visible spectrum, the same processing techniques may be applied to images captured using imagers sensitive to other forms of light such as infrared.

Related fields

Machine vision is distinct from computer vision, an academic field of research often classified as a subfield of artificial intelligence. Computer vision extends to topics related to autonomous robotics and machine representation of human vision. Machine vision refers to automated imaging systems used in factories, assembly plants, and other industrial environments.

See also

• artificial intelligence
• barcode
• computer science
• computer vision
• digital image processing, image processing
• morphological image processing
• industrial robot, robot
• medical imaging
• optical character recognition
• pattern recognition

External links

• The Mimas Vision Toolkit
• Automated Imaging Association
• Intel Open Source Computer Vision Library
• LTI-Lib: Open Source C++ Computer Vision Library
• HALCON The Software Solution for Machine Vision Applications
• ActivVisionTools: Machine Vision Software without writing any code
• DVT: Providing machine vision systems for industrial applications. Free software and training
• Xiris: Developer of custom machine vision automation systems and software
• ATS Automation Tooling Systems: The world's largest industrial automation systems integrator
• Computer vision wikicity