Machine vision (MV) is the process of applying a range of technologies and methods to provide imaging-based automatic inspection, process control and robot guidance in industrial applications.[1][2] While the scope of MV is broad and a comprehensive definition is difficult to distil,[2][3] a "generally accepted definition of machine vision is '... the analysis of images to extract data for controlling a process or activity.'"[4]
Contents |
The primary uses for machine vision are automatic inspection and robot guidance.[5] Common MV applications include quality assurance, sorting, material handling, robot guidance, and optical gauging.[4]
Machine vision methods are defined as both the process of defining and creating a MV solution,[6][7] and as the technical process that occurs during the operation of the solution. Here the latter is addressed. As of 2006, there was little standardization in the interfacing and configurations used in MV. This includes user interfaces, interfaces for the integration of multi-component systems and automated data interchange.[8] Nonetheless, the first step in the MV sequence of operation is acquisition of an image, typically using cameras, lenses, and lighting that has been designed to provide the differentiation required by subsequent processing.[9][10] MV software packages then employ various digital image processing techniques to allow the hardware to recognize what it is looking at, extract the required information, and often make decisions (such as pass/fail) based on the extracted information.[11]
While conventional (2D visible light) imaging is most commonly used in MV, alternatives include imaging various infrared bands,[12] line scan imaging, 3D imaging of surfaces and X-ray imaging.[5] Key divisions within MV 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.[13]
The imaging device (e.g. camera) can either be separate from the main image processing unit or combined with it in which case the combination is generally called a smart camera or smart sensor. When separated, the connection may be made to specialized intermediate hardware, a frame grabber using either a standardized (Camera Link) or custom interface.[14][15] MV implementations also have used digital cameras capable of direct connections (without a framegrabber) to a computer via FireWire, USB or Gigabit Ethernet interfaces.[15]
Techniques used in MV 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).[16][14]
The most common outputs from machine vision systems are pass/fail decisions. These decisions may in turn trigger mechanisms that reject failed items or sound an alarm. Other common outputs include object position and orientation information from robot guidance systems.[5] Additionally, output types include numerical measurement data, data read from codes and characters, displays of the process or results, stored images, alarms from automated space monitoring MV systems, and process control signals.[10][6]
As recently as 2006, one industry consultant reported that MV represented a $1.5 billion market in North America.[17] However, the editor-in-chief of an MV trade magazine asserted that "machine vision is not an industry per se" but rather "the integration of technologies and products that provide services or applications that benefit true industries such as automotive or consumer goods manufacturing, agriculture, and defense."[3]
As of 2006, experts estimated that MV had been employed in less than 20% of the applications for which it is potentially useful.[18]