Learning algorithms for machine vision are essential for many of the applications that require inspection and guidance. These algorithms typically require some type of learning step before the actual inspection can take place. Some of the algorithms that fall into this category include pattern matching, color matching, color pattern matching, and Optical Character Recognition (OCR). Industries rely on these algorithms to speed-up manufacturing, increase yields, and improve quality. For example, semiconductor applications require the identification of a fiducial, which aids in the alignment of wafers, and pharmaceutical vendors in the drug discovery arena may want to match up colors according to different reactions that occur.
For pattern matching, the first step always includes a learning process. A "gold" master is used to create a template. This template is used for identification purposes on all subsequent parts. A score is generated depending on how well the object or feature under inspection matches the original template. You can take advantage of pattern matching in applications that include alignment, gauging, and inspection.
Gauging measures lengths, diameters, angles, and other critical dimensions. You can use pattern matching to locate the object you want to gauge. Gauging applications locate and then measure, or gauge, the distance between these objects. If the measurement falls within a tolerance range, the part is considered good. If it falls outside the tolerance range, the component is rejected. Searching and finding a feature is the key processing task that determines the success of many gauging applications, such as inspecting the leads on a quad pack or inspecting an antilock-brake sensor.
Using inspection, you can detect simple flaws, such as missing parts or illegible printing. You can also inspect fiber optic core or cladding, to ensure that the fiber optic cable has a consistent shape and is free of flaws. In addition, you could also take advantage of inspection in a packaging application, where it is important how a label is placed on a package or bottle.
Closely related to grayscale pattern matching, color pattern matching is another aspect of visual inspection. You can use color pattern matching, for instance, to inspect different colored fuses in automotive applications or colored icons on a consumer electronics device. Color can also have important significance for coding different types of parts to ensure that the correct parts go with the correct colors.
Relying on learning algorithms, this software module - NI Vision Development Module - enables high-speed pattern matching for locating objects of various size and orientation, even in poor light. The module includes IMAQ Vision Builder, an interactive environment for quickly prototyping vision applications without programming, and IMAQ Vision, a library of functions for image processing. IMAQ Vision Builder can automatically generate an IMAQ Vision block diagram that contains the same functionality as the series of operations users already prototyped in IMAQ Vision Builder. The diagram can be integrated into the users automation or production test application, which may include motion control, instrument control, and data acquisition.
This work was done by Jason Mulliner, Vision product manager, for National Instruments. For more information call (512) 683-0100 or visit National Instruments online at www.ni.com.
NI Vision Development Module is a development tool for LabVIEW, LabWindows/CVI, and Measurement Studio.