Abstract: A machine vision inspection system (MVIS) and a related light stripe edge feature location method are disclosed. The MVIS comprises a control system, a light stripe projection system, an imaging system, and a user interface. In a region of interest including the edge feature, the light stripe projection system focuses a light stripe transverse to the edge direction and across the edge feature, such that the light stripe has a changing stripe intensity profile along the light stripe. The imaging system acquires an image of the light stripe and the control system analyzes the image to determine the location of the edge feature based on a changing light intensity profile along the stripe. The method may be implemented in an edge detection video tool. The method may be advantageous for inspecting highly textured, beveled, chamfered, rounded or damaged edges, for example.

Abstract: A system and method for correcting surface height measurements for optical aberration is provided. Heights determined by an autofocus tool, which may depend on surface feature angles in a focus region of interest (ROI) and on the ROI location in the field of view, are corrected based on a novel error calibration. Error calibration data includes height corrections for different feature angles in images, and for multiple locations in a field of view. Height corrections are determined by weighting and combining the angle dependent error calibration data, e.g., based on a gradient (edge) angle distribution determined in the ROIs. When Z-heights are determined for multiple ROIs in a field of view, storage of image data from particular images of a global image stack may be efficiently controlled based on determining early in processing whether a particular image is a sufficiently focused “near-peak” focused image or not.

Abstract: A system and method for correcting surface height measurements for optical aberration is provided. Heights determined by an autofocus tool, which may depend on surface feature angles in a focus region of interest (ROI) and on the ROI location in the field of view, are corrected based on a novel error calibration. Error calibration data includes height corrections for different feature angles in images, and for multiple locations in a field of view. Height corrections are determined by weighting and combining the angle dependent error calibration data, e.g., based on a gradient (edge) angle distribution determined in the ROIs. When Z-heights are determined for multiple ROIs in a field of view, storage of image data from particular images of a global image stack may be efficiently controlled based on determining early in processing whether a particular image is a sufficiently focused “near-peak” focused image or not.

Abstract: A machine vision inspection system (MVIS) and a related light stripe edge feature location method are disclosed. The MVIS comprises a control system, a light stripe projection system, an imaging system, and a user interface. In a region of interest including the edge feature, the light stripe projection system focuses a light stripe transverse to the edge direction and across the edge feature, such that the light stripe has a changing stripe intensity profile along the light stripe. The imaging system acquires an image of the light stripe and the control system analyzes the image to determine the location of the edge feature based on a changing light intensity profile along the stripe. The method may be implemented in an edge detection video tool. The method may be advantageous for inspecting highly textured, beveled, chamfered, rounded or damaged edges, for example.

Abstract: Fast approximate focus operations providing an approximately focused image that is sufficiently focused to support certain subsequent inspection operations. The operations are particularly advantageous when used to provide images for successive inspection operations that predominate when inspecting planar workpieces. Improved inspection throughput is provided because, in contrast to conventional autofocus operations, the fast approximate focus operations do not acquire an image stack during a run mode as a basis for determining a best focused image. Rather, during learn mode, a representative feature-specific focus curve and a focus threshold value are determined and used during run mode to provide an approximately focused image that reliably supports certain inspection operations. In one embodiment, an acceptable approximately focused inspection image is provided within a limit of two focus adjustment moves that provide two corresponding images.

Abstract: Fast approximate focus operations providing an approximately focused image that is sufficiently focused to support certain subsequent inspection operations. The operations are particularly advantageous when used to provide images for successive inspection operations that predominate when inspecting planar workpieces. Improved inspection throughput is provided because, in contrast to conventional autofocus operations, the fast approximate focus operations do not acquire an image stack during a run mode as a basis for determining a best focused image. Rather, during learn mode, a representative feature-specific focus curve and a focus threshold value are determined and used during run mode to provide an approximately focused image that reliably supports certain inspection operations. In one embodiment, an acceptable approximately focused inspection image is provided within a limit of two focus adjustment moves that provide two corresponding images.

Abstract: An image focus assessment method is provided that works reliably for images of a variety of relatively dissimilar workpieces or workpiece features. The focus assessment method is based on analysis of a single image (without the benefit of comparison to other images). The robustness of the focus assessment method is enhanced by the use of at least one classifier based on a plurality of focus classification features. In one application, a primary advantage of assessing focus from a single image is that an overall workpiece inspection time may be reduced by avoiding running an autofocus routine if an image is already in focus. In various embodiments, the focus assessment method may include an ensemble of classifiers. The ensemble of classifiers can be trained on different training data (sub)sets or different parameter (sub)sets, and their classification outcomes combined by a voting operation or the like, in order to enhance the overall accuracy and robustness of the focus assessment method.

Abstract: A fast template matching method by adaptive template decomposition is provided. The template decomposition technique subdivides a template into a number of horizontal and/or vertical subdivisions and one-dimensional characterizations are determined for the subdivisions. The template decomposition may be adapted during learn mode operations of a general-purpose precision machine vision inspection system, with the support of corresponding user interfaces. The matching results for one or more template decomposition configurations may be evaluated by a user, or by an automatic decomposition configuration evaluation routine, to determine a configuration that provides a desirable trade-off between speed and matching position accuracy. Automatic workpiece inspection instructions may implement the configuration to repeatedly provide optimum speed versus accuracy trade-offs during run mode operations of the inspection system.

Abstract: A system and method for correcting surface height measurements for optical aberration is provided. Heights determined by an autofocus tool, which may depend on surface feature angles in a focus region of interest (ROI) and on the ROI location in the field of view, are corrected based on a novel error calibration. Error calibration data includes height corrections for different feature angles in images, and for multiple locations in a field of view. Height corrections are determined by weighting and combining the angle dependent error calibration data, e.g., based on a gradient (edge) angle distribution determined in the ROIs. When Z-heights are determined for multiple ROIs in a field of view, storage of image data from particular images of a global image stack may be efficiently controlled based on determining early in processing whether a particular image is a sufficiently focused “near-peak” focused image or not.

Abstract: Methods and systems for automatically recovering a failed video inspection tool in a precision machine vision inspection system are described. A set of recovery instructions may be associated or merged with a video tool to allow the tool to automatically recover and proceed to provide an inspection result after an initial failure. The recovery instructions include operations that evaluate and modify feature inspection parameters that govern acquiring an image of a workpiece feature and inspecting the feature. The set of instructions may include an initial phase of recovery that adjusts image acquisition parameters. If adjusting image acquisition parameters does not result in proper tool operation, additional feature inspection parameters, such as the tool position, may be adjusted. The order in which the multiple feature inspection parameters and their related characteristics are considered may be predefined so as to most efficiently complete the automatic tool recovery process.