Abstract: This invention provides a system and method for finding multiple line features in an image. Two related steps are used to identify line features. First, the process computes x and y-components of the gradient field at each image location, projects the gradient field over a plurality subregions, and detects a plurality of gradient extrema, yielding a plurality of edge points with position and gradient. Next, the process iteratively chooses two edge points, fits a model line to them, and if edge point gradients are consistent with the model, computes the full set of inlier points whose position and gradient are consistent with that model. The candidate line with greatest inlier count is retained and the set of remaining outlier points is derived. The process then repeatedly applies the line fitting operation on this and subsequent outlier sets to find a plurality of line results. The process can be exhaustive RANSAC-based.

Abstract: This invention provides a system and method for finding line features in an image that allows multiple lines to be efficiently and accurately identified and characterized. When lines are identified, the user can train the system to associate predetermined (e.g. text) labels with respect to such lines. These labels can be used to define neural net classifiers. The neural net operates at runtime to identify and score lines in a runtime image that are found using a line-finding process. The found lines can be displayed to the user with labels and an associated probability score map based upon the neural net results. Lines that are not labeled are generally deemed to have a low score, and are either not flagged by the interface, or identified as not relevant.

Abstract: This invention provides a system and method for selecting the correct profile from a range of peaks generated by analyzing a surface with multiple exposure levels applied at discrete intervals. The cloud of peak information is resolved by comparison to a model profile into a best candidate to represent an accurate representation of the object profile. Illustratively, a displacement sensor projects a line of illumination on the surface and receives reflected light at a sensor assembly at a set exposure level. A processor varies the exposure level setting in a plurality of discrete increments, and stores an image of the reflected light for each of the increments. A determination process combines the stored images and aligns the combined images with respect to a model image. Points from the combined images are selected based upon closeness to the model image to provide a candidate profile of the surface.

Abstract: This invention provides a system and method for finding multiple line features in an image. Two related steps are used to identify line features. First, the process computes x and y-components of the gradient field at each image location, projects the gradient field over a plurality subregions, and detects a plurality of gradient extrema, yielding a plurality of edge points with position and gradient. Next, the process iteratively chooses two edge points, fits a model line to them, and if edge point gradients are consistent with the model, computes the full set of inlier points whose position and gradient are consistent with that model. The candidate line with greatest inlier count is retained and the set of remaining outlier points is derived. The process then repeatedly applies the line fitting operation on this and subsequent outlier sets to find a plurality of line results. The process can be exhaustive RANSAC-based.

Abstract: A system and method for automated determination of position and movement of a contact lens with respect to a subject wearer's eye based upon a complimentary pair of images, acquired in rapid succession, in which one image of the pair is acquired using light that allows viewing of the pupil and/or limbus through the lens and the other image is acquired using light that is absorbed by the lens to generate an opaque image with a defined edge relative to the surrounding sclera. The images of the pair are acquired in close enough temporal proximity to ensure that eye movement in the interval therebetween is insignificant and both images are in the same approximate reference frame. Thus, the location of the pupil and limbus in one image can be accurately compared with the location of the contact lens edge in the other image.

Abstract: This invention provides a system and method for finding multiple line features in an image. Two related steps are used to identify line features. First, the process computes x and y-components of the gradient field at each image location, projects the gradient field over a plurality subregions, and detects a plurality of gradient extrema, yielding a plurality of edge points with position and gradient. Next, the process iteratively chooses two edge points, fits a model line to them, and if edge point gradients are consistent with the model, computes the full set of inlier points whose position and gradient are consistent with that model. The candidate line with greatest inlier count is retained and the set of remaining outlier points is derived. The process then repeatedly applies the line fitting operation on this and subsequent outlier sets to find a plurality of line results. The process can be exhaustive RANSAC-based.

Abstract: This invention provides a system and method for determining the pose of shapes that are known to a vision system that undergo both affine transformation and deformation. The object image with fiducial is acquired. The fiducial has affine parameters, including degrees of freedom (DOFs), search ranges and search step sizes, and control points with associated DOFs and step sizes. Each 2D affine parameter's search range and the distortion control points' DOFs are sampled and all combinations are obtained. The coarsely specified fiducial is transformed for each combination and a match metric is computed for the transformed fiducial, generating a score surface. Peaks are computed on this surface, as potential candidates, which are refined until a match metric is maximized. The refined representation exceeding a predetermined score is returned as potential shapes in the scene. Alternately the candidate with the best score can be used as a training fiducial.

Abstract: This invention provides a calibration fixture that enables more accurate calibration of a touch probe on, for example, a CMM, with respect to the camera. The camera is mounted so that its optical axis is approximately or substantially parallel with the z-axis of the probe. The probe and workpiece are in relative motion, along a plane defined by orthogonal x and y axes, and optionally the z-axis and/or and rotation R about the z-axis. The calibration fixture is arranged to image from beneath the touch surface of the probe and, via a 180-degree prism structure, to transmit light from the probe touch point along the optical axis to the camera. Alternatively, two cameras respectively view the fiducial location relative to the CMM arm and the probe location when aligned on the fiducial. The fixture can define an integrated assembly with an optics block and a camera assembly.

Abstract: This invention provides a system and method for determining the location and characteristics of certain surface features that comprises elevated or depressed regions with respect to a smooth surrounding surface on an object. A filter acts on a range image of the scene. A filter defines an annulus or other perimeter shape around each pixel in which a best-fit surface is established. A normal to the pixel allows derivation of local displacement height. The displacement height is used to establish a height deviation image of the object, with which bumps, dents or other height-displacement features can be determined. The bump filter can be used to locate regions on a surface with minimal irregularities by mapping such irregularities to a grid and then thresholding the grid to generate a cost function. Regions with a minimal cost are acceptable candidates for application of labels and other items in which a smooth surface is desirable.

Abstract: This invention provides a system and method for determining the pose of shapes that are known to a vision system that undergo both affine transformation and deformation. The object image with fiducial is acquired. The fiducial has affine parameters, including degrees of freedom (DOFs), search ranges and search step sizes, and control points with associated DOFs and step sizes. Each 2D affine parameter's search range and the distortion control points' DOFs are sampled and all combinations are obtained. The coarsely specified fiducial is transformed for each combination and a match metric is computed for the transformed fiducial, generating a score surface. Peaks are computed on this surface, as potential candidates, which are refined until a match metric is maximized. The refined representation exceeding a predetermined score is returned as potential shapes in the scene. Alternately the candidate with the best score can be used as a training fiducial.

Abstract: A system and method for generating golden template images in a vision system to inspect an acquired runtime image of an object with a multi-layer printed pattern is provided. The system and method performs a registration process on runtime images using registration models each trained on respective canonical layer mask images, and outputting poses. Based upon the poses, warped layer masks are generated. Combination masks are computed based upon differing combinations of the warped layer masks. Intensity values for pixels of the foreground regions for the combination masks are estimated. The estimated intensity values are then blended associated with the combination masks to generate a golden template image. This golden template image can be used to compare with a runtime image. An exemplary application of this system and method is in print inspection on flat and non-flat surfaces.

Abstract: A system and method for generating golden template images in a vision system to inspect an acquired runtime image of an object with a multi-layer printed pattern is provided. The system and method performs a registration process on runtime images using registration models each trained on respective canonical layer mask images, and outputting poses. Based upon the poses, warped layer masks are generated. Combination masks are computed based upon differing combinations of the warped layer masks. Intensity values for pixels of the foreground regions for the combination masks are estimated. The estimated intensity values are then blended associated with the combination masks to generate a golden template image. This golden template image can be used to compare with a runtime image. An exemplary application of this system and method is in print inspection on flat and non-flat surfaces.

Abstract: Provided is the ability to produce an orthogonal-view representation of a selected feature plane of a three-dimensional object. A plurality of images of the object are acquired, each corresponding to a distinct orientation of the object about a selected object axis. In at least one acquired image, feature points are identified in the selected feature plane as-projected into that acquired image. Feature points are associated with an orthogonal-view representation of the selected feature plane, and feature points from at least one acquired image are correlated with physical orientations on the selected feature plane based on the object orientation corresponding to that acquired image. An orthogonal-view representation of the selected object feature plane can be analyzed for a specified feature configuration even when the acquired object images are perspective-view images. This can be accomplished even through only a subset of feature points may be available in any one given image of the object.

Abstract: Provided is the ability to validate detected features in acquired images to thereby enhance the integrity of any analysis carried out on the detected and validated features. A sequence of images of, e.g., an object is acquired, each image in the sequence corresponding to a distinct orientation of the object about a selected object axis. Images in the sequence are inspected for feature points of the selected feature plane, as-projected into the images, at a first feature detection location and at a second feature detection location. The second feature detection location is configured at an image position at which a feature point detected in the first feature detection location in a first inspected image is expected to appear in a second inspected image. Valid object feature points are identified as being those feature points which are detected in both the first feature detection location in a first inspected image and in the second feature detection location in a second inspected image of the image sequence.

Abstract: A method and apparatus is provided that detects extended defects in a surface, by detecting connected features and classifying the connected features so as to identify defects. A method and apparatus is described which processes an image for edges, thresholds the edge and then determines whether the edges are connected features by examining the orientation of the edges compared to their neighboring edges. Application of the method to read/write heads in a storage-drive assembly application is disclosed. Particular enhancements of the method and apparatus for that application are described, including classifying the defects on a head based on their relationship to the boundary of the head, and applying hysteresis thresholding or diffusion to identify cracks which interfere with the function of the heads.

Abstract: The invention provides a method for visually monitoring the radius of an item which is rotating about a fixed axis and which has a trackable contour known to lie in a plane normal to the rotation, such as a part turned on a lathe. The present invention can also estimate the cross-sectional diameter of a growing crystal, and the height of the cross-section above the melt surface. In addition, the height and radius of the meniscus at the crystal/melt interface can be tracked by the system of the invention. The present makes it possible to further automate crystal growing processes in a manner that increases manufacturing efficiency, consistency, and overall quality. In general, the invention provides a machine vision method for estimating both a longitudinal position and a radius of a circular cross-sectional feature of a solid of revolution.