Abstract: A metrology system is provided including a projected pattern for points-from-focus type processes. The metrology system includes an objective lens portion, a light source, a pattern projection portion and a camera. Different lenses (e.g., objective lenses) having different magnifications and cutoff frequencies may be utilized in the system. The pattern projection portion includes a pattern component with a pattern. At least a majority of the area of the pattern includes pattern portions that are not recurring at regular intervals across the pattern (e.g., as corresponding to a diverse spectrum of spatial frequencies that result in a relatively flat power spectrum over a desired range and with which different lenses with different cutoff frequencies may be utilized). The pattern is projected on a workpiece surface (e.g., for producing contrast) and an image stack is acquired, from which focus curve data is determined that indicates 3 dimensional positions of workpiece surface points.

Abstract: A workpiece inspection and defect detection system includes a light source, a lens that inputs image light arising from a surface of a workpiece, and a camera that receives imaging light transmitted along an imaging optical path. The system utilizes images of workpieces acquired with the camera as training images to train a defect detection portion to detect defect images that include workpieces with defects. Anomaly detector classification characteristics are determined based on features of the training images. Run mode images of workpieces are acquired with the camera, and based on determined features from the images, the anomaly detector classification characteristics are utilized to determine if the images of the workpieces are classified as anomalous. In addition, the defect detection portion determines if images are defect images that include workpieces with defects and for which additional operations may be performed (e.g., metrology operations for measuring dimensions of the defects, etc.

Abstract: A metrology system is provided including a projected pattern for points-from-focus type processes. The metrology system includes an objective lens portion, a light source, a pattern projection portion and a camera. Different lenses (e.g., objective lenses) having different magnifications and cutoff frequencies may be utilized in the system. The pattern projection portion includes a pattern component with a pattern. At least a majority of the area of the pattern includes pattern portions that are not recurring at regular intervals across the pattern (e.g., as corresponding to a diverse spectrum of spatial frequencies that result in a relatively flat power spectrum over a desired range and with which different lenses with different cutoff frequencies may be utilized). The pattern is projected on a workpiece surface (e.g., for producing contrast) and an image stack is acquired, from which focus curve data is determined that indicates 3 dimensional positions of workpiece surface points.

Abstract: A workpiece inspection and defect detection system includes a light source, a lens that inputs image light arising from a surface of a workpiece, and a camera that receives imaging light transmitted along an imaging optical path. The system utilizes images of workpieces acquired with the camera as training images to train a defect detection portion to detect defect images that include workpieces with defects. Anomaly detector classification characteristics are determined based on features of the training images. Run mode images of workpieces are acquired with the camera, and based on determined features from the images, the anomaly detector classification characteristics are utilized to determine if the images of the workpieces are classified as anomalous. In addition, the defect detection portion determines if images are defect images that include workpieces with defects and for which additional operations may be performed (e.g., metrology operations for measuring dimensions of the defects, etc.

Abstract: A workpiece inspection and defect detection system includes a light source, a lens that inputs image light arising from a surface of a workpiece, and a camera that receives imaging light transmitted along an imaging optical path. The system utilizes images of workpieces acquired with the camera as training images to train a defect detection portion to detect defect images that include workpieces with defects, and determines a performance of the defect detection portion as trained with the training images. Based on the performance of the defect detection portion, an indication is provided as to whether additional defect images should be provided for training. After training is complete, the camera is utilized to acquire new images of workpieces which are analyzed to determine defect images that include workpieces with defects, and for which additional operations may be performed (e.g., metrology operations for measuring dimensions of the defects, etc.

Abstract: A method of automatically adjusting lighting conditions improves the results of points from focus (PFF) 3D reconstruction. Multiple lighting levels are automatically found based on brightness criteria and an image stack is taken at each lighting level. In some embodiments, the number of light levels and their respective light settings may be determined based on trial exposure images acquired at a single global focus height which is a best height for an entire region of interest, rather than the best focus height for just the darkest or brightest image pixels in a region of interest. The results of 3D reconstruction at each selected light level are combined using a Z-height quality metric. In one embodiment, the PFF data point Z-height value that is to be associated with an X-Y location is selected based on that PFF data point having the best corresponding Z-height quality metric value at that X-Y location.

Abstract: A method for operating an edge focus tool to focus the optics of a machine vision inspection system proximate to an edge adjacent to a beveled surface feature is provided. The method comprises defining a region of interest (ROI) including the edge in a field of view of the machine vision inspection system; acquiring an image stack of the ROI over a Z range including the edge; generating a point cloud including a Z height for a plurality of points in the ROI, based on determining a best focus Z height measurement for the plurality of points; defining a proximate subset of the point cloud comprising points proximate to the beveled surface feature and corresponding to the shape of the beveled surface feature; defining a Z-extremum subset of the proximate subset of the point cloud; and focusing the optics at a Z height corresponding to the Z-extremum subset.

Abstract: A multi-region focus navigation interface for a machine vision inspection system is provided to assist a user with user-directed or manual focus operations. The multi-region focus navigation interface comprises a plurality of regional focus elements, each corresponding to a respective region of interest and superimposed on a displayed field of view. Each focus element comprises at least first and second operating states corresponding to its focus distance being in a close or intermediate range, respectively. Each operating state comprises a respective graphical focus indicator. For the intermediate range, a focus improvement direction may also be indicated. In one embodiment, in the close range operating state, a user may activate a region focus element to perform autofocus operations, while in the intermediate range operating state, a user may activate a focus element to perform operations that move toward the focus height by a predetermined step size.

Abstract: A method for correcting coaxial light image edge location errors in a precision machine vision inspection system is disclosed. The method comprises comparing an edge position measurement of a workpiece edge feature using coaxial light and stage light. Edge position measurements using stage light have a lower uncertainty than that of coaxial light. Position correction factors may be determined from the difference between the two edge position measurements. The position correction factors may be stored for correcting subsequent edge position measurements that are based on images acquired using coaxial light. In some embodiments, position correction factors may be determined based on comparing edge position measurements for a plurality of edges.

Abstract: A method for correcting coaxial light image edge location errors in a precision machine vision inspection system is disclosed. The method comprises comparing an edge position measurement of a workpiece edge feature using coaxial light and stage light. Edge position measurements using stage light have a lower uncertainty than that of coaxial light. Position correction factors may be determined from the difference between the two edge position measurements. The position correction factors may be stored for correcting subsequent edge position measurements that are based on images acquired using coaxial light. In some embodiments, position correction factors may be determined based on comparing edge position measurements for a plurality of edges.

Abstract: A method for efficient and quick string matching is presented. The algorithm gains its efficiency through the assumption that the text to be searched is large and that the pattern searched for is also somewhat large. A preprocessing step is performed on the text and the pattern that consists of finding the locations of matches with a small patch of characters that occurs commonly in both the text and pattern. The distances between successive small patch matching locations (called interdistances) are stored as lists. Based on comparison of the interdistance lists, the probability of match can be calculated. The method is fast because the interdistance lists are much smaller than the text and pattern data and comparing these two smaller lists is significantly faster than comparing the text and pattern data using existing algorithms.

Abstract: I present a method for matching the spatial relationships between an input set of feature points and a template set of feature points. A feature point consists of a location in space and a label describing the feature at that location in space. A tessellation over the feature point locations is performed. Next, a search identifies polyhedra that have similar contents, the contents being the angles and labels associated with feature points of the polyhedra. Once a match is found, then appropriate adjacent and neighboring polyhedra are examined. Matching the node labels and angular relationships for a set of appropriate adjacent and neighboring polyhedra extends the volume over which matches exist and significantly increases the certainty that a positive match exists.

Abstract: I present a method for matching the spatial relationships between an input set of feature points and a template set of feature points. A feature point consists of a location in space and a label describing the feature at that location in space. A tessellation over the feature point locations is performed. Next, a search identifies polyhedra that have similar contents, the contents being the angles and labels associated with feature points of the polyhedra. Once a match is found, then appropriate adjacent and neighboring polyhedra are examined. Matching the node labels and angular relationships for a set of appropriate adjacent and neighboring polyhedra extends the volume over which matches exist and significantly increases the certainty that a positive match exists.