Cognex Corporation

Xiaoguang Wang

Lowell D Jacobson

Nathaniel R Bogan

Aaron S Wallack

David Y Li

Lei Wang

Li Sun

Yukun Bian

Dave Li

This invention provides a system and method for calibration of a 3D vision system using a multi-layer 3D calibration target that removes the requirement of accurate pre-calibration of the target. The system and method acquires images of the multi-layer 3D calibration target at different spatial locations and at different times, and computes the orientation difference of the 3D calibration target between the two acquisitions. The technique can be used to perform vision-based single-plane orientation repeatability inspection and monitoring. By applying this technique to an assembly working plane, vision-based assembly working plane orientation repeatability, inspection and monitoring can occur. Combined with a moving robot end effector, this technique provides vision-based robot end-effector orientation repeatability inspection and monitoring. Vision-guided adjustment of two planes to achieve parallelism can be achieved. The system and method operates to perform precise vision-guided robot setup to achieve parallelism of the robot's end-effector and the assembly working plane.

System and method for three-dimensional calibration of a vision system

A computer-implemented method which may be used with imaging systems is provided. The method may include receiving a first image from a first device configured to generate the first image based upon, at least in part, a first portion of an item. The method may further include receiving a second image from a second device configured to generate the second image based upon, at least in part, a second portion of the item. The method may also include extracting one or more features from the first image and the second image in a multi-view calibration space wherein the one or more features share a global coordinate system. The method may further include applying a global constraints embedded Hough transform to the one or more features present in the first image and the second image.

Imaging system for determining multi-view alignment

Described are computer-based methods and apparatuses, including computer program products, for identifying defects in a material. A set of features is identified based on an image of a material, wherein each feature in the set of features is a candidate portion of a defect in the material. A set of chained features is selected based on the set of features, wherein each chained feature comprises one or more features that represent candidate portions of a same defect in the material. A defect in the material is identified based on the set of chained features and the image.

System and method for identifying defects in a material

A system and method for high-speed alignment of components is provided. During training time of a machine vision system, a small subset of alignment significant blobs along with a quantum of geometric analysis for picking granularity is determined. By utilizing only the alignment significant blobs and the geometric analysis, the use of conventional alignment techniques may achieve significantly better speed and robustness for component alignment. In operation, during training time, grayscale blobs are extracted using a scale space search. Alignment significant blobs are then determined from the grayscale blobs. Once alignment significant blobs are determined, run time smoothing and down sampling are then determined on the alignment significant blobs. The machine vision system is then trained to operate with the alignment significant regions.

High speed method of aligning components having a plurality of non-uniformly spaced features

Described are methods and apparatuses, including computer program products, for determining model uniqueness with a quality metric of a model of an object in a machine vision application. Determining uniqueness involves receiving a training image, generating a model of an object based on the training image, generating a modified training image based on the training image, determining a set of poses that represent possible instances of the model in the modified training image, and computing a quality metric of the model based on an evaluation of the set of poses with respect to the modified training image.

Determining the uniqueness of a model for machine vision

Described are methods and apparatuses, including computer program products, for determining model uniqueness with a quality metric of a model of an object in a machine vision application. Determining uniqueness involves receiving a training image and a first set of model parameters, generating a first model of an object, generating a second model of the object based on the training image and a second set of model parameters modified from the first set of model parameters, determining a set of poses that represent possible instances of the second model in the training image, and computing a quality metric of the first model based on an evaluation of the set of poses with respect to the training image.

A system and method for high-speed alignment and inspection of components, such as BGA devices, having non-uniform features is provided. During training time of a machine vision system, a small subset of alignment significant blobs along with a quantum of geometric analysis for picking granularity is determined. Also, during training time, balls may be associated with groups, each of which may have its own set of parameters for inspection.

System and method for alignment and inspection of ball grid array devices

A system and method for performing multi-image training for pattern recognition and registration is provided. A machine vision system first obtains N training images of the scene. Each of the N images is used as a baseline image and the N&#x2212;1 images are registered to the baseline. Features that represent a set of corresponding image features are added to the model. The feature to be added to the model may comprise an average of the features from each of the images in which the feature appears. The process continues until every feature that meets a threshold requirement is accounted for. The model that results from the present invention represents those stable features that are found in at least the threshold number of the N training images. The model may then be used to train an alignment/inspection tool with the set of features.

Growing community of inventors

Alpharetta, GA, United States of America

Xiaoguang Wang