Abstract: A vision system capable of performing run-time 3D calibration includes a mount configured to hold an object, the mount including a 3D calibration structure; a camera; a motion stage coupled with the mount or the camera; and a computing device configured to perform operations including: acquiring images from the camera when the mount is in respective predetermined orientations relative to the camera, each of the acquired images including a representation of at least a portion of the object and at least a portion of the 3D calibration structure that are concurrently in a field of view of the camera; performing at least an adjustment of a 3D calibration for each of the acquired images based on information relating to the 3D calibration structure as imaged in the acquired images; and determining 3D positions, dimensions or both of one or more features of the object.

Abstract: A vision system capable of performing run-time 3D calibration includes a mount configured to hold an object, the mount including a 3D calibration structure; a camera; a motion stage coupled with the mount or the camera; and a computing device configured to perform operations including: acquiring images from the camera when the mount is in respective predetermined orientations relative to the camera, each of the acquired images including a representation of at least a portion of the object and at least a portion of the 3D calibration structure that are concurrently in a field of view of the camera; performing at least an adjustment of a 3D calibration for each of the acquired images based on information relating to the 3D calibration structure as imaged in the acquired images; and determining 3D positions, dimensions or both of one or more features of the object.

Abstract: This invention provides a system and method to determine orientation/pose of a contact lens residing on the transparent bottom of a fluid-filled, typically opaque-sided cuvette. This allows the system to determine whether the subject contact lens is in a concave up or concave down orientation, and whether the lens is everted. An illuminator is aligned on a longitudinal axis of the cuvette through the contact lens at a position over the cuvette, and a vision system camera is aligned beneath the bottom of the cuvette on the axis. In alternate embodiments the axial locations of the camera and the illuminator can be varied. The camera acquires images of the contact lens. The vision system associated finds the appropriate contact lens edges and characteristics of features. These features allow each of the four poses to be distinguished and categorized for either an acceptable/good or unacceptable/bad pose within the cuvette.

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: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: An embodiment of the invention provides a method for training a system to inspect a spatially distorted pattern. A digitized image of an object, including a region of interest, is received. The region of interest is further divided in to a plurality of sub-regions. A size of each of the sub-regions is small enough such that a conventional inspecting method can reliably inspect each of the sub-regions. A search tool and an inspecting tool are trained for a respective model for each of the sub-regions. A search tree is built for determining an order for inspecting the sub-regions. A coarse alignment tool is trained for the region of interest. Another embodiment of the invention provides a method for inspecting a spatially distorted pattern. A coarse alignment tool is run to approximately locate a pattern. Search tree information and an approximate location of a root image, found by the coarse alignment tool, is used to locate sub-regions sequentially in an order according to the search tree information.

Abstract: A method and system is provided for aligning a geometric object model with a pixel image. A geometric object model representing an object is obtained first. Using the geometric object model of the object, a revised geometric object model is created. An alignment tool is then trained based on the revised geometric object model. The alignment model can be applied to a pixel image of the object so that the pose of the object can be computed by aligning the revised geometric object model with the image.

Abstract: A method and apparatus are disclosed for analyzing a boundary of an object. An embodiment for determining defects of a boundary to sub-pixel precision and an embodiment for fast correlation scoring are disclosed. The boundary is analyzed by matching a first boundary, such as a model of an ideal object boundary, to a second boundary, such as the boundary of an object being produced at a factory. The boundaries are represented as a set of indexed vertices, which are generated by parsing the boundaries into a set of segments. One embodiment refines the parse through merging segments and reassigning data points near the endpoints of the segments. The model produced is very accurate and is useful in other applications. To analyze the boundaries, the sets of indexed vertices are matched, and optionally the segmentation of the second boundary is refined to increase the extent of matching.

Abstract: The three-dimensional orientation of a given object is determined. The given object may comprise an object having surface characteristics which provide poor contrast in representative images of the given object. In a specific embodiment, the object may comprise a golf ball. A model representation is obtained of a reference object, and a run-time image is obtained of the given object. From the run-time image, shape information is obtained for certain identified shapes collectively forming a subset of the visible shapes. The shape information is matched to a number of incremental poses of the model representation varying along three degrees of freedom.