Image analysis – Pattern recognition – Template matching
Reexamination Certificate
1997-12-31
2001-01-16
Tran, Phuoc (Department: 2721)
Image analysis
Pattern recognition
Template matching
C382S203000, C382S209000, C382S219000, C382S278000, C117S014000, C348S050000
Reexamination Certificate
active
06175652
ABSTRACT:
FIELD OF THE INVENTION
This invention relates to machine vision for industrial processes, and more particularly relates to machine vision techniques for analyzing feature information about an object based on an acquired image of the object.
BACKGROUND OF THE INVENTION
Machine vision systems are increasingly employed to replace human vision in a wide range of industrial processes such as manufacturing operations. A machine vision system typically provides automated, computer-based image acquisition and analysis capabilities that can be employed for tasks such as measurement and inspection of parts or materials. For such tasks, a machine vision system typically is configured with a camera for acquiring an image of an object of interest, e.g., a part being produced, and further is configured with processing functionality to process the acquired image and produce information about the object. Frequently, in measurement and inspection tasks, the object image acquisition is tailored to include specific object features that are of interest for a given analysis task.
There exist well-established machine vision techniques for acquiring and analyzing an image of a substantially two-dimensional object or a substantially two-dimensional face of a three-dimensional object. Here a camera is optimally positioned orthogonal to the plane of the object or object face under consideration to acquire an image that includes the entire object or object face. Features across the entire object or object face are then in full view in the image and are together available in the image for analysis. Even perspective image views acquired at a non-orthogonal, i.e., oblique, camera position can generally capture a complete view of a two-dimensional face or an object that is effectively two-dimensional.
For many three-dimensional parts and many manufacturing environments, this full-view image acquisition cannot be accomplished, however. Specifically, for complicated three-dimensional object shapes, and more specifically for complicated opaque objects, and for various feed material and tooling configurations, one or more object regions may obscure other object regions from the line-of-sight view of an image acquisition camera's position. As a consequence, it may not be possible from a single camera position to simultaneously view related object features such as circumferential points of a complete cross-sectional object profile. In other words, unlike that of substantially two-dimensional objects or a two-dimensional object face, related features of a complicated and opaque three-dimensional object are not guaranteed to be together fully exposed for simultaneous image acquisition. Instead, only a portion of the object and a subset of related object features are likely to be fully exposed to a single image acquisition camera angle.
The complications of this scenario are compounded in many applications where the location of a single image acquisition camera is limited by the manufacturing environment; e.g., where an optimum camera location cannot be accommodated. For example, in a scenario where an orthogonal, top-down view of a three-dimensional object may be known to encompass a complete set of object features, such vertical location of the camera may not be practical. For a large class of manufacturing applications, accommodation can be made for only a single, oblique camera location that results in a acquisition of only a perspective view of an object; and for some camera angles this can result in a large fraction of related object features being obscured in the object image.
A further complication is added for machine vision applications in which an object to be viewed is moving, e.g., rotating, during the process being monitored. In this case, a different subset of related features, e.g., a different portion of an object's cross-sectional profile or shape, is in view of the camera's line-of-sight at any given time. Traditional vision system techniques, developed typically for orthogonal image acquisition and analysis of substantially two-dimensional object surfaces, are found to be ineffective at addressing these combinations of complicated object configurations, object movement, and manufacturing constraints using only a single image acquisition camera.
SUMMARY OF THE INVENTION
The invention provides the ability to produce a complete orthogonal representation of a selected feature plane of a three-dimensional object even when only one image acquisition camera can be accommodated. This is accomplished in accordance with the invention even for image acquisition configurations in which an oblique, e.g., perspective view, of the object is captured for analysis. In accordance with the invention, a machine vision method is carried out in which 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.
With the techniques provided by the invention, an orthogonal-view representation of the selected object feature plane can be analyzed for a specified feature configuration. This can be accomplished even through only a subset of feature points may be available in any one given image of the object. Such may be the case, e.g., where portions of a complicated three-dimensional object obscure other portions of the object in a selected view of the object. A wide range of machine vision applications for inspection, monitoring, or measurement of objects, object features, object configurations, and other scenarios, are thereby enabled by the invention.
In embodiments provided by the invention, the acquired object images can be perspective-view images. In this case, feature points are identified as-projected into the perspective-view images. Feature points are here associated with an orthogonal feature plane view by mapping feature points from a two-dimensional image coordinate system that is parallel with the selected perspective view to a three-dimensional coordinate system that is aligned with the selected object axis.
In general, object images can be acquired as a sequence of images, e.g., a video sequence. A portion of each image in the sequence preferably is in common with a portion of an adjacent image in the sequence. If the object is rotating about the selected axis, then to capture images of all sides of the object, the number of images in the sequence is preferably at least a minimum number, M, of images, where M is selected as M=T
0
/T
a
, where T
0
is a period of revolution of the object and T
a
is a period required for acquiring one image.
The sequence of images can be taken from a fixed viewing location as the object rotates about the selected object axis or alternatively, an image acquisition camera can be rotated about the selected object axis, e.g., while the object remains stationary. The selected object axis can be perpendicular to the selected object feature plane, e.g., with the selected object axis operating as a vertical axis of revolution and the selected feature plane being a horizontal plane located at a position along the axis of revolution. The feature points to be identified in the feature plane can be circumferential feature points of the object.
In other embodiments provided by the invention, feature points are identified by searching for feature points in an area of the image where the feature points are expected. Here several edge detection regions can be applied at image locations corresponding to an expected location of a projection of the selected feature plane into the image. Each edge detection region is searched for an edge of a feature point, and positions of the
Jacobson Lowell D.
Ruzhitsky Vladimir N.
Cognex Corporation
Lober Theresa A.
Mariam Daniel G.
Tran Phuoc
LandOfFree
Machine vision system for analyzing features based on... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Machine vision system for analyzing features based on..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Machine vision system for analyzing features based on... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2446644