Back to results
US 6,748,110 B1Granted
Object and object feature detector system and method
AssigneeCognex Technology and Investment Corporation
InventorAaron Wallack
Life of this patent
Estimating the term…
Abstract
A system and method for object inspection detects and reports object and/or object feature shapes from an acquired image of an inspected sample-object using both edge-based and grey level-based data. Such systems and methods are particularly useful for detecting objects and/or object features whose appearances are relatively unknown prior to inspection.
Claims18
An image data analysis method comprising:
- acquiring image data corresponding to a sample-object;
- generating boundary points of at least one segmented region by performing grey level-based segmentation analysis on the image data;
- generating edge data by performing edge detection on the image data;
- and
- computing a boundary description of the at least one segmented region by comparing the locations of edge data and boundary points of the at least one segmented region, wherein the boundary description includes edge data rather than boundary points of the at least one segmented region when the edge data is sufficiently close in proximity to the boundary points of the at least one segmented region.
2 more elements
An image data analysis method comprising:
- acquiring image data corresponding to a sample-object;
- generating boundary points of at least one segmented region by performing grey level-based segmentation analysis on the image data;
- generating edge data by performing edge detection on the image data;
- and
- computing a boundary description of the at least one segmented region by comparing the locations of edge data and boundary points of the at least one segmented region, wherein computing the boundary description is performed by substituting data contained in edgelets in the edge data, for boundary points of the at least one segmented region.
2 more elements
An image data analysis method comprising:
- acquiring image data corresponding to a sample-object;
- generating boundary points of at least one segmented region by performing grey level-based segmentation analysis on the image data;
- generating edge data by performing edge detection on the image data;
- and
- computing a boundary description of the at least one segmented region by comparing the locations of edge data and boundary points of the at least one segmented region and the boundary description includes boundary points of the at least one segmented region when the edge data is not sufficiently close in proximity to the boundary points of the at least one segmented region.
2 more elements
An image data analysis method comprising:
- acquiring image data corresponding to a sample-object;
- generating boundary points of at least one segmented region by performing grey level-based segmentation analysis on the image data;
- generating edge data by performing edge detection on the image data;
- and
- computing a boundary description of the at least one segmented region the step of computing including snapping edge-based image data to the boundary points of the at least one segmented region by substituting detected edgelets in the edge data for boundary points of the at least one segmented region if the edgelets are close in geographical proximity.
2 more elements
Dependencies are inferred from the claim text.