Methods and apparatuses for refining a geometric description of an object having a plurality of extensions

• US 6,526,165 B1
• Filed: 11/30/1998
• Issued: 02/25/2003
• Est. Priority Date: 11/30/1998
• Status: Expired due to Term

• Current Assignee: Cognex Corporation
• Original Assignee: Cognex Corporation
• Inventors: Marrion, Cyril C. Jr., Montillo, Albert A., Bachelder, Ivan A.
• Primary Examiner(s): Mehta, Bhavesh
• Assistant Examiner(s): CHAWAN, SHEELA C
• Application Number:
  US09/203,182
• Time in Patent Office: 1,548 Days
• Field of Search: 382/146, 382/151, 382/168, 382/170, 382/173, 382/289, 382/149, 382/147, 382/199, 348/87, 348/583, 348/94, 348/95, 348/126, 395/137, 395/904, 250/559.34, 250/559.36, 250/559.37, 356/237.4
• US Class Current: 382/145
• CPC Class Codes: G06T 2207/30141 Printed circuit board [PCB]
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/7515 Shifting the patterns to accommodate for positional errors

Abstract

A method and apparatus are disclosed for refining a rough geometric description (GD) and a rough pose of an object having extensions. The invention locates anchor points within an image of the object and uses the anchor points to align in at least one dimension the rough GD. In one embodiment, the anchor points are the tips of the extensions of the object; the rough GD of the object is then aligned along the angular orientation indicated by the tips. Thereafter, other dimensions of the rough GD and the rough pose are measured, measuring the dimensions having less unknowns first. The rough GD and the rough pose are then updated to provide the refined GD and refined pose. For one measurement, an extent of a region is measured using the expected area of region to threshold the region and segment it from the remainder of the image before measuring the extent of the region. An application of refining a GD of a leaded object is disclosed.

Claims

1. A method for refining a rough geometric description and a rough pose of an object having a plurality of extensions so as to provide a refined geometric description and a refined pose, the method comprising:

acquiring an image of the object;

locating at least two anchor points in the image related to at least two of the plurality of extensions;

aligning in a least one dimension the rough geometric description relative to the object in the image using the at least two anchor points to provide a partially aligned rough geometric description;

measuring dimensions of the object in the image using the partially aligned rough geometric description to provide measured dimensions; and

updating the rough geometric description to substantially match the measured dimensions of the object, thereby generating a refined geometric description and a refined pose of at least a portion of the object.

2. The method of claim 1, wherein the plurality of extensions are contacts and the object is an electronic component.

3. The method of claim 1, wherein the anchor points comprise points of high contrast on substantially all the plurality of extensions.

4. The method of claim 1, wherein the anchor points comprises centroids of bright regions on substantially all the plurality of extensions.

5. The method of claim 1, wherein the rough geometric description and the rough pose are provided by electronically reading a drawing.

6. The method of claim 1, wherein locating at least two anchor points in the image related to at least two of the plurality of extensions comprises,

locating at least two points of high contrast to provide rough anchor points by projecting pixels within a locating window having a projection axis positioned substantially at an angle of the rough pose and covering at least a portion of two of the plurality of extensions;

fitting a curve to the at least two points; and

locating a point of highest contrast for each of the plurality of extensions being the at least two anchor points by projecting pixels within a locating window for each of the extensions having a projection axis positioned substantially at an angle of the curve.

7. The method of claim 6, wherein the locating window is a window of the CALIPER TOOL.

8. The method of claim 1, wherein locating at least two anchor points in the image related to at least two of the plurality of extensions comprises,

locating at least two centroids of a region of brightness to provide rough anchor points by examining pixels within a locating window having at least one side positioned substantially at an angle of the rough pose and covering at least a portion of two of the plurality of extensions;

fitting a curve to the at least two centroids; and

locating a centroid for each of the plurality of extensions being the at least two anchor points by examining pixels within a locating window for each of the extensions having at least one side positioned substantially at an angle of the curve.

9. The method of claim 1, wherein aligning in at least one dimension the rough geometric description relative to the object in the image using the at least two anchor points to provide a partially aligned rough geometric description involves, calculating a refined dimension of the rough pose using the at least two anchor points;

and

aligning the rough geometric description according to the refined dimension relative to the object in the image to provide a partially aligned rough geometric description.

10. The method of claim 9, wherein calculating a refined dimension of the rough pose using the at least two anchor points involves, calculating an angle of a curve substantially fitting the at least two anchor points,

where the angle of the curve is the refined dimension.

11. The method of claim 1, wherein measuring dimensions of the object in the image using the partially aligned rough geometric description to provide measured dimensions includes,

measuring dimensions of the plurality of extensions.

12. The method of claim 11, wherein updating the rough geometric description to substantially match the measured dimensions of the object, thereby generating a refined geometric description of at least a portion of the object involves,

updating the rough geometric description and rough pose to substantially match the measured dimensions of the object and the plurality of extensions, thereby generating a refined geometric description and refined pose of at least a portion of the object and the plurality of extensions.

13. The method of claim 1, wherein measuring dimensions of the object in the image using the partially aligned rough geometric description to provide measured dimensions involves,

locating an end of substantially each of the extensions by projecting pixels within a window superimposed over the image oriented with a projection axis aligned with the aligned rough geometric description;

using positions of the ends of substantially each of the extensions in the image and the rough geometric description to measure other dimensions of the object in the image.

14. The method of claim 1, wherein measuring dimensions of the object in the image using the partially aligned rough geometric description to provide measured dimensions involves,

locating sides of substantially each of the extensions by projecting pixels within a window superimposed over the image oriented with a projection axis aligned with the aligned rough geometric description;

using positions of the sides of substantially each of the extensions in the image and the rough geometric description to measure other dimensions of the object in the image.

15. The method of claim 1, wherein measuring dimensions of the object in the image using the partially aligned rough geometric description to provide measured dimensions includes,

calculating a histogram of at least one region of the object within a window superimposed over the image oriented with at least one side aligned with the aligned rough geometric description, the histogram having a plurality of brightnesses;

identifying a potential threshold region between two opposed outlying regions of the histogram by identifying the two opposed outlying regions using expected areas of the each of the two outlying opposed brightness regions, a portion of the expected areas being the rough geometric description;

identifying a threshold within the potential threshold region to segment the region of the object;

thresholding the image containing the region to generate an object image containing the region of the object to measure; and

measuring the extent of the region within the object image.

16. The method of claim 15, wherein the region is a foot of a lead.

17. The method of claim 1, wherein measuring dimensions of the object in the image using the partially aligned rough geometric description to provide measured dimensions involves,

measuring least unknown dimensions before measuring more unknown dimensions.

18. The method of claim 1, further comprising,

displaying the refined geometric description graphically.

19. The method of claim 1, further comprising,

displaying the refined pose graphically.

20. The method of claim 1, further comprising,

validating the refined geometric description against predetermined values.

21. The method of claim 1, wherein the rough geometric description is approximately 20 percent different in at least one dimension than a geometric description of the object.

22. A method for refining a rough geometric description of an object having a plurality of extensions, the method comprising:

acquiring an image of the object;

locating at least two anchor points in the image related to at least two of the plurality of extensions;

aligning in at least one dimension the rough geometric description relative to the object in the image using the at least two anchor points to provide a partially aligned rough geometric description;

measuring dimensions of the object using the partially aligned rough geometric description to provide measured dimensions; and

updating the rough geometric description to substantially coincide with the measured dimensions of the object, thereby generating a refined geometric description of at least a portion of the object.

23. The method of claim 22, wherein acquiring an image of the object includes acquiring a rough pose of the object, and wherein updating the rough geometric description to substantially coincide with the measured dimensions of the object, includes updating the rough geometric description and the rough pose to substantially coincide with the measured dimensions of the object, thereby generating a refined geometric description and a refined pose of at least a portion of the object.

24. The method of claim 23, wherein locating at least two anchor points in the image related to at least two of the plurality of extensions comprises,

locating at least two points of high contrast to provide rough anchor points by projecting pixels within a locating window having a projection axis positioned substantially at an angle of the rough pose and covering at least a portion of two of the plurality of extensions;

fitting a curve to the at least two points; and

locating a point of highest contrast for each of the plurality of extensions being the at least two anchor points by projecting pixels within a locating window for each of the extensions having a projection axis positioned substantially at an angle of the curve.

25. The method of claim 23, wherein locating at least two anchor points in the image related to at least two of the plurality of extensions comprises,

locating at least two centroids of a region of brightness to provide rough anchor points by examining pixels within a locating window having at least one side positioned substantially at an angle of the rough pose and covering at least a portion of two of the plurality of extensions;

fitting a curve to the at least two centroids; and

locating a centroid for each of the plurality of extensions being the at least two anchor points by examining pixels within a locating window for each of the extensions having at least one side positioned substantially at an angle of the curve.

26. The method of claim 23, wherein aligning in at least one dimension the rough geometric description relative to the object in the image using the at least two anchor points to provide a partially aligned rough geometric description involves,

calculating a refined dimension of the rough pose using the at least two anchor points;

and

aligning the rough geometric description according to the refined dimension relative to the object in the image to provide a partially aligned rough geometric description.

27. The method of claim 26, wherein calculating a refined dimension of the rough pose using the at least two anchor points involves,

calculating an angle of a curve substantially fitting the at least two anchor points, where the angle of the curve is the refined dimension.

28. The method of claim 27, wherein measuring dimensions of the object in the image using the partially aligned rough geometric description to provide measured dimensions includes,

measuring dimensions of the plurality of extensions.

29. The method of claim 22, wherein measuring dimensions of the object in the image using the partially aligned rough geometric description to provide measured dimensions includes,

calculating a histogram of at least one region of the object within a window superimposed over the image oriented with at least one side aligned with the aligned rough geometric description, the histogram having a plurality of brightnesses;

identifying a potential threshold region between two opposed outlying regions of the histogram by identifying the two opposed outlying regions using expected areas of the each of the two outlying opposed brightness regions, a portion of the expected areas being the rough geometric description;

identifying a threshold within the potential threshold region to segment the region of the object;

thresholding the image containing the region to generate an object image containing the region of the object to measure; and

measuring the extent of the region within the object image.

30. The method of claim 22, further comprising,

validating the refined geometric description against predetermined values.

31. An apparatus for refining a rough geometric description of an object having a plurality of extensions, the apparatus comprising:

an image of the object;

at least two anchor points in the image related to at least two of the plurality of extensions;

means for aligning in at least one dimension the rough geometric description relative to the object in the image using the at least two anchor points to provide a partially aligned rough geometric description;

means for measuring dimensions of the object using the partially aligned rough geometric description to provide measured dimensions; and

means for updating the rough geometric description to substantially coincide with the measured dimensions of the object, thereby generating a refined geometric description of at least a portion of the object.

32. The apparatus of claim 31, further comprises:

means for locating at least two points of high contrast to provide rough anchor points by projecting pixels within a locating window having a projection axis positioned substantially at an angle of the rough pose and covering at least a portion of two of the plurality of extensions;

means for fitting a curve to the at least two points; and

means for locating a point of highest contrast for each of the plurality of extensions being the at least two anchor points by projecting pixels within a locating window for each of the extensions having a projection axis positioned substantially at an angle of the curve.

33. The apparatus of claim 31, further comprises:

means for locating at least two centroids of a region of brightness to provide rough anchor points by examining pixels within a locating window having at least one side positioned substantially at an angle of the rough pose and covering at least a portion of two of the plurality of extensions;

means for fitting a curve to the at least two centroids; and

means for locating a centroid for each of the plurality of extensions being the at least two anchor points by examining pixels within a locating window for each of the extensions having at least one side positioned substantially at an angle of the curve.

34. The apparatus of claim 31, wherein means for aligning in at least one dimension the rough geometric description relative to the object in the image using the at least two anchor points to provide a partially aligned rough geometric description involves,

means for calculating a refined dimension of the rough pose using the at least two anchor points;

and

means for aligning the rough geometric description according to the refined dimension relative to the object in the image to provide a partially aligned rough geometric description.

35. The apparatus of claim 31, wherein means for calculating a refined dimension of the rough pose using the at least two anchor points involves,

means for calculating an angle of a curve substantially fitting the at least two anchor points, where the angle of the curve is the refined dimension.

36. The apparatus of claim 31, wherein means for measuring dimensions of the object in the image using the partially aligned rough geometric description to provide measured dimensions includes,

means for measuring dimensions of the plurality of extensions.

37. The apparatus of claim 31, wherein the means for measuring dimensions of the object in the image using the partially aligned rough geometric description to provide measured dimensions includes,

means for calculating a histogram of at least one region of the object within a window superimposed over the image oriented with at least one side aligned with the aligned rough geometric description, the histogram having a plurality of brightnesses;

means for identifying a potential threshold region between two opposed outlying regions of the histogram by identifying the two opposed outlying regions using expected areas of the each of the two outlying opposed brightness regions, a portion of the expected areas being the rough geometric description;

means for identifying a threshold within the potential threshold region to segment the region of the object;

means for thresholding the image containing the region to generate an object image containing the region of the object to measure; and

means for measuring the extent of the region within the object image.

38. The apparatus of claim 31, further comprising,

validating the refined geometric description against predetermined values.