Machine vision methods for inspection of leaded components

• US 6,639,624 B1
• Filed: 04/11/2000
• Issued: 10/28/2003
• Est. Priority Date: 12/30/1999
• Status: Expired due to Term

• Current Assignee: Cognex Corporation
• Original Assignee: Cognex Corporation
• Inventors: Sarachik, Karen, Collins, Edward, Roberts, Karen, Wallack, Aaron, Silver, William, Bachelder, Ivan
• Primary Examiner(s): RAO, ANAND SHASHIKANT
• Application Number:
  US09/547,590
• Time in Patent Office: 1,295 Days
• Field of Search: 348/86-95, 348/125-134
• US Class Current: 348/87
• CPC Class Codes: G01R 31/2813 Checking the presence, location, orientation or value, e.g. resistance, of components or conductors orientation of the DUT with respect to the test fixture G01R1/06705, G01R31/281
• CPC Class Codes: G06T 2207/30148 Semiconductor; IC; Wafer
• CPC Class Codes: G06T 2207/30152 Solder
• CPC Class Codes: G06T 7/001 using an image reference approach
• CPC Class Codes: G06T 7/74 involving reference images or patches

Abstract

A machine vision method for locating a leaded electronic device, such as integrated circuit chips, includes searching the image with a template depicting only a portion—e.g., one or two “side” edges—of each of one or more of the leads expected on the device. The template can include portions representing expected leads, as well as unexpected leads or unexpected lead positions. Positive and negative weightings are applied to such portions, as appropriate. A location of the device, or of one or more of its leads, is based on the results of the search.

Claims

1. A machine vision method of locating a leaded electronic device in an image, the method comprising the steps of

searching the image with a template representing a portion of each of one of more leads, each portion constituting less than an entirety of the respective lead,

the searching step including

positively weighting a portion represented in the template that matches an apparent lead at an expected position,

negatively weighting a portion represented in the template that matches an apparent lead at an unexpected position,

determining a location, if any, of any of a lead and the device based on results of the searching step.

2. The method of claim 1, wherein the template represents no more than two edges of each represented lead.

3. The method of claim 1, wherein the template represents no more than one edge of each represented lead.

4. The method of any of claims 2-3, wherein the template represents side edges of each represented lead.

5. The method of any of claims 1-3, wherein the template represents at least a portion of a foot of each represented lead.

6. The method of claim 1, comprising the step of generating the template from a training image.

7. The method of claim 1, comprising the step of generating the template from a training image from a geometric description of any of the device and the expected leads.

8. A machine vision method of locating a leaded electronic device in an image, the method comprising the steps of

generating, from any of a training image and a geometric description, a template representing a portion of each of one of more leads, each portion constituting no more than two edges of each of the expected leads,

searching the image with the template,

the searching step including

positively weighting a portion represented in the template that matches an apparent lead at an expected position,

negatively weighting a portion represented in the template that matches an apparent lead an unexpected position,

determining a location, if any, of any of a lead and the device based on results of the searching step.

9. The method of claim 8, wherein the generating step includes generating the template to represent no more than one edge of each of the represented leads.

10. The method of any of claims 8-9, wherein the generating step includes generating the template to represent at least a portion of a foot of each of the represented leads.

11. A machine vision method of locating a leaded electronic device in an image, the method comprising the steps of:

determining a position in the image of not more than two side edges of each of one or more expected leads of the electronic device,

determining a location, if any, of the device in the image based on positions of the side edges of each of the one of more expected leads, wherein the step of determining the location, if any, of the device in the image includes;

searching the image with a template representing a portion of one or more leads, each portion comprising not more than two side edges of each one or more of the respective lead, the searching step including;

positively weighting a portion represented in the template that matches an apparent lead at an expected position, and

negatively weighting a portion represented in the template that matches an apparent lead an unexpected position.

12. The method of claim 11 adapted for use in locating in an image a leaded electronic device having leads that are substantially spaced from one another.

13. The method of claim 12 adapted for use in locating in an image an electronic device having ten or fewer leads.

14. The method of claim 12 adapted for use in locating in an image an electronic device having five or fewer leads.

15. The method of claim 12 adapted for use in locating in an image an electronic device having three or fewer leads.

16. The method of claim 11, comprising the step of generating the template from a training image.

17. The method of claim 11, comprising the step of generating the template from a training image from a geometric description of any of the device and the expected leads.

18. A machine vision method of locating a leaded electronic device in an image, the method comprising the steps of:

determining a position in the image of not more than one side edges of each of one or more expected leads of the electronic device,

determining a location, if any, of the device in the image based on positions of the side edges of each of the one of more expected leads, wherein the step of determining the location, if any, of the device in the image includes;

searching the image with a template representing a portion of one or more leads, each portion comprising not more than one side edge of each respective lead, the searching step including;

positively weighting a portion represented in the template that matches an apparent lead at an expected position, and

negatively weighting a portion represented in the template that matches an apparent lead an unexpected position.

19. A machine vision method of locating a leaded electronic device in an image, the method comprising the steps of:

determining a position in the image of not more than one side edge of each of one or more expected leads of the electronic device,

determining a location, if any, of the device in the image based on positions of the side edges of each of the one of more expected leads, wherein the step of determining the location, if any, of the device in the image includes;

searching the image with a template representing the aforesaid side edge of each of one or more of the expected leads, the searching step including;

positively weighting a portion represented in the template that matches an apparent lead at an expected position, and

negatively weighting a portion represented in the template that matches an apparent lead an unexpected position.

20. The method of claim 19 adapted for use in locating in an image an electronic device having one hundred or fewer leads.

21. The method of claim 19 adapted for use in locating in an image an electronic device having fifty or fewer leads.

22. The method of claim 19 adapted for use in locating in an image an electronic device having between three and fifty leads.

23. The method of claim 19 adapted for use in locating in an image an electronic device having thirty or fewer leads.

24. The method of claim 19 adapted for use in locating in an image an electronic device having between three and thirty leads.

25. The method of claim 19, comprising the step of generating the template from a training image.

26. The method of claim 19, comprising the step of generating the template from a training image from a geometric description of any of the device and the expected leads.

27. A machine vision method of locating a leaded electronic device in an image, the method comprising the steps of:

determining a position in the image of not more than one tip edge of each of plural expected leads of the electronic device,

determining a location, if any, of the device in the image based on positions of the tip edges of each of the plural expected leads, wherein the step of determining the location, if any, of the device in the image includes;

searching the image with a template representing a portion of plural leads, each portion comprising not more than one tip edge of each respective lead, the searching step including;

positively weighting a portion represented in the template that matches an apparent lead at an expected position, and

negatively weighting a portion represented in the template that matches an apparent lead an unexpected position.

28. A machine vision method of locating a leaded electronic device in an image, the method comprising the steps of:

determining a position in the image of not more than one tip edge of each of plural expected leads of the electronic device,

determining a location, if any, of the device in the image based on positions of the tip edges of each of the plural expected leads, wherein the step of determining the location, if any, of the device in the image includes;

searching the image with a template representing the aforesaid tip edge of each of one or more of the expected leads, searching step including;

positively weighting a portion represented in the template that matches an apparent lead at an expected position, and

negatively weighting a portion represented in the template that matches an apparent lead an unexpected position.

29. The method of claim 28 adapted for use in locating in an image an electronic device having thirty or more leads.

30. The method of claim 28 adapted for use in locating in an image an electronic device having fifty or more leads.

31. The method of claim 28 adapted for use in locating in an image an electronic device having one hundred or more leads.

32. The method of claim 28, comprising the step of generating the template from a training image.

33. The method of claim 28, comprising the step of generating the template from a training image from a geometric description of any of the device and the expected leads.