Machine vision methods for enhancing the contrast between an object and its background using multiple on-axis images

• US 6,259,827 B1
• Filed: 03/21/1996
• Issued: 07/10/2001
• Est. Priority Date: 03/21/1996
• Status: Expired due to Term

• Current Assignee: Cognex Corporation
• Original Assignee: Cognex Corporation
• Inventors: Nichani, Sanjay
• Primary Examiner(s): Bella, Matthew C.
• Assistant Examiner(s): CHAWAN, SHEELA C
• Application Number:
  US08/621,137
• Time in Patent Office: 1,937 Days
• Field of Search: 382/173, 382/174, 382/176, 382/141, 382/142, 382/145, 382/147, 382/149, 382/143, 382/130, 382/199, 382/270, 382/294, 382/180, 348/87, 348/126, 348/127, 348/92, 358/464, 356/237, 250/223.B, 250/559.05
• US Class Current: 382/291
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30141 Printed circuit board [PCB]
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/174 involving the use of two or more images
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation

Abstract

Machine vision methods for segmenting an image include the steps of generating a first image of the background of an object, generating a second image of the object and background, and subtracting the second image from the first image. The methods are characterized in that the second image is generated such that subtraction of it from the first image emphasizes the object with respect to the background.

Claims

1. A machine vision method for inspecting an object, comprising the steps of:

illuminating the object with an illumination source selected from a group of illumination sources including (i) a direct on-axis light source that illuminates the object with direct illumination along a direction of a first axis, and (ii) a diffuse off-axis light source that illuminates the object with diffuse illumination at a grazing angle, and generating a first on-axis image of the object with an image capture device while the object is so illuminated, the image capture device being oriented for capturing the first on-axis image in the direction of the first axis;

illuminating the object with another illumination source selected from the aforesaid group, and generating a second on-axis image of the object with the image capture device while it is so illuminated, the image capture device being oriented for capturing the second on-axis image in the direction of the first axis; and

subtracting the second image from the first image to form a third image that increases a contrast between the object and a background thereof.

2. A method according to claim 1, wherein the step of generating the second image includes the step of generating that image such that subtraction of the second image from the first image increases a contrast between the object and the background.

3. A method according to claim 1, comprising the step of isolating the object within the third image.

4. A method according to claim 3, where the isolating step comprises the step of performing connectivity analysis on the third image to distinguish the object from the background.

5. A method according to claim 3, wherein the isolating step comprises the step of detecting and tracking edges in the third image to isolate the object.

6. A method according to claim 3, wherein the isolating step comprises the step of thresholding the third image to distinguish at least one of the object and its edges from the background.

7. A method according to claim 6, wherein the thresholding step comprises the step of determining an intensity threshold value that distinguishes at least one of the object and its edges from the background.

8. A method according to claim 6, comprising the steps of

generating a threshold image from at least one of the first and second images, the threshold image having pixels representing local threshold intensity values; and

using the threshold image to distinguish, in the third image, at least one of the object and its edges from the background.

9. A method according to claim 8, wherein the step of generating the threshold image includes the step of mapping image intensity values in the second image to generate the threshold image.

10. A method according to claim 8, wherein the step of using the threshold image includes the step of subtracting the threshold image from the third image.

11. A method according to claim 1, comprising the step of normalizing at least one of the first and second images before the subtracting step.

12. A method according to 11, wherein the normalizing step includes the steps of

determining distributions of intensity values of each of the first and second images;

generating a mapping function for matching extrema of those distributions; and

transforming the intensity values of at least one of the first and second images with that mapping function.

13. A method according to claim 1, including the step of generating the first and second images with light of different respective polarizations.

14. A method according to claim 1, including the step of generating the first and second images by illuminating the semiconductor device with emissions in different respective wavelengths.

15. A method according to claim 1, including the further step of registering the first and second images with one another before the subtracting step.

16. A machine vision method for inspecting an object, comprising the steps of:

illuminating the object with an illumination source selected from a group of illumination sources including (i) a direct on-axis light source that illuminates the object with direct illumination along a direction of a first axis, and (ii) a diffuse off-axis light source that illuminates the object with diffuse illumination at a grazing angle;

generating a first on-axis image of the object with an image capture device while the object is so illuminated, the image capture device being oriented for capturing the first on-axis image in the direction of the first axis;

illuminating the object with another illumination source selected from the aforesaid group;

generating a second on-axis image of the object with the image capture device while it is so illuminated, the image capture device being oriented for capturing the second on-axis image in the direction of the first axis;

subtracting the second image from the first image to form a third image that enhances a contrast between the object and a background thereof; and

isolating the object from the background in the third image by any of segmentation, edge detection and tracking, connectivity analysis, and thresholding.

17. A machine vision method for inspecting an object, comprising the steps of:

illuminating the object with an illumination source selected from a group of illumination sources including a front lighting source and a back lighting source, and generating a first image of the object with an image capture device while it is so illuminated, the image capture device generating an image with radiation reflected from the object when the illumination source is a front lighting source, the image capture device generating an image with radiation transmitted through the object when the illumination source is a back lighting source;

illuminating the object with another illumination source selected from the aforesaid group, and generating a second image of the object with the image capture device while it is so illuminated; and

subtracting the second image from the first image to form a third image that increases a contrast between the object and a background thereof.

18. A method according to claim 17, wherein the step of generating the second image includes the step of generating that image such that subtraction of the second image from the first image increases a contrast between the object and the background.

19. A method according to claim 17, comprising the step of isolating the object within the third image.

20. A method according to claim 19, where the isolating step comprises the step of performing connectivity analysis on the third image to distinguish the object from the background.

21. A method according to claim 19, wherein the isolating step comprises the step of detecting and tracking edges in the third image to isolate the object.

22. A method according to claim 19, wherein the isolating step comprises the step of thresholding the third image to distinguish at least one of the object and its edges from the background.

23. A method according to claim 22, wherein the thresholding step comprises the step of determining an intensity threshold value that distinguishes at least one of the object and its edges from the background.

24. A method according to claim 22, comprising the steps of

generating a threshold image from at least one of the first and second images, the threshold image having pixels representing local threshold intensity values; and

using the threshold image to distinguish, in the third image, at least one of the object and its edges from the background.

25. A method according to claim 24, wherein the step of generating the threshold image includes the step of mapping image intensity values in the second image to generate the threshold image.

26. A method according to claim 24, wherein the step of using the threshold image includes the step of subtracting the threshold image from the third image.

27. A method according to claim 17, comprising the step of normalizing at least one of the first and second images before the subtracting step.

28. A method according to 27, wherein the normalizing step includes the steps of

determining distributions of intensity values of each of the first and second images;

generating a mapping function for matching extrema of those distributions; and

transforming the intensity values of at least one of the first and second images with that mapping function.

29. A method according to claim 17 including the further step of registering the first and second images with one another before the subtracting step.

30. A machine vision method for inspecting an object, comprising the steps of:

illuminating the object with an illumination source selected from a group of illumination sources including a front lighting source and a back lighting source;

generating a first of the object with an image capture device while it is so illuminated, the image capture device generating an image with radiation reflected from the object when the illumination source is a front lighting source, the image capture device generating an image with radiation transmitted through the object when the illumination source is a back lighting source;

illuminating the object with another illumination source selected from the aforesaid group;

generating a second image of the object with the image capture device while it is so illuminated;

subtracting the second image from the first image to form a third image that enhances a contrast between the object and a background thereof; and

isolating the object from the background in the third image by any of segmentation, edge detection and tracking, connectivity analysis, and thresholding.

31. A machine vision method for inspecting an object, comprising the steps of:

lighting the object with a light source selected from a group of light sources including (i) a direct on-axis light source that lights the object with direct lighting along a direction of a first axis, and (ii) a diffuse off-axis light source that lights the object at a grazing angle, and generating a first on-axis image of the object with the image capture device while the object is so lighted, the image capture device being oriented for capturing the first on-axis image in the direction of the first axis;

lighting the object with another light source selected from the aforesaid group, and generating a second on-axis image of the object with the image capture device while it is so lighted, the image capture device being oriented for capturing the second on-axis image in the direction of the first axis; and

subtracting the second image from the first image to form a third image that increases a contrast between the object and a background thereof.

32. A method according to claim 31, wherein the step of generating the second image includes the step of generating that image such that subtraction of the second image from the first image increases a contrast between the object and the background.

33. A method according to claim 31, comprising the step of isolating the object within the third image.

34. A method according to claim 33, where the isolating step comprises the step of performing connectivity analysis on the third image to distinguish the object from the background.

35. A method according to claim 33, wherein the isolating step comprises the step of detecting and tracking edges in the third image to isolate the object.

36. A method according to claim 33, wherein the isolating step comprises the step of thresholding the third image to distinguish at least one of the object and its edges from the background.

37. A method according to claim 36, wherein the thresholding step comprises the step of determining an intensity threshold value that distinguishes at least one of the object and its edges from the background.

38. A method according to claim 36, comprising the steps of

generating a threshold image from at least one of the first and second images, the threshold image having pixels representing local threshold intensity values; and

using the threshold image to distinguish, in the third image, at least one of the object and its edges from the background.

39. A method according to claim 38, wherein the step of generating the threshold image includes the step of mapping image intensity values in the second image to generate the threshold image.

40. A method according to claim 38, wherein the step of using the threshold image includes the step of subtracting the threshold image from the third image.

41. A method according to claim 31, comprising the step of normalizing at least one of the first and second images before the subtracting step.

42. A method according to 41, wherein the normalizing step includes the steps of

determining distributions of intensity values of each of the first and second images;

generating a mapping function for matching extrema of those distributions; and

transforming the intensity values of at least one of the first and second images with that mapping function.

43. A method according to claim 31, including the step of generating the first and second images with light of different respective polarizations.

44. A method according to claim 31, including the step of generating the first and second images by lighting the semiconductor device with emissions in different respective wavelengths.

45. A method according to claim 31, including the further step of registering the first and second images with one another before the subtracting step.

46. A machine vision method for inspecting an object, comprising the steps of:

lighting the object with a light source selected from a group of light sources including (i) a direct on-axis light source that lights the object with direct lighting along a direction of a first axis, and (ii) a diffuse off-axis light source that lights the object at a grazing angle, and generating a first on-axis image of the object with the image capture device while it is so lighted, the image capture device being oriented for capturing the first on-axis image in the direction of the first axis;

lighting the object with another light source selected from the aforesaid group, and generating a second on-axis image of the object with the image capture device while it is so lighted, the image capture device being oriented for capturing the second on-axis image in the direction of the first axis;

subtracting the second image from the first image to form a third image that enhances a contrast between the object and a background thereof; and

isolating the object from the background in the third image by any of segmentation, edge detection and tracking, connectivity analysis, and thresholding.

47. A machine vision method for inspecting an object, comprising the steps of:

lighting the object with a lighting source selected from a group of lighting sources including a front lighting source and a back lighting source, and generating a first image of the object with an image capture device while it is so lighted the image capture device generating an image with radiation reflected from the object when the lighting source is a front lighting source, the image capture device generating an image with radiation transmitted through the object when the lighting source is a back lighting source;

lighting the object with another lighting source selected from the aforesaid group, and generating a second image of the object with the image capture device while it is so lighted; and

subtracting the second image from the first image to form a third image that increases a contrast between the object and a background thereof.

48. A method according to claim 47, wherein the step of generating the second image includes the step of generating that image such that subtraction of the second image from the first image increases a contrast between the object and the background.

49. A method according to claim 47, comprising the step of isolating the object within the third image.

50. A method according to claim 49, where the isolating step comprises the step of performing connectivity analysis on the third image to distinguish the object from the background.

51. A method according to claim 49, wherein the isolating step comprises the step of detecting and tracking edges in the third image to isolate the object.

52. A method according to claim 49, wherein the isolating step comprises the step of thresholding the third image to distinguish at least one of the object and its edges from the background.

53. A method according to claim 52, wherein the thresholding step comprises the step of determining an intensity threshold value that distinguishes at least one of the object and its edges from the background.

54. A method according to claim 52, comprising the steps of

generating a threshold image from at least one of the first and second images, the threshold image having pixels representing local threshold intensity values; and

using the threshold image to distinguish, in the third image, at least one of the object and its edges from the background.

55. A method according to claim 54, wherein the step of generating the threshold image includes the step of mapping image intensity values in the second image to generate the threshold image.

56. A method according to claim 54, wherein the step of using the threshold image includes the step of subtracting the threshold image from the third image.

57. A method according to claim 47, comprising the step of normalizing at least one of the first and second images before the subtracting step.

58. A method according to 57, wherein the normalizing step includes the steps of

determining distributions of intensity values of each of the first and second images;

generating a mapping function for matching extrema of those distributions; and

transforming the intensity values of at least one of the first and second images with that mapping function.

59. A method according to claim 47 including the further step of registering the first and second images with one another before the subtracting step.

60. A machine vision method for inspecting an object, comprising the steps of:

lighting the object with a lighting source selected from a group of lighting sources including a front lighting source and a back lighting source;

generating a first image of the object with an image capture device while it is so lighted, the image capture device generating an image with radiation reflected from the object when the lighting source is a front lighting source, the image capture device generating an image with radiation transmitted through the object when the lighting source is a back lighting source;

lighting the object with another lighting source selected from the aforesaid group;

generating a second image of the object with the image capture device while it is so lighted;

subtracting the second image from the first image to form a third image that enhances a contrast between the object and a background thereof; and

isolating the object from the background in the third image by any of segmentation, edge detection and tracking, connectivity analysis, and thresholding.