Method and apparatus for visual detection and inspection of objects

• US 9,092,841 B2
• Filed: 06/09/2004
• Issued: 07/28/2015
• Est. Priority Date: 06/09/2004
• Status: Active Grant

• Current Assignee: Cognex Technology & Investment Corporation (Cognex Corporation)
• Original Assignee: Cognex Technology & Investment Corporation (Cognex Corporation)
• Inventors: Silver, William M.
• Primary Examiner(s): Rahmjoo, Mike
• Application Number:
  US10/865,155
• Publication Number:
  US 20050275831A1
• Time in Patent Office: 4,066 Days
• Field of Search: 382/141, 382/100, 382/209, 382/159, 382/190, 382/194, 382/195, 382/216, 382/217, 382/218, 382/170, 382/155
• US Class Current: 1/1
• CPC Class Codes: G01N 2021/8909 Scan signal processing specially adapted for inspection of running sheets
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/0006 using a design-rule based approach
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/443 by matching or filtering

Abstract

Disclosed are methods and apparatus for automatic optoelectronic detection and inspection of objects, based on capturing digital images of a two-dimensional field of view in which an object to be detected or inspected may be located, analyzing the images, and making and reporting decisions on the status of the object. Decisions are based on evidence obtained from a plurality of images for which the object is located in the field of view, generally corresponding to a plurality of viewing perspectives. Evidence that an object is located in the field of view is used for detection, and evidence that the object satisfies appropriate inspection criteria is used for inspection. Methods and apparatus are disclosed for capturing and analyzing images at high speed so that multiple viewing perspectives can be obtained for objects in continuous motion.

Claims

1. A method for inspection of an object, comprising:

continuously moving the object relative to a two-dimensional field of view of a vision detector, the object comprising a set of visible features, the set of visible features containing at least one visible feature;

capturing a plurality of frames, each frame of the plurality of frames comprising a two-dimensional image of the field of view of the vision detector, such that the set of visible features of the object are located in the field of view of the vision detector for each frame of the plurality of frames, and such that the plurality of frames comprises a plurality of differing perspectives of the set of visible features relative to the field of view of the vision detector;

determining, using a processor, responsive to a first analysis of each of the plurality of frames, a plurality of object pass scores comprising a set of measurements wherein each measurement of the set of measurements is responsive to a characteristic of one of the set of visible features of the object;

wherein determining the plurality of object pass scores further comprises;

converting the set of measurements to a corresponding set of logic values; and

combining the set of logic values to produce the object pass score;

reporting the plurality of object pass scores.

2. The method according to claim 1 wherein the first analysis comprises

computing the plurality of object pass scores corresponding respectively to the plurality of frames, each object pass score of the plurality of object pass scores comprising evidence that the object satisfies at least one inspection criterion.

3. The method according to claim 2 wherein

each object pass score of the plurality of object pass scores is computed responsive to a second analysis of at least one region of interest in the frame.

4. The method according to claim 3 wherein the second analysis comprises, for each object pass score of the plurality of object pass scores,

calculating a set of measurements corresponding respectively to the at least one region of interest;

and

computing, responsive to the set of measurements, the object pass score.

5. The method according to claim 2 wherein

each object pass score of the plurality of object pass scores comprises one of a first binary value.

6. The method according to claim 2 wherein

each object pass score of the plurality of object pass scores comprises a range of at least three values indicating relative confidence that the object satisfies the at least one inspection criterion.

7. The method according to claim 2 wherein

the first analysis further comprises determining, for each frame of the plurality of frames, an object detection weight comprising evidence that the set of visible features are located in the field of view for the frame.

8. The method according to claim 7 wherein

the first analysis further comprises computing a weighted average of the object pass scores weighted by the corresponding object detection weight.

9. The method according to claim 7 wherein

the first analysis further comprises computing a weighted average of the object pass scores weighted by the corresponding percentile of the object detection weights.

10. The method according to claim 2 wherein

the first analysis further comprises computing an average of the object pass scores.

11. The method according to claim 2 wherein

the first analysis further comprises calculating a percentile of the object pass scores.

12. The method according to claim 1 wherein

each logic value of the set of logic values is a binary logic value.

13. The method according to claim 1 wherein

each logic value of the set of logic values is a fuzzy logic value.

14. The method according to claim 1 wherein

the step of moving includes moving the object no more than one-quarter of the field of view between successive frames of the plurality of frames.

15. The method according to claim 1 wherein

the step of moving includes moving the object no more than five percent of the field of view between successive frames.

16. The method according to claim 1 wherein

the capturing of the plurality of frames and the first analysis of the plurality of frames is performed at a rate of not less than two hundred frames per second.

17. The method according to claim 1 wherein

the step of reporting the result comprises producing an output pulse.

18. The method according to claim 17 wherein

the step of reporting the result further comprises signaling a reject actuator with the output pulse.

19. The method according to claim 17 wherein

the step of reporting the result further comprises producing the output pulse only if the object satisfies at least one inspection criterion.

20. The method according to claim 17 wherein

the step of reporting the result further comprises producing the output pulse only if the object does not satisfy at least one inspection criterion.

21. The method according to claim 17 wherein

the step of reporting the result further comprises producing the output pulse in synchronization with the object crossing a fixed reference point.

22. The method according to claim 1, further comprising:

providing a trigger signal that indicates when the set of visible features is located in the field of view; and

starting the capturing responsive to the trigger signal.

23. The method according to claim 22 wherein

the step of reporting the result comprises producing an output pulse in synchronization with the trigger signal.

24. The method according to claim 1 wherein the capturing the plurality of frames occurs during continuous movement of the object occurs such that the set of visible features are located in the field of view for each frame of the plurality of frames.

25. The method according to claim 1, wherein the vision detector, further comprising the processor, performs the first analysis and captures the plurality of frames.

26. The method according to claim 1, wherein the first analysis comprises determining an object detection weight representing evidence that an object is located in a field of view, computed for each frame.

27. The method according to claim 1, wherein the object moves no more than a small fraction of the field of view between successive frames due to a high frame rate of the vision detector.

28. A system for inspection of an object, comprising:

a conveyer that continuously moves the object relative to a two dimensional field of view, the object comprising a set of visible features, the set of visible features containing at least one visible feature;

an image capture device that captures, a plurality of frames, each frame of the plurality of frames comprising a two-dimensional image of the field of view of vision detector, such that the set of visible features of the object are located in the field of view of the vision detector for each frame of the plurality of frames, and such that the plurality of frames comprises a plurality of perspectives of the set of visible features relative to the field of view of the vision detector;

an analyzer that determines, responsive to a first analysis of each of the plurality of frames, a plurality of object test scores comprising a set of measurements wherein each measurement of the set of measurements is responsive to a characteristic of one of the set of visible features of the object;

wherein the analyzer determines the plurality of object pass scores by;

converting the set of measurements to a corresponding set of logic values; and

combining the set of logic values to produce the object pass score; and

an output signaler that reports the plurality of object pass scores.

29. The system according to claim 28, wherein the first analysis comprises computing a plurality of object pass scores corresponding respectively to the plurality of frames, each object pass score of the plurality of object pass scores comprising evidence that the object satisfies at least one inspection criterion.

30. The system according to claim 29, wherein each object pass score of the plurality of object pass scores comprises one of a first binary value and a second binary value.

31. The system according to claim 29, wherein each object pass score of the plurality of object pass scores comprises a range of at least three values indicating relative confidence that the object satisfies the at least one inspection criterion.

32. The system according to claim 29, wherein each object pass score of the plurality of object pass scores is computed responsive to a second analysis of at least one region of interest in the frame.

33. The system according to claim 32, wherein the second analysis comprises, for each object pass score of the plurality of object pass scores,

calculating a set of measurements corresponding respectively to the at least one region of interest;

and

computing, responsive to the set of measurements, the object pass score.

34. The system according to claim 29, wherein the first analysis further comprises computing an average of the object pass scores.

35. The system according to claim 29, wherein the first analysis further comprises calculating a percentile of the object pass scores.

36. The system according to claim 29, wherein the first analysis further comprises determining, for each frame of the plurality of frames, an object detection weight comprising evidence that the set of visible features are located in the field of view for the frame.

37. The system according to claim 36, wherein the first analysis further comprises computing a weighted average of the object pass scores weighted by the corresponding object detection weight.

38. The system according to claim 36, wherein the first analysis further comprises computing a weighted average of the object pass scores weighted by the corresponding percentile of the object detection weights.

39. The system according to claim 28, wherein each logic value of the set of logic values is a binary logic value.

40. The system according to claim 28, wherein each logic value of the set of logic values is a fuzzy logic value.

41. The system according to claim 28, wherein the conveyer moves the object no more than one-quarter of the field of view between successive frames of the plurality of frames.

42. The system according to claim 28, wherein the conveyer moves the object no more than five percent of the field of view between successive frames.

43. The system according to claim 28, wherein the image capture device and the analyzer operate at a rate of not less than two hundred frames per second.

44. The system according to claim 28, wherein the image capture device comprises an array of no more than about 40,000 pixels.

45. The system according to claim 44, wherein the image capture device comprises an LM9630.

46. The system according to claim 28, wherein the output signaler reports the result by producing an output pulse.

47. The system according to claim 46, further comprising a reject actuator;

and wherein

the output pulse signals the reject actuator.

48. The system according to claim 46, wherein the output signaler produces the output pulse only if the object satisfies at least one inspection criterion.

49. The system according to claim 46, wherein the output signaler produces the output pulse only if the object does not satisfy at least one inspection criterion.

50. The system according to claim 46, wherein the output signaler produces the output pulse in synchronization with the object crossing a fixed reference point.

51. The system according to claim 28, further comprising

a trigger signal that indicates when the set of visible features is located in the field of view;

and wherein

the image capture device captures the plurality of frames in response to the trigger signal.

52. The system according to claim 51, wherein the output signaler produces an output pulse in synchronization with the trigger signal.

53. The method according to claim 28 wherein the capturing the plurality of frames occurs during continuous movement of the object occurs such that the set of visible features are located in the field of view for each frame of the plurality of frames.

54. A method for inspection of an object, comprising:

continuously moving the object relative to a two-dimensional field of view, the object comprising a set of visible features, the set of visible features containing at least one visible feature;

capturing a plurality of frames, using an imager with a global shutter, each frame of the plurality of frames comprising a two-dimensional image of the field of view of a vision detector, such that the set of visible features of the object are located in the field of view of the vision detector for each frame of the plurality of frames, and such that the plurality of frames comprises a plurality of perspectives of the set of visible features in the field of view of the vision detector,

determining, by a processor, responsive to a first analysis of each of the plurality of frames, a plurality of object pass scores comprising a set of measurements wherein each measurement of the set of measurements is responsive to a characteristic of one of the set of visible features of the object;

wherein determining the plurality of object pass scores further comprises;

converting the set of measurements to a corresponding set of logic values; and

combining the set of logic values to produce the object pass score;

reporting the plurality of object pass scores.

55. The method according to claim 54 wherein the first analysis comprises

computing the plurality of object pass scores responsive to the plurality of frames, each object pass score of the plurality of object pass scores comprising evidence that the object satisfies at least one inspection criterion.

56. The method according to claim 55 wherein the first analysis further comprises determining, for each frame of the plurality of frames, an object detection weight comprising evidence that the set of visible features of the object are located in the field of view for the frame, wherein the plurality of frames comprise frames recorded at least before and after determining that the set of visible features are located in the field of view for the frame.

57. The method according to claim 54 wherein the computing the object pass score comprises,

calculating a set of measurements responsive to at least one region of interest in the frame;

and

computing, responsive to the set of measurements, the object pass score.

58. The method according to claim 54 wherein the step of moving includes moving the object no more than one-quarter of the field of view between successive frames of the plurality of frames.

59. The method according to claim 54 wherein the step of moving includes moving the object no more than five percent of the field of view between successive frames.

60. A system for inspection of an object in continuous movement relative to a two dimensional field of view of a vision detector, the object comprising a set of visible features, the set of visible features containing at least one visible feature, the system comprising:

a processor programmed to perform the steps of;

receiving a plurality of frames from a capture device having a global shutter, each frame of the plurality of frames comprising a two-dimensional image of the field of view of the vision detector, such that the set of visible features of the object are located in the field of view of the vision detector for each frame of the plurality of frames, and such that the plurality of frames comprises a plurality of perspectives of the set of visible features in the field of view of the vision detector;

calculating responsive to a first analysis of each of the plurality of frames, a plurality of object pass scores comprising a set of measurements wherein each measurement of the set of measurements is responsive to a characteristic of one of the set of visible features of the object;

wherein calculating the plurality of object pass scores further comprises;

converting the set of measurements to a corresponding set of logic values; and

combining the set of logic values to produce the object pass score;

and

providing a value responsive to the object pass score for consumption by an i/o module, wherein the i/o module uses the value in an industrial process.

61. The system according to claim 60, wherein the first analysis comprises computing the plurality of object pass scores corresponding respectively to the plurality of frames, each object pass score of the plurality of object pass scores comprising evidence that the object satisfies at least one inspection criterion.

62. The system according to claim 60, wherein each object pass score of the plurality of object pass scores is computed responsive to a second analysis of at least one region of interest in the frame.

63. The system according to claim 62, wherein the second analysis comprises, for each object pass score of the plurality of object pass scores,

calculating a set of measurements corresponding respectively to the at least one region of interest, each measurement in the set of measurements responsive to a characteristic of one of the set of visible features of the object;

and

computing, responsive to the set of measurements, the object pass score.

64. The system according to claim 60, wherein the first analysis further comprises determining, for each frame of the plurality of frames, an object detection weight comprising evidence that the set of visible features of the object are located in the field of view for the frame, wherein the plurality of frames comprise frames recorded at least before and after determining that all the visible features of the set of visible are located in the field of view for the frame.

65. The system according to claim 60, wherein a conveyor moves the object no more than five percent of the field of view between successive frames.

66. The system according to claim 60, wherein the image capture device and the first analysis operate at a rate of not less than two hundred frames per second.

67. The system according to claim 60, further comprising a reject actuator;

and wherein

the value signals the reject actuator.