Determining the orientation of subject data in a two-dimensional data set

• US 6,792,139 B1
• Filed: 05/16/2000
• Issued: 09/14/2004
• Est. Priority Date: 05/16/2000
• Status: Expired due to Fees

• Current Assignee: Siemens AG
• Original Assignee: Siemens AG
• Inventors: Maetschke, Stefan
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): AZARIAN, SEYED H
• Application Number:
  US09/572,028
• Time in Patent Office: 1,582 Days
• Field of Search: 382/289, 382/288, 382/287, 382/286, 382/285, 382/291, 382/141, 382/144, 382/145, 382/151, 382/168, 382/170, 382/184, 382/199, 382/172, 356/138, 356/139, 356/139.1, 702/150, 702/151, 702/45, 348/86, 348/125, 345/596, 345/597, 358/3.01, 358/3.23
• US Class Current: 382/151
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06T 7/77 using statistical methods

Abstract

A method of determining the orientation of subject data in a two-dimensional data set includes: determining a center of the subject data; determining angles from the center to each subject data; generating a frequency distribution based on the angles; and determining the orientation of the subject data based on the frequency distribution.

Claims

1. In a computerized system, a method of determining the orientation of subject data in a two-dimensional data set, comprising:

determining a center of the subject data;

determining angles from the center to each subject data;

generating a frequency distribution based on the angles; and

determining the orientation of the subject data based on the frequency distribution.

2. The method of claim 1, further comprising locating one of a maximum and a minimum on the frequency distribution, whereby the angle associated with the one of the maximum and the minimum represents the angle of orientation of the subject data in the two-dimensional data set.

3. The method of claim 1, wherein the frequency distribution includes a set of intervals and associated frequencies, the method further comprising:

generating a mean value of the frequencies in the frequency distribution; and

determining an interval having the greatest difference in frequency from the mean value, whereby the angle associated with the interval represents the angle of orientation of the subject data in the two-dimensional data set.

4. The method of claim 3, wherein the interval includes a plurality of angles.

5. The method of claim 4, further comprising determining the mean value of the angles in the interval, whereby the mean value of the angles in the interval represents the angle of orientation of the subject data.

6. The method of claim 1, further comprising segmenting the subject data from the two-dimensional data set.

7. The method of claim 1, wherein the two-dimensional data set is an image data set.

8. The method of claim 7, wherein the subject data is object data.

9. The method of claim 1, wherein the subject data includes visible characteristic data, further comprising:

determining mean values of the visible characteristic data for each angle; and

determining the orientation of the subject data based on the visible characteristic data.

10. The method of claim 9, wherein the visible characteristic is selected from the group consisting of gray scale, color, and texture.

11. The method of claim 1, wherein the center is determined by finding the mean values of the subject data along each dimension.

12. The method of claim 1, wherein each angle is a function of the coordinates of the center minus the coordinates of the subject data.

13. The method of claim 12, wherein the function is the arctangent function.

14. The method of claim 1, further comprising calculating vectors from the center to each subject data.

15. In a computerized system, a method of determining the orientation of object data in an image data set, the object data including visible characteristic data, the method comprising:

determining a graphical center of the object data;

determining angles from the graphical center to each object data;

grouping the angles into intervals;

determining mean values of the visible characteristic data for each interval; and

determining the orientation of the object data based on the mean values of the visible characteristic data.

16. The method of claim 15, wherein each interval includes a one degree angular interval.

17. The method of claim 15, further comprising segmenting the object data from the image data set.

18. The method of claim 15, wherein the visible characteristic data is selected from the group consisting of gray scale data, color data, and texture data.

19. The method of claim 15, wherein the graphical center is determined by finding the mean values of the object data along each dimension of the object data.

20. The method of claim 15, wherein each angle is calculated as a function of the coordinates of the graphical center minus the coordinates of the object data.

21. A system for determining the orientation of subject data in a two-dimensional data set, comprising:

means for determining a center of the subject data;

means for determining angles from the center to each subject data;

means for generating a frequency distribution based on the angles; and

means for determining the orientation of subject data based on the frequency distribution.

22. The system of claim 21, further comprising means for locating one of a maximum and a minimum on the frequency distribution, whereby the angle associated with the one of the maximum and the minimum represents the angle of orientation of the subject data in the two-dimensional data set.

23. The system of claim 21, wherein the frequency distribution includes a set of intervals and associated frequencies, the system further comprising:

means for generating a mean value of the frequencies in the frequency distribution; and

means for determining an interval whose frequency has the greatest difference from the mean value, whereby the angle associated with the interval represents the angle of orientation of the subject data in the two-dimensional data set.

24. The system of claim 23, further comprising means for determining the mean value of the angles in the interval, whereby the mean value of the angles in the interval represents the angle of orientation of the object data.

25. The system of claim 21, further comprising means for segmenting the subject data from the two-dimensional data set.

26. The system of claim 21, wherein the subject data includes visible characteristic data, further comprising:

means for determining mean values of the visible characteristic data; and

means for determining the orientation of the subject data based on the visible characteristic data.

27. The system of claim 26, wherein the visible characteristic is gray scale.

28. The system of claim 21, further comprising means for calculating vectors from the center to each subject data.

29. An apparatus for determining the orientation of an object, comprising:

a video camera configured to acquire an image of the object and to generate an image data set having object data;

a memory; and

a signal processing circuit coupled to the video camera and the memory, the signal processing circuit configured to store the image data set in the memory, determine angles from a center of the image data set to each object data, generate a frequency distribution of the object data based on the angles, and determine the orientation of the object based on the frequency distribution.

30. The apparatus of claim 29, wherein the signal processing circuit is configured to locate one of a maximum and a minimum on the frequency distribution, whereby the angle associated with the one of the maximum and the minimum represents the orientation of the object.

31. The apparatus of claim 29, wherein the signal processing circuit is further configured to generate a mean value of the frequencies in the frequency distribution and determine an interval having the greatest difference in frequency from the mean value, whereby the angle associated with the interval represents the angle of orientation of the object.

32. The apparatus of claim 31, wherein the signal processing circuit is further configured to determine the mean value of the angles in the interval, whereby the mean value of the angles in the interval represents the angle of orientation of the object.

33. The apparatus of claim 29, further comprising means for segmenting the object data from the image data set.

34. The apparatus of claim 29, wherein the object data includes visible characteristic data, wherein the signal processing circuit is further configured to determine mean values of the visible characteristic data for each interval, and determine the orientation of the object based on the visible characteristic data.

35. An apparatus for determining the orientation of an object, comprising:

a processing circuit configured to;

receive subject data of a subject of interest which subject data is collected from an image of the subject of interest;

identify a characteristic point in the image received;

determine angles from the characteristic point to a plurality of subject data points of the subject data with respect to a reference, the determined angles comprising a plurality of angular values; and

determine orientation of the subject of interest using the determined angles.

36. The apparatus of claim 35, wherein the plurality of subject data points comprise each point of subject data meeting a predetermined criteria.

37. The apparatus of claim 36, wherein the predetermined criteria is being darker than a predetermined grayscale value.

38. The apparatus of claim 36, wherein the processing circuit is further configured to generate a frequency distribution based on the determined angles, and orientation is determined based on the frequency distribution.

39. The apparatus of claim 35, wherein the characteristic point is a center of the subject data.

40. The apparatus of claim 35, wherein receiving subject data comprises receiving an image from a video camera and segmenting the subject data from the background data.

41. The apparatus of claim 35, wherein the processing circuit is further configured to generate a frequency distribution based on the determined angles, and orientation is determined based on the frequency distribution.

42. The apparatus of claim 35, wherein the processing circuit is further configured to determine mean values of subject data at a plurality of angular intervals based on the determined angles, and orientation is determined based on the mean values.

43. The apparatus of claim 42, wherein the processing circuit is further configured to generate a frequency distribution based on the mean values of the subject data at each angular interval, and orientation is determined based on the frequency distribution.

44. The apparatus of claim 35 wherein the plurality of angular values comprise an angular value of at least one of 0 and 360 degrees and comprise a plurality of different angular values between 0 and 360 degrees.