METHOD AND APPARATUS FOR CAPTION DETECTION

• US 20080260032A1
• Filed: 04/17/2007
• Published: 10/23/2008
• Est. Priority Date: 04/17/2007
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Hu, Wei, Ma, Rui
• Granted Patent: US 8,929,461 B2
• Time in Patent Office: Days
• US Class Current: 375/240.16
• CPC Class Codes: G06V 20/62 Text, e.g. of license plates, overlay texts or captions on TV images
• CPC Class Codes: G06V 20/635 Overlay text, e.g. embedded captions in a TV program
• CPC Class Codes: H04N 21/4884 for displaying subtitles

Abstract

Machine-readable media, methods, apparatus and system for caption detection are described. In some embodiments, a plurality of text boxes may be detected from a plurality of frames. A first percentage of the plurality of text boxes whose locations on the plurality of frames fall into a location range may be obtained. A second percentage of the plurality of text boxes whose sizes fall into a size range may be obtained. Then, it may be determined if the first percentage and the location range are acceptable and if the second percentage and the size range are acceptable.

Claims

1. A method, comprising detecting a plurality of text boxes from a plurality of frames;

obtaining a first percentage of the plurality of text boxes whose locations on the plurality of frames fall into a location range;

obtaining a second percentage of the plurality of text boxes whose sizes fall into a size range;

determining if the first percentage and the location range are acceptable; and

determining if the second percentage and the size range are acceptable.

2. The method of claim 1, wherein the size range comprises a height range.

3. The method of claim 1, wherein the size range comprises a width range.

4. The method of claim 1, wherein the determining if the first percentage and the location range are acceptable, further comprises:

comparing the first percentage with a first predetermined value;

comparing the location range with a second predetermined value;

determining the first percentage and the location range are acceptable if the first percentage is not smaller than the first predetermined value and if the location range is not larger than the second predetermined value.

5. The method of claim 1, wherein the determining if the second percentage and the size range are acceptable, further comprises:

comparing the second percentage with a third predetermined value;

comparing the size range with a fourth predetermined value;

determining the second percentage and the size range are acceptable if the second percentage is not smaller than the third predetermined value and if the size range is not larger than the fourth predetermined value.

6. The method of claim 1, further comprising:

in response that the first percentage and the location range are acceptable and the second percentage and the size range are acceptable, determining a text box of the plurality of text boxes as a caption candidate if the text box has a location within the location range and has a size within the size range.

7. The method of claim 1, wherein the obtaining the first percentage further comprises:

obtaining a plurality of first percentages for the plurality of text boxes having a plurality of locations on the plurality of frames, each of the plurality of first percentages corresponding to each of the plurality of locations;

determining a first percentage range based upon the plurality of first percentages, wherein the first percentage range covers a highest first percentage from the plurality of first percentages; and

determining a lowest first percentage from the percentage range as the first percentage.

8. The method of claim 7, wherein the obtaining the first percentage further comprises:

determining the location range based upon the plurality of locations, wherein the location range corresponds to the first percentage range.

9. A machine-readable medium comprising a plurality of instructions that in response to being executed result in a system:

detecting a plurality of text boxes from a plurality of frames;

obtaining a first percentage of the plurality of text boxes whose locations on the plurality of frames fall into a location range;

obtaining a second percentage of the plurality of text boxes whose sizes fall into a size range;

determining if the first percentage and the location range are acceptable; and

determining if the second percentage and the size range are acceptable.

10. The machine-readable medium of claim 9, wherein the size range comprises a height range.

11. The machine-readable medium of claim 10, wherein the size range comprises a width range.

12. The machine readable medium of claim 9, wherein the plurality of instructions that result in the system determining if the first percentage and the location range are acceptable, further result in the system:

comparing the first percentage with a first predetermined value;

comparing the location range with a second predetermined value; and

determining the first percentage and the location range are acceptable if the first percentage is not smaller than the first predetermined value and if the location range is not larger than the second predetermined value.

13. The machine readable medium of claim 9, wherein the plurality of instructions that result in the system determining if the second percentage and the size range are acceptable, further result in the system:

comparing the second percentage with a third predetermined value;

comparing the size range with a fourth predetermined value; and

determining the second percentage and the size range are acceptable if the second percentage is not smaller than the third predetermined value and if the size range is not larger than the fourth predetermined value.

14. The machine readable medium of claim 11, wherein the plurality of instructions further result in the system:

in response that the first percentage and the location range are acceptable and the second percentage and the size range are acceptable, determining a text box of the plurality of text boxes as a caption candidate if the text box has a location within the location range and has a size within the size range.

15. The machine readable medium of claim 9, wherein the plurality of instructions that result in the system obtaining the first percentage, further result in the system:

obtaining a plurality of first percentages for the plurality of text boxes having a plurality of locations on the plurality of frames, each of the plurality of first percentages corresponding to each of the plurality of locations;

determining a first percentage range based upon the plurality of first percentages, wherein the first percentage range covers a highest first percentage from the plurality of first percentages;

determining a lowest first percentage from the percentage range as the first percentage; and

determining the location range based upon the plurality of locations, wherein the location range corresponds to the first percentage range.