DETECTING OBJECTS IN IMAGES USING COLOR HISTOGRAMS

• US 20140233852A1
• Filed: 04/28/2014
• Published: 08/21/2014
• Est. Priority Date: 12/13/2011
• Status: Active Grant

• Current Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Original Assignee: The Nielsen Company LLC (MOOD Media Corporation)
• Inventors: Lee, Morris
• Granted Patent: US 8,953,884 B2
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 10/50 by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
• CPC Class Codes: G06V 10/56 relating to colour

Abstract

Methods, apparatus and articles of manufacture for detecting objects in images using color histograms are disclosed. Example methods disclosed herein include determining differences between bin values of a first color histogram corresponding to an object and respective adjusted bin values of a second color histogram corresponding to a first subregion of an image. Such disclosed example methods also include determining a first metric based on the differences. Such disclosed example methods further include comparing the first metric to a threshold to determine whether the first subregion of the image corresponds to a first possible location of the object in the image.

Claims

1. A method to detect an object in an image, the method comprising:

determining, with a processor, differences between bin values of a first color histogram corresponding to the object and respective adjusted bin values of a second color histogram corresponding to a first subregion of the image;

determining, with the processor, a first metric based on the differences; and

comparing, with the processor, the first metric to a threshold to determine whether the first subregion of the image corresponds to a first possible location of the object in the image.

2. A method as defined in claim 1, further comprising:

obtaining color values of pixels in the first subregion of the image; and

determining bin values of the second color histogram based on the color values.

3. A method as defined in claim 2, further comprising:

scaling the bin values of the second color histogram by a scale factor to determine scaled bin values of the second color histogram; and

determining an adjusted bin value for a first color bin of the second color histogram, the adjusted bin value being determined to be a smaller of (1) a scaled bin value for the first color bin of the first color histogram and (2) a bin value for a corresponding first color bin of the first color histogram.

4. A method as defined in claim 2, further comprising randomly sampling a portion of the pixels of the first subregion of the image to obtain the color values.

5. A method as defined in claim 1, further comprising, in response to the first metric satisfying the threshold, including an outline of the first subregion in a presentation of the image to indicate that the first subregion corresponds to the first possible location of the object in the image.

6. A method as defined in claim 1, further comprising:

segmenting the image into a plurality of subregions;

comparing the bin values of the first color histogram corresponding to the object and respective adjusted bin values of a plurality of color histograms corresponding to the plurality of subregions to determine a plurality of metrics corresponding to the plurality of subregions, the plurality of metrics including the first metric; and

comparing the plurality of metrics to the threshold to determine whether ones of the plurality of subregions correspond to possible locations of the object in the image.

7. A method as defined in claim 6, further comprising:

identifying a subset of subregions having respective metrics that meet the threshold; and

combining centroids of the subregions in the subset of subregions to determine an estimated location of the object in the image.

8. A tangible machine readable medium comprising machine readable instructions which, when executed, cause a machine to at least:

determine differences between bin values of a first color histogram corresponding to an object and respective adjusted bin values of a second color histogram corresponding to a first subregion of an image;

determine a first metric based on the differences; and

compare the first metric to a threshold to determine whether the first subregion of the image corresponds to a first possible location of the object in the image.

9. A tangible machine readable medium as defined in claim 8, wherein the instructions, when executed, further cause the machine to:

obtain color values of pixels in the first subregion of the image; and

determine bin values of the second color histogram based on the color values.

10. A tangible machine readable medium as defined in claim 9, wherein the instructions, when executed, further cause the machine to:

scale the bin values of the second color histogram by a scale factor to determine scaled bin values of the second color histogram; and

determine an adjusted bin value for a first color bin of the second color histogram, the adjusted bin value being determined to be a smaller of (1) a scaled bin value for the first color bin of the first color histogram and (2) a bin value for a corresponding first color bin of the first color histogram.

11. A tangible machine readable medium as defined in claim 9, wherein the instructions, when executed, further cause the machine to randomly sample a portion of the pixels of the first subregion of the image to obtain the color values.

12. A tangible machine readable medium as defined in claim 8, wherein the instructions, when executed, further cause the machine to, in response to the first metric being determined to satisfy the threshold, include an outline of the first subregion in a presentation of the image to indicate that the first subregion corresponds to the first possible location of the object in the image.

13. A tangible machine readable medium as defined in claim 8, wherein the instructions, when executed, further cause the machine to

segment the image into a plurality of subregions;

compare the bin values of the first color histogram corresponding to the object and respective adjusted bin values of a plurality of color histograms corresponding to the plurality of subregions to determine a plurality of metrics corresponding to the plurality of subregions, the plurality of metrics including the first metric; and

compare the plurality of metrics to the threshold to determine whether ones of the plurality of subregions correspond to possible locations of the object in the image.

14. A tangible machine readable medium as defined in claim 13, wherein the instructions, when executed, further cause the machine to:

identify a subset of subregions having respective metrics that meet the threshold; and

combine centroids of the subregions in the subset of subregions to determine an estimated location of the object in the image.

15. An apparatus to detect an object in an image, the apparatus comprising:

a metric determiner to;

determine differences between bin values of a first color histogram corresponding to the object and respective adjusted bin values of a second color histogram corresponding to a first subregion of the image;

determine a first metric based on the differences; and

a comparator to compare the first metric to a threshold to determine whether the first subregion of the image corresponds to a first possible location of the object in the image;

16. An apparatus as defined in claim 15, further comprising a histogram generator to:

obtain color values of pixels in the first subregion of the image; and

determine bin values of the second color histogram based on the color values.

17. An apparatus as defined in claim 16, further comprising a bin adjuster to:

scale the bin values of the second color histogram by a scale factor to determine scaled bin values of the second color histogram; and

determine an adjusted bin value for a first color bin of the second color histogram, the adjusted bin value being determined to be a smaller of (1) a scaled bin value for the first color bin of the first color histogram and (2) a bin value for a corresponding first color bin of the first color histogram.

18. An apparatus as defined in claim 15, further comprising an object locator to include an outline of the first subregion in a presentation of the image to indicate that the first subregion corresponds to the first possible location of the object in the image in response to the comparator determining that the first metric satisfies the threshold.

19. An apparatus as defined in claim 15, further comprising an image segmenter to segment the image into a plurality of subregions, wherein the metric determiner is further to:

compare the bin values of the first color histogram corresponding to the object and respective adjusted bin values of a plurality of color histograms corresponding to the plurality of subregions to determine a plurality of metrics corresponding to the plurality of subregions, the plurality of metrics including the first metric; and

compare the plurality of metrics to the threshold to determine whether ones of the plurality of subregions correspond to possible locations of the object in the image.

20. An apparatus as defined in claim 19, further comprising an object locator to:

identify a subset of subregions having respective metrics that meet the threshold; and

combine centroids of the subregions in the subset of subregions to determine an estimated location of the object in the image.