Method of and apparatus for detecting a face-like region and observer tracking display

• US 6,504,942 B1
• Filed: 01/13/1999
• Issued: 01/07/2003
• Est. Priority Date: 01/23/1998
• Status: Expired due to Fees

• Current Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Original Assignee: Sharp Kabushiki Kaisha (Hon Hai Precision Industry Co., Ltd.)
• Inventors: Ezra, David, Holliman, Nicolas Steven, Hong, Qi He
• Primary Examiner(s): WERNER, BRIAN P
• Application Number:
  US09/229,187
• Time in Patent Office: 1,455 Days
• Field of Search: 382/103, 382/118, 382/164, 382/165, 382/173, 382/203, 382/239, 382/291, 382/299, 713/186, 713/200, 434/155, 345/330, 345/358, 345/431, 345/591, 345/863, 902/3, 902/6, 348/14, 348/14.13, 348/156, 348/161, 348/77, 356/71, 340/5.53, 340/5.83
• US Class Current: 382/103
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

A method of detecting a face-like region of a colour image, comprises reducing the resolution of the colour image by averaging the saturation to form a reduced resolution image and searching for a region of the reduced resolution image. The searched region has, in a predetermined shape, a substantially uniform saturation which is substantially different from the saturation of the portion of the reduced resolution image surrounding the predetermined shape.

Claims

1. A method of detecting a face-like region of a colour image, comprising the steps of:

reducing the resolution of the colour image by averaging the saturation of fixed size areas of the image to form a reduced resolution image;

determining a uniformity status for each reduced resolution pixel based on the saturations of each pixel and its neighboring pixels; and

based on the determining, searching for a region of the reduced resolution image having, in a predetermined shape, a substantially uniform saturation which is substantially different from the saturation of the portion of the reduced resolution image surrounding the predetermined shape,

wherein the colour image comprises a rectangular array of M by N picture elements, the reduced resolution image comprises (M/m) by (N/n) picture elements, each of which corresponds to m by n picture elements in the colour image, where m and n are integers, 1<

m<

M, and 1<

n<

N.

2. A method as claimed in claim 1, wherein the colour image comprises a plurality of picture elements and the resolution is reduced such that the predetermined shape is from two to three reduced resolution picture elements across.

3. A method as claimed in claim 2, wherein the saturation P of each picture element of the reduced resolution image is given by:

$P=\left(1/\mathrm{mn}\right)<br><br>\underset{i=0}{\overset{m-1}{\sum <br><br>}}<br><br>\underset{j=o}{\overset{n-1}{\sum <br><br>}}<br><br>f<br><br>\left(i,j\right)$

where f (i,j) is the saturation of the picture element of the ith column and the jth row of the m by n picture elements.

4. A method as claimed in claim 2, further comprising the step of repeating the resolution reduction and searching at least once with the reduced resolution picture elements shifted with respect to the colour image picture elements.

5. A method as claimed in claim 1, further comprising the step of storing the saturations of each picture element of the reduced resolution image in a store.

6. A method as claimed in claim 1, wherein a uniformity value is ascribed to each of the reduced resolution picture elements by comparing the saturation of each of the reduced resolution picture elements with the saturation of at least one adjacent reduced resolution picture element.

7. A method as claimed in claim 6, wherein each uniformity value is ascribed a first value if

8. A method as claimed in claim 7, wherein T is substantially equal to 0.15.

9. A method as claimed in claim 6, wherein the resolution is reduced such that the predetermined shape is two or three reduced resolution picture elements across and in which the method further comprises indicating detection of a face-like region when a uniformity value of the first value is ascribed to any of one reduced resolution picture element, two vertically or horizontally adjacent reduced resolution picture elements and a rectangular two-by-two array of picture elements and when a uniformity value of the second value is ascribed to each surrounding reduced resolution picture element.

10. A method as claimed in claim 9, further comprising the step of storing the saturations of each picture element of the reduced resolution image in a store, wherein detection is indicated by storing a third value different from the first and second values in the store in place of the corresponding uniformity value.

11. A method as claimed in claim 6, further comprising the step of storing the saturations of each picture element of the reduced resolution image in a store, wherein at least one adjacent reduced resolution picture element has not been ascribed a uniformity value and each uniformity value is stored in the store in place of the corresponding saturation.

12. A method as claimed in claim 1, wherein the saturation is derived from red, green and blue components as

13. A method as claimed in claim 1, further comprising the step of capturing the colour image.

14. A method as claimed in claim 13, wherein the colour image is captured by a video camera and the resolution reduction and searching are repeated for different video fields or frames from the video camera.

15. A method as claimed in claim 14, wherein a first colour image is captured while illuminating an expected range of positions of a face, a second colour image is captured using ambient light, and the second colour image is subtracted from the first colour image to form the colour image.

16. A method as claimed in claim 1, wherein the step of reducing the resolution is carried out by averaging only the saturation of fixed size areas of the image to form the reduced resolution image.

17. A method as claimed in claim 1, wherein the fixed size areas of the image each have the same size, and the saturation P of each picture element of the reduced resolution image is given by:

$P=\left(1/\mathrm{mn}\right)<br><br>\underset{i=0}{\overset{m-1}{\sum <br><br>}}<br><br>\underset{j=o}{\overset{n-1}{\sum <br><br>}}<br><br>f<br><br>\left(i,j\right)$

where f(i,j) is the saturation of the picture element of the ith column and the jth row of the m by n picture elements.

20. An apparatus as claimed in claim 16, wherein the means to reduce the resolution averages only the saturation of fixed size areas of the image to form the reduced resolution image.

18. An apparatus for detecting a face-like region of a colour image, comprising a data processor with means to reduce the resolution of the colour image by averaging the saturation of fixed size areas of the image to form a reduced resolution image, means for determining a uniformity status for each reduced resolution pixel based on the saturations of each pixel and its neighboring pixels, and means to search, based on the determining, for a region of the reduced resolution image having, in a predetermined shape, a substantially uniform saturation which is substantially different from the saturation of the portion of the reduced resolution image surrounding the predetermined shape,

wherein the colour image comprises a rectangular array of M by N picture elements, the reduced resolution image comprises (M/m) by (N/n) picture elements, each of which corresponds to m by n picture elements in the colour image, where m and n are integers, 1<

m<

M, and 1<

n<

N.

19. An observer tracking display comprising:

a tracking system; and

a display system co-operating with a tracking system, the

display system receiving a position data signal from the tracking system,

wherein the tracking system includes an apparatus for detecting a face-like region of a color image, the apparatus is one according to claim 18.