IMAGE PROCESSING APPARATUS AND IMAGE PROCESSING METHOD

• US 20100183221A1
• Filed: 03/30/2010
• Published: 07/22/2010
• Est. Priority Date: 05/28/2008
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: OKAMOTO, Yasukazu, IKE, Tsukasa, OHTAKE, Toshifumi
• Granted Patent: US 8,013,890 B2
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 40/162 using pixel segmentation or colour matching
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113
• CPC Class Codes: H04N 23/57 Mechanical or electrical details of cameras or camera modules specially adapted for being embedded in other devices
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body

Abstract

According to one embodiment, an image processing apparatus includes an image-capturing module configured to captures an image, a module configured to detect a first object region from the image, a module configured to extract color information of an image of the first object region, a module configured to detect candidates of a second object region, which is an object of recognition, from the image, a module configured to extract color information of an image of the second object region, and sets reference color data, a module configured to select the candidates of the second object region on the basis of the reference color data and the color information of the image of the first object region with respect to each of the candidates of the second object region, and a module configured to output, as an object of recognition, any one of the candidates of the second object region.

Claims

1. An image processing apparatus comprising:

a first object region detection module configured to detect a first object region based on a shape of a first object which specifies a region in an image based on preset color information;

a color information extraction module configured to extract color information of an image of the first object region and to set reference color data;

a second object region detection module configured to detect candidates of a second object region based on a shape of a second object of an object of recognition, different from the first object; and

an output module configured to output one of the candidates of the second object region detected by the second object region detection module as an object of recognition, the one of the candidates comprising the reference color data set by the color information extraction module.

2. The image processing apparatus of claim 1, wherein the color information extraction module is configured to calculate a set of averages of color values in the first object region as the color information.

3. The image processing apparatus of claim 1, further comprising a reference color data memory module configured to store the reference color data set by the color information extraction module, with respect to a plurality of images,

wherein the output module is configured to output the second object region, based on reference color data corresponding to a last image stored in the reference color data memory module, when the first object region is not detected from the image.

4. The image processing apparatus of claim 1, wherein the first object region detection module is configured to detect a region corresponding to a face image of a person, as the first object region, from the image, and

the second object region detection module is configured to detect a region corresponding to a hand image of the person, as the second object region, from the image.

5. An image processing method comprising:

detecting a first object region based on a shape of a first object which specifies a region in an image based on preset color information;

extracting color information of an image of the first object region and setting reference color data;

detecting candidates of a second object region based on a shape of a second object of an object of recognition, different from the first object; and

outputting one of the candidates of the second object region detected by the second object region detection as an object of recognition, the one of the detected candidates comprising the reference color data set by the color information detection.

6. The image processing method of claim 5, wherein the extracting color information comprises calculating a set of averages of color values in the first object region as the color information.

7. The image processing method of claim 5, further comprising storing the reference color data set by the color information extraction, with respect to a plurality of images,

wherein the outputting comprises outputting the second object region, based on reference color data corresponding to a last image stored by the reference color data memory, when the first object region is not detected from the image.

8. The image processing method of claim 5, wherein the detecting the first object region comprises detecting a region corresponding to a face image of a person, as the first object region, from the image, and

the detecting the second object region comprises detecting a region corresponding to a hand image of the person, as the second object region, from the image.

9. A computer-readable medium comprising a computer program executable by a computer, the computer program causes the computer to:

detect a first object region based on a shape of a first object which specifies a region in an image based on preset color information;

extract color information of an image of the first object region and setting reference color data;

detect candidates of a second object region based on a shape of a second object of an object of recognition, which differs from the first object; and

output one of the candidates of the second object region detected by the second object region detection as an object of recognition, the one of the detected candidates having the reference color data set by the color information detection.

10. The computer-readable medium of claim 9, wherein the program further causes the computer to calculate a set of averages of color values in the first object region as the color information.

11. The computer-readable medium of claim 9, wherein the program further causes the computer to:

store the reference color data set by the color information extraction, with respect to a plurality of images, and

output the second object region, based on reference color data corresponding to a last image stored by the reference color data memory, when the first object region is not detected from the image.

12. The computer-readable medium of claim 9, wherein the program further causes the computer to:

detect a region corresponding to a face image of a person, as the first object region, from the image, and

detect a region corresponding to a hand image of the person, as the second object region, from the image.