Device and method for correcting image including person area

• US 20060008173A1
• Filed: 06/24/2005
• Published: 01/12/2006
• Est. Priority Date: 06/29/2004
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Mitarai, Yusuke, Matsugu, Masakazu, Kaneda, Yuji, Mori, Katsuhiko
• Granted Patent: US 7,580,587 B2
• Time in Patent Office: Days
• US Class Current: 382/274
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: H04N 1/62 Retouching, i.e. modification of isolated colours only or in isolated picture areas only
• CPC Class Codes: H04N 1/624 Red-eye correction control of camera based on recognised facial parts H04N23/611
• CPC Class Codes: H04N 1/628 Memory colours, e.g. skin or sky

Abstract

A person area is detected from an inputted image, a category to which a person shown in the person area belongs is recognized, a correction area is extracted from the person area, and the correction area is corrected based on the recognized category. Thus, the inputted image is easily corrected in an appropriate manner according to the category of the person, that is, an object.

Claims

1. An image-processing device comprising:

an input unit configured to input at least one image;

a person-area detection unit configured to detect at least one person area from the image input via the input unit;

a recognition unit configured to recognize at least one category to which at least one person in the person area belongs;

an extraction unit configured to extract at least one correction area from the person area; and

a correction unit configured to correct the correction area based on the category recognized by the recognition unit.

2. The image-processing device according to claim 1, wherein the correction unit includes a correction-data storing unit configured to store correction data corresponding to the category, so as to read the correction data corresponding to the category recognized by the recognition unit from the correction-data storing unit and perform the correction.

3. The image-processing device according to claim 2, further comprising a registering unit configured to register the correction data into the correction-data storing unit in relation to the category recognized by the recognition unit.

4. The image-processing device according to claim 3, wherein if the recognition unit cannot recognize a predetermined person registered in advance in the person area, the registering unit is configured to register correction data corresponding to the correction area into the correction-data storing unit in relation to identification data of a person in the person area.

5. The image-processing device according to claim 2, wherein the correction area includes at least one pupil area with a poor color tone and the correction data is data on at least one pupil color component.

6. The image-processing device according to claim 2, wherein the correction area includes at least one flesh-color area and wherein the correction data includes flesh-color data of the person who belongs to the category recognized by the recognition unit.

7. The image-processing device according to claim 1, wherein the category recognized by the recognition unit corresponds to at least one of specific-personal information, gender information, age information, and race information.

8. The image-processing device according to claim 1, wherein the correction unit determines details of the correction based on an output transmitted from the recognition unit.

9. The image-processing device according to claim 1, wherein the correction unit changes details of the correction based on an output transmitted from the recognition unit.

10. The image-processing device according to claim 1, wherein the correction unit determines and changes details of the correction based on an output transmitted from the recognition unit.

11. The image-processing device according to claim 1, wherein the person-area detection unit is configured to detect a face area of the person.

12. The image-processing device according to claim 11, wherein the person-area detection unit is configured to detect at least one area including at least one element of a face of the person when the face-area is detected and wherein the extraction unit is configured to extract the correction area based on the area including the element of the face.

13. The image-processing device according to claim 11, wherein the category corresponds to at least one countenance of the person and the correction unit is configured to change a specific countenance to another countenance.

14. An image-pickup device comprising:

an image-pickup unit; and

the image-processing device according to claim 1,

wherein the image-processing device corrects at least one image picked up by the image-pickup unit.

15. An image-processing method comprising steps of:

inputting at least one image;

detecting at least one person area from the image;

recognizing at least one category to which at least one person in the person area belongs;

extracting at least one correction area from the person area; and

correcting the correction area based on the category.

16. A computer-readable program for controlling a computer to perform the image-processing method according to claim 15.