Particular-region detection method and apparatus, and program therefor

• US 20050238217A1
• Filed: 04/06/2005
• Published: 10/27/2005
• Est. Priority Date: 04/06/2004
• Status: Active Grant

• Current Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Original Assignee: Fuji Photo Film Co Limited (Fujifilm Holdings Corporation)
• Inventors: Iida, Takayuki, Enomoto, Jun, Matsushita, Takafumi
• Granted Patent: US 7,620,242 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: G06V 40/18 Eye characteristics, e.g. of the iris

Abstract

The particular region detecting method and apparatus detect particular region candidates in an image, then perform face detection in a region including one of the detected particular region candidates and specify as a particular region of a detection target the one candidate included in the region where a face can be detected. In the method and apparatus, detection conditions is changed for at least one of the candidate detection and the face detection between main and non-main portion regions of the image, face information regarding the face detected in the region is stored and the face detection corresponding to a particular region candidate to be next subjected to the face detection is performed using the thus stored face information. The program is caused a computer to execute the method.

Claims

1. A method of detecting particular regions, comprising:

detecting particular region candidates in an image;

then performing face detection in a region including one of the thus detected particular region candidates; and

specifying as a particular region of a detection target said one particular region candidate that is included in said region where a face can be detected;

wherein detection conditions is changed for at least one of said detection of said particular region candidates and said face detection between main and non-main portion regions of said image,

face information regarding said face detected in said region including said one particular region candidate is stored, and

said face detection corresponding to a particular region candidate to be next subjected to said face detection is performed using the thus stored face information.

2. The method of detecting particular regions according to claim 1, wherein said particular regions include a region of a red eye or a golden eye.

3. The method of detecting particular regions according to claim 1, wherein said main portion region is an image center region which is previously determined.

4. The method of detecting particular regions according to claim 1, wherein a region in which said particular region candidates concentrate is set as said main portion region during said face detection.

5. The method of detecting particular regions according to claim 1, wherein said particular region candidate to be next subjected to said face detection is at least one of a particular region candidate to be next subjected to said face detection in said image and a particular region candidate to be first subjected to face detection in a next image.

6. The method of detecting particular regions according to claim 1, wherein said face information is information regarding face direction, and said face detection corresponding to said particular region candidate to be next subjected to said face detection is performed initially for said face direction stored.

7. The method of detecting particular regions according to claim 1, wherein said face information is information regarding face size, and said face detection corresponding to said particular region candidate to be next subjected to said face detection is performed initially for said face size stored.

8. An apparatus for detecting particular regions, comprising:

particular region candidate detection means for detecting particular region candidates from an image using fed image data of said image;

face detection means for performing face detection in a region including one of said particular region candidates detected by said particular region candidate detection means;

specifying means for specifying as a particular region of a detection target said one particular region candidate that is included in said region where a face can be detected by said face detection means; and

storing means for storing face information regarding said face detected in said region including said one particular region candidate by said face detection means,

wherein at least one of said particular region candidate detection means and said face detection means changes detection conditions of said detection target between main and non-main portion regions of said image, and said face detection means reads said face information from said storing means and uses the thus read face information to perform said face detection corresponding to a particular region candidate to be next subjected to said face detection.

9. The apparatus for detecting particular regions according to claim 8, wherein said particular regions include a region of a red eye or a golden eye.

10. The apparatus for detecting particular regions according to claim 8, wherein said face detection means has:

a first face detection mode in which said face detection means performs said face detection by changing said detection conditions of said detection target between said main and non-main portion regions of said image and, in addition, reading said face information from said storing means for use in said face detection when performing said face detection corresponding to said particular region candidate to be next subjected to face detection;

a second face detection mode in which said face detection means performs said face detection without distinguishing between said main and non-main portion regions of said image, and by reading said face information from said storing means for use in said face detection when performing said face detection corresponding to said particular region candidate to be next subjected to said face detection; and

a third face detection mode in which said face detection means performs said face detection using no face information stored, and by changing said detection conditions between said main and non-main portion regions of said image, and

wherein said face detection means selects one of said first, second and third face detection modes to perform said face detection in accordance with input instruction.

11. A program for causing a computer to execute:

a particular region candidate detection step of detecting particular region candidates from an image using fed image data of said image;

a face detection step of performing face detection in a region including.one of said particular region candidates detected in said particular region candidate detection step;

a specifying step of specifying as a particular region of a detection target said one particular region candidate that is included in said region where a face can be detected in said face detection step; and

a storing step of storing in a storage medium face information regarding said face detected in said region including said one particular region candidate by said face detection step,

wherein said computer is caused to change detection conditions of said detection target between main and non-main portion regions of said image in at least one of said particular region candidate detection step and said face detection step, and perform said face detection in said face detection step by reading said face information from said storage medium for use in said face detection when performing said face detection corresponding to a particular region candidate to be next subjected to said face detection.

12. The program according to claim 11, wherein said particular regions include a region of a red eye or a golden eye.