IMAGE PROCESSING APPARATUS, METHOD AND PROGRAM

• US 20100080423A1
• Filed: 09/16/2009
• Published: 04/01/2010
• Est. Priority Date: 10/01/2008
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Ishii, Akiyoshi
• Granted Patent: US 8,285,008 B2
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06F 16/70 of video data
• CPC Class Codes: G06V 40/173 face re-identification, e.g. recognising unknown faces across different face tracks

Abstract

The image processing apparatus displays a list of individual information from which individual information selected by the individual information selecting unit and individual information lapped over the individual information included in the retrieved individual groups are excluded from individual information included in individual groups retrieved by the individual group retrieval unit, and the individual group retrieval unit narrows down individual groups to be retrieved by adding on individual information designated from the individual information displayed in the list.

Claims

1. An image processing apparatus comprising:

an image detection unit configured to detect whether an image matching a predetermined conditions exists in input video;

an image analyzing unit configured to acquire a feature data that is indicative of a feature of an image from the image detected by said image detection unit;

an image identifying unit configured to compare the feature data of a plurality of images detected by said image detection unit and identifying whether the images are images in which the same individual is shot;

an individual information storage unit configured to store individual information of an individual identified by said image identifying unit;

an individual group storage unit configured to store a combination of a plurality of individual information as an individual group;

an individual information selecting unit configured to select individual information from among a plurality of individual information;

an individual group retrieval unit configured to retrieve an individual group that includes the individual from the individual information selected by said individual information selecting unit; and

an interface unit configured to display a list of individual groups retrieved by said individual group retrieval unit;

wherein said interface unit displays a list of individual information from which individual information selected by said individual information selecting unit and individual information lapped over the individual information included in the retrieved individual groups are excluded from individual information included in individual groups retrieved by said individual group retrieval unit, and said individual group retrieval unit narrows down individual groups to be retrieved by adding on individual information designated from the individual information displayed in the list.

2. The apparatus according to claim 1, wherein said interface unit displays a list of individual groups retrieved by said individual group retrieval unit and makes it possible to designate at least any one of individual groups displayed in the list.

3. The apparatus according to claim 1, wherein said interface unit makes it possible to cancel designation of any individual information from a plurality of individual information designated by said individual information selecting unit.

4. The apparatus according to claim 1, wherein said individual group storage unit stores a combination of all individual information identified in a video section comprising a plurality of video, as the individual group in association with the video section.

5. The apparatus according to claim 1, further comprising a video retrieval unit configured to retrieve, from one or a plurality of individual groups, video associated with these individual groups.

6. The apparatus according to claim 1, wherein said image detection unit detects whether a person'"'"'s face is present as an image that matches the predetermined conditions;

and

said image analyzing unit acquires feature data for identifying the face individually from the person'"'"'s face detected by said image detection unit.

7. The apparatus according to claim 6, wherein said image identifying unit handles every person as a single individual and identifies whether a plurality of faces detected by said image detection unit are those of the same person.

8. The apparatus according to claim 4, wherein the video section is video continuously shot from the start of one recording operation to the end of this recording operation.

9. The apparatus according to claim 4, wherein the video section is video that is the result of partitioning video stored in the image processing apparatus, at a predetermined time intervals.

10. The apparatus according to claim 4, wherein the video section is video that is the result of partitioning videostored in the image processing apparatus, into a predetermined date-and-time sections.

11. An image processing method comprising:

an image detection step of detecting whether an image matching a predetermined conditions exists in input video;

an image analyzing step of acquiring a feature data that is indicative of a feature of an image from the image detected in said image detection step;

an image identifying step of comparing the feature data of a plurality of images detected in said image detection step and identifying whether the images are images in which the same individual is shot;

an individual information storage step of storing individual information of an individual identified in said image identifying step;

an individual group storage step of storing a combination of a plurality of individual information as an individual group;

an individual information selecting step of selecting individual information from among a plurality of individual information;

an individual group retrieval step of retrieving an individual group that includes the individual from the individual information selected in said individual information selecting unit; and

an interface step of displaying a list of individual groups retrieved in said individual group retrieval step;

wherein said interface step displays a list of individual information from which individual information selected in said individual information selecting step and individual information lapped over the individual information included in the retrieved individual groups are excluded from individual information included in individual groups retrieved in said individual group retrieval step, and said individual group retrieval step narrows down individual groups to be retrieved by adding on individual information designated from the individual information displayed in the list.

12. The method according to claim 11, wherein said interface step displays a list of individual groups retrieved in said individual group retrieval step and makes it possible to designate at least any one of individual groups displayed in the list.

13. The method according to claim 11, wherein said interface step makes it possible to cancel designation of any individual information from a plurality of individual information designated by said individual information selecting step.

14. The method according to claim 11, wherein said individual group storage step stores a combination of all individual information identified in a video section comprising a plurality of video, as the individual group in association with the video section.

15. The method according to claim 11, further comprising a video retrieval step of retrieving, from one or a plurality of individual groups, video associated with these individual groups.

16. The method according to claim 11, wherein said image detection step detects whether a person'"'"'s face is present as an image that matches the predetermined conditions;

and

said image analyzing step acquires feature data for identifying the face individually from the person'"'"'s face detected in said image detection step.

17. The method according to claim 16, wherein said image identifying step handles every person as a single individual and identifies whether a plurality of faces detected in said image detection step are those of the same person.

18. The method according to claim 14, wherein the video section is video continuously shot from the start of one recording operation to the end of this recording operation.

19. The method according to claim 14, wherein the video section is video that is the result of partitioning video stored in an image processing apparatus, at a predetermined time intervals.

20. The method according to claim 14, wherein the video section is video that is the result of partitioning videostored in an image processing apparatus, into a predetermined date-and-time sections.

21. A storage medium storing a program for causing a computer to execute the image processing method set forth in claim 11.