Image retrieval apparatus and method, and image display apparatus and method thereof

• US 7,308,119 B2
• Filed: 11/08/2004
• Issued: 12/11/2007
• Est. Priority Date: 11/26/2003
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Gohda, Makoto, Oka, Hiroto
• Primary Examiner(s): Kassa, Yosef
• Application Number:
  US10/982,802
• Publication Number:
  US 20050157952A1
• Time in Patent Office: 1,128 Days
• Field of Search: 382/115, 382/117, 382/118, 382/190, 382/209, 382/219, 382/278, 382/282, 340/5.52, 340/5.53
• US Class Current: 382/118
• CPC Class Codes: G06F 16/5854 using shape and object relationship
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions

Abstract

Image data containing the face image of a person is retrieved from a plurality of images, the retrieved image data is displayed, face image data, which is for image retrieval, is extracted from the displayed image data, and the extracted face image data is registered as reference face image data. Specified reference face image data in the registered reference face image data is designated and image data that contains the reference face image data is retrieved.

Claims

1. An image retrieval apparatus comprising:

retrieving means for retrieving at least one image that includes a face of a person from plural images;

display means for displaying the at least one image retrieved by said retrieving means;

designation means for designating an image from the at least one image displayed by said display means to register as reference face data;

registering means for extracting feature data of the face in the image designated by said designation means and for registering the feature data as the reference face data, which is for image retrieval; and

image retrieving means for retrieving an image which contains the reference face data registered by said registering means from a plurality of images, by extracting feature data of a face in each image within the plurality of images and comparing the extracted feature data with the feature data registered by said registering means.

2. The apparatus according to claim 1, wherein in a case where said display means displays the plurality of images, said designation means designates an image from the plurality of images.

3. The apparatus according to claim 2, wherein said registering means further comprises means for appending identification information to the feature data.

4. The apparatus according to claim 3, wherein said image retrieving means retrieves the image that contains the reference face data specified by the identification information.

5. The apparatus according to claim 1, wherein said designating means designates a face of a person in the image retrieved by said image retrieving means, in a case where the image includes a plurality of persons.

6. An image retrieval apparatus comprising:

extracting means for extracting at least one image that includes a face of a person from plural images;

display means for displaying the at least one image extracted by said extracting means;

command means for, in a case where said display means displays a plurality of images, selecting and commanding registration of an image, which is for image retrieval, from the plurality of images;

registering means, which is responsive to a command from said command means, for extracting feature data of the face in the image selected by said command means, and for registering the feature data as reference face data;

input means for inputting identification information of the reference face data registered by said registering means; and

image retrieving means for retrieving, from the plurality of images, an image that includes the reference face data specified by using the identification information.

7. An image retrieval method comprising:

a retrieving step of retrieving at least one image that includes a face of a person from plural images;

a display step of displaying the at least one image retrieved in said retrieving step;

a designation step of designating an image from the at least one image displayed in said display step to register as reference face data;

a registering step of extracting feature data of the face in the image designated in said designation step, and for registering the feature data as the reference face data, which is for image retrieval; and

an image retrieving step of retrieving an image which contains the reference face data registered in said registering step from a plurality of images, by extracting feature data of a face in each image within the plurality of images and comparing the extracted feature data with the feature data registered in said registering step.

8. The method according to claim 7, wherein in a case where the display step displays the plurality of images, said designation step designates an image from the plurality of images.

9. The method according to claim 8, wherein said registering step further includes a step of appending identification information to the feature data.

10. The method according to claim 9, wherein the image that contains the reference face data specified by the identification information is retrieved in said image retrieving step.

11. The method according to claim 7, wherein said designating step designates a face of a person in the image retrieved in said image retrieving step, in a case where the image includes a plurality of persons.

12. A computer-readable storage medium storing a program for implementing the image retrieval method set forth in claim 7.

13. An image display apparatus comprising:

face-area detecting means for detecting a face area of each person contained in an image;

storage means for storing area information, which indicates the face area detected by said face-area detecting means, in association with the image;

image display means for displaying the image;

first selecting means for selecting the face area contained in a first image in response to a selection command, in a case that the first image includes a plurality of face areas;

second selecting means for, after all face areas of the first image have been selected by said first selecting means, selecting the face area contained in a second image in response to the selection command until all face areas of the second image have been selected; and

display control means for causing said image display means to display the first image or the second image in such a manner that the face area selected by said first or second selecting means is identifiable.

14. The apparatus according to claim 13, wherein said storage means stores the face area detected by said face-area detecting means in the form of rectangle information.

15. The apparatus according to claim 13, wherein in a case where a face area is selected by said first or second selecting means, said display control means displays the face area selected by said first or second selecting means with a frame appended thereto.

16. The apparatus according to claim 13, wherein in a case where a face area is selected by said first or second selecting means, said display control means displays, in inverse video, the face area selected by said first or second selecting means.

17. An image display method comprising:

a face-area detecting step of detecting a face area of each person contained in an image;

a storage step of storing area information, which indicates the face area detected in said face-area detecting step, in a memory in association with the image;

an image display of displaying the image;

a first selecting step of selecting the face area contained in a first image in response to a selection command, in a case that the first image includes a plurality of face areas;

a second selecting step of, after all face areas of the image have been selected in said first selection step, selecting the face area contained in a second image in response to the selection command until all face areas of the second image have been selected; and

a display control step of causing said image display step to display the first image or the second image in such a manner that the face area selected in said first or second selecting step is identifiable.

18. The method according to claim 17, wherein said memory stores the face area detected in said face-area detecting step in the form of rectangle information.

19. The method according to claim 17, wherein in a case where a face area is selected in said first or second selecting step, the selected face area is displayed with a frame appended thereto in said display control step.

20. The method according to claim 17, wherein in a case where a face area is selected in said first or second selecting step, the selected face area is displayed in inverse video in said display control step.