Method, apparatus, and program for human figure region extraction

• US 8,041,081 B2
• Filed: 06/27/2007
• Issued: 10/18/2011
• Est. Priority Date: 06/28/2006
• Status: Active Grant

• Current Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Original Assignee: Fujifilm Corporation (Fujifilm Holdings Corporation)
• Inventors: Hu, Yi
• Primary Examiner(s): Ahmed; Samir
• Assistant Examiner(s): Patel; Jayesh A
• Application Number:
  US11/819,465
• Publication Number:
  US 20080002890A1
• Time in Patent Office: 1,574 Days
• Field of Search: 382/103, 382/118, 382/117, 382/154
• US Class Current: 382/118
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/162 using pixel segmentation or colour matching
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships

Abstract

Upon extraction of a human figure region in an image, a face or facial part is detected in the image, and an estimated region which is estimated to include the human figure region is determined from position information of the detected face or facial part. The human figure region is extracted in the estimated region. Judgment is made as to whether at least a portion of the human figure region exists in an outline periphery region of the estimated region, and the estimated region is extended and updated so as to include a near outer region near the human figure region in the outline periphery region and outside the estimated region, in the case where a result of the judgment is affirmative. The human figure region is extracted in the extended and updated estimated region.

Claims

1. A human figure region extraction method for extracting a human figure region in a single image, the method comprising the steps of:

detecting a face or facial part in the image;

determining an estimated region which is estimated to include the human figure region, based on position information of the detected face or facial part;

extracting the human figure region in the estimated region;

judging whether at least a portion of the extracted human figure region exists in an outline periphery region in the estimated region;

extending and updating the estimated region so as to include a near outer region located near the human figure region in the outline periphery region and outside the estimated region, in the case where at least a portion of the human figure region has been judged to exist; and

extracting the human figure region in the extended and updated estimated region.

2. The human figure region extraction method according to claim 1, wherein the step of judging whether at least a portion of the human figure region exists in the outline periphery region, the step of extending and updating the estimated region, and the step of extracting the human figure region in the extended and updated estimated region are repeated until the human figure region has been judged not to exist in the outline periphery region.

3. A human figure region extraction apparatus for extracting a human figure region in an image, the apparatus comprising:

face detection means for detecting a face or facial part in the image;

estimated region determination means for determining an estimated region which is estimated to include the human figure region, based on position information of the detected face or facial part;

human figure region extraction means for extracting the human figure region in the estimated region; and

judgment means for judging whether at least a portion of the extracted human figure region exists in an outline periphery region in the estimated region, wherein,

in the case where the judgment means has judged that at least a portion of the human figure region exists, the estimated region determination means extends and updates the estimated region so as to include a near outer region located near the human figure region in the outline periphery region and outside the estimated region and the human figure region extraction means extracts the human figure region in the extended and updated estimated region.

4. The human figure region extraction apparatus according to claim 3, wherein the judgment means, the estimated region determination means, and the human figure region extraction means repeatedly judges whether at least a portion of the human figure region exists in the outline periphery region, extends and updates the estimated region, and extracts the human figure region in the extended and updated estimated region until the judgment means has judged that the human figure region does not exist in the outline periphery region.

5. The human figure region extraction apparatus according to claim 3, wherein the human figure region extraction means calculates an evaluation value for each pixel in the estimated region from image data therein and from image data in an outside region located outside the estimated region, and extracts the human figure region based on the evaluation value.

6. The human figure region extraction apparatus according to claim 4, wherein the human figure region extraction means calculates an evaluation value for each pixel in the estimated region from image data therein and from image data in an outside region located outside the estimated region, and extracts the human figure region based on the evaluation value.

7. The human figure region extraction apparatus according to claim 5, wherein the human figure region extraction means extracts the human figure region by using skin color information in the image.

8. The human figure region extraction apparatus according to claim 6, wherein the human figure region extraction means extracts the human figure region by using skin color information in the image.

9. A non-transitory computer-readable recording medium storing a program for extracting a human figure region in an image, the program causing a computer to execute the procedures of:

detecting a face or facial part in the image;

determining an estimated region which is estimated to include the human figure region, based on position information of the detected face or facial part;

extracting the human figure region in the estimated region;

judging whether at least a portion of the extracted human figure region exists in an outline periphery region in the estimated region;

extending and updating the estimated region so as to include a near outer region located near the human figure region in the outline periphery region and outside the estimated region, in the case where at least a portion of the human figure region has been judged to exist; and

extracting the human figure region in the extended and updated estimated region.