Facial image display apparatus, facial image display method, and facial image display program

• US 9,247,156 B2
• Filed: 07/10/2014
• Issued: 01/26/2016
• Est. Priority Date: 08/12/2005
• Status: Active Grant

• Current Assignee: Sony Interactive Entertainment Inc. (Sony Group Corp.)
• Original Assignee: Sony Computer Entertainment Incorporated (Sony Group Corp.), Sony Corporation (Sony Group Corp.)
• Inventors: Tsuda, Munetaka, Hiramatsu, Shuji, Suzuki, Akira
• Primary Examiner(s): Merouan, Abderrahim
• Application Number:
  US14/328,095
• Publication Number:
  US 20140321722A1
• Time in Patent Office: 565 Days
• Field of Search: 382190-208, 3484021-699, 704260-278, 345419-475, 352 44- 55
• US Class Current: 1/1
• CPC Class Codes: G06T 13/80 2D [Two Dimensional] animation, e.g. using sprites
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships
• CPC Class Codes: G06V 40/167 using comparisons between temporally consecutive images
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: H04N 5/2628 Alteration of picture size, shape, position or orientation, e.g. zooming, rotation, rolling, perspective, translation

Abstract

The present invention provides a facial image display apparatus that can display moving images concentrated on the face when images of people'"'"'s faces are displayed. A facial image display apparatus is provided wherein a facial area detecting unit (21) detects facial areas in which faces are displayed from within a target image for displaying a plurality of faces; a dynamic extraction area creating unit (22) creates, based on the facial areas detected by the facial area detecting means, a dynamic extraction area of which at least one of position and surface area varies over time in the target image; and a moving image output unit (27) sequentially extracts images in the dynamic extraction area and outputs the extracted images as a moving image.

Claims

1. A facial image display apparatus comprising:

a memory, one or more processors configured to execute instructions stored on said memory to embody;

a detector that detects areas containing faces in a target image displaying a plurality of faces, wherein the target image is a still image;

wherein the detector creates, using the areas containing faces, a path across the still image connecting the detected areas containing faces;

a moving image creating unit that creates a moving image in which a camera scrolls across the target image according to the path,

wherein the moving image contains the areas containing faces from the target image;

a time estimator that estimates the time needed to detect facial areas in one or a plurality of other target images; and

wherein the facial image display apparatus outputs the moving image on a display on the basis of a plurality of target images;

wherein a time duration of the moving image is determined on the basis of the detection time estimated by the detection time estimating means.

2. The facial image display apparatus according to claim 1, wherein a sequence of the path is determined based a number of faces displayed the detected areas, a relative size of the detected areas, and relative positions of the detected areas.

3. The facial image display apparatus according to claim 1, wherein the moving image creating unit selects the pattern from among specific moving image pattern options on the basis of at least one of the number of detected facial areas.

4. The facial image display apparatus according to claim 1, wherein the detected facial areas are detected as rectangles.

5. The facial image display apparatus according to claim 1, wherein the detected facial areas are detected as circles.

6. The facial image display apparatus according to claim 1, wherein the detector identifies the faces contained in the detected facial areas.

7. The facial image display apparatus according to claim 1, wherein the detector determines attribute information pertaining to attributes of the faces.

8. The facial image display apparatus according to claim 7, wherein the attributes include an age or an expression.

9. The facial image display apparatus according to claim 1, wherein the moving image zooms in on the detected facial areas.

10. The facial image display apparatus according to claim 1, wherein the detector assigns a score to each of the detected facial areas.

11. The facial image display apparatus according to claim 10, wherein the score is determined based on a number of faces and a surface area of each detected facial area.

12. The facial image display apparatus according to claim 10, wherein the scores are used to determine the path.

13. A facial image display method executed on a computer comprising:

detecting at least two feature areas, including one or more areas containing faces in a target image displaying a plurality of faces, wherein the target image is a still image;

automatically creating, using the detected feature areas, a path across the still image connecting the detected feature areas; and

creating a moving image in which a camera scrolls across the target image according to the path,

wherein the moving image contains the detected areas containing faces from the target image,

wherein, when a distance between two areas containing faces is less than a predetermined value, the two areas containing faces are considered a single feature area when the path is being determined.

14. A non-transitory computer readable medium having stored thereon a program comprising the steps of:

detecting at least two feature areas, including one or more areas containing faces in a target image displaying a plurality of faces, wherein the target image is a still image;

automatically creating, using the detected feature areas, a path across the still image connecting the detected feature areas; and

creating a moving image in which a camera scrolls across the target image according to the path,

wherein the moving image contains the detected areas containing faces from the target image,

wherein, when a distance between two areas containing faces is less than a predetermined value, the two areas containing faces are considered a single feature area when the path is being determined.