Image processing device, image processing method and electronic apparatus

• US 8,488,840 B2
• Filed: 10/27/2009
• Issued: 07/16/2013
• Est. Priority Date: 10/27/2008
• Status: Expired due to Fees

• Current Assignee: Xacti Corporation (Office Support KK)
• Original Assignee: Sanyo Electric Company Limited (Panasonic Holdings Corporation)
• Inventors: Fukumoto, Shinpei, Takeuchi, Satoru, Kojima, Kazuhiro, Tsunekawa, Norikazu
• Primary Examiner(s): Thompson, James A
• Assistant Examiner(s): Chu, David H
• Application Number:
  US12/606,411
• Publication Number:
  US 20100103192A1
• Time in Patent Office: 1,358 Days
• Field of Search: None
• US Class Current: 382/103
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: H04N 23/61 based on recognised objects
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/635 Region indicators; Field of view indicators
• CPC Class Codes: H04N 23/73 by influencing the exposure time
• CPC Class Codes: H04N 5/144 Movement detection for video coding H04N19/503; analysis of motion in general G06T7/20

Abstract

A clipping processing portion is provided with: a subject detection portion that detects a main subject and a sub-subject from an input image; a degree-of-relationship calculation portion that calculates the degree of relationship between the main subject and the sub-subject; a clip region setting portion that sets a clip region based on the positions of the main subject and the sub-subject in the input image and the degree of relationship; a clipping portion that clips the clip region from the input image. The clip region setting portion sets the clip region so as to include the main subject and the sub-subject having the high degree of relationship thereof.

Claims

1. An image processing device comprising:

a subject detection portion that detects predetermined subjects from an input image and that sets one of the detected subjects as a main subject and another of the detected subjects as a sub-subject;

a determination portion that determines a degree of relationship between the main subject and the sub-subject based on degree-of-relationship information, wherein the degree-of-relationship information indicates strength of relationship between the main subject and the sub-subject;

a clip region setting portion that sets a clip region in the input image based on positions of the main subject and the sub-subject in the input image and the degree of relationship; and

a clipping portion that clips the clip region from the input image to generate a clipped image

wherein the degree-of-relationship includes at least one of (a) to (d) below;

(a) orientations of faces of the main subject and the sub-subject;

(b) a degree of similarity of face between the main subject and the sub-subject;

(c) a degree of similarity of color between the main subject and the sub-subject; and

(d) a ratio between a number of images that are sequentially input as the input image and a number of input images including the sub-subject.

2. The image processing device of claim 1, wherein the clip region setting portion sets the clip region including:

the main subject; and

the sub-subject having, with the main subject, the degree of relationship that is determined by the determination portion to be close.

3. The image processing device of claim 1, wherein

the subject detection portion detects the subjects by detecting faces, and

one of the subjects that has a face corresponding to at least one of:

a largest face in the input image,

a face closest to a center of the input image,

a face recognized as a specific fac; and

a face specified by a selection signal input from outside is set as the main subject.

4. The image processing device of claim 1, wherein the degree-of-relationship information includes at least one of:

a distance between the main subject and the sub-subject;

orientations of faces of the main subject and the sub-subject;

sounds emitted by the main subject and the sub-subject;

a degree of similarity of face between the main subject and the sub-subject;

a degree of similarity of color between the main subject and the sub-subject;

a degree to which the face of the sub-subject is recognized as a specific face;

a ratio between a number of images that are sequentially input as the input image and a number of input images including the sub-subject.

5. An electronic apparatus comprising:

the image processing device of claim 1, wherein the clipped image output from the image processing device is recorded or displayed.

7. The image processing device of claim 1, wherein the degree-of-relationship information includes a distance between the main subject and the sub-subject.

8. The image processing device of claim 1, wherein the degree-of-relationship information includes sounds emitted by the main subject and the sub-subject.

9. The image processing device of claim 1, wherein the degree-of-relationship information includes a degree to which the face of the sub-subject is recognized as a specific face.

6. An image processing method comprising, performing the following steps via a processor:

detecting predetermined subjects from an input image and setting one of the detected subjects as a main subject and another of the detected subjects as a sub-subject;

determining a degree of relationship between the main subject and the sub-subject based on degree of information, wherein the degree-of-relationship information indicates strength of relationship between the main subject and the sub-subject;

setting a clip region in the input image based on positions of the main subject and the sub-subject in the input image and the degree of relationship; and

clipping, from the input image, the clip region to generate a clipped image

wherein the degree-of-relationship includes at least one of (a) to (d) below;

(a) orientations of faces of the main subject and the sub-subject;

(b) a degree of similarity of face between the main subject and the sub-subject;

(c) a degree of similarity of color between the main subject and the sub-subject; and

(d) a ratio between a number of images that are sequentially input as the input image and a number of input images including the sub-subject.