Robot apparatus, face identification method, image discriminating method and apparatus

• US 7,317,817 B2
• Filed: 01/22/2007
• Issued: 01/08/2008
• Est. Priority Date: 11/17/2000
• Status: Expired due to Fees

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Fukuchi, Masaki, Sabe, Kohtaro, Okubo, Atsushi, Kawamoto, Kenta
• Primary Examiner(s): Ahmed; Samir
• Assistant Examiner(s): TABATABAI, ABOLFAZL
• Application Number:
  US11/656,115
• Publication Number:
  US 20070122012A1
• Time in Patent Office: 351 Days
• Field of Search: 382/103, 382/115, 382/118, 382/119, 382/156, 382/157, 382/158, 382/159, 348/169, 348/170, 348/171, 348/208.14, 348/526, 348/579, 348/587, 348/604, 348/700, 348/703, 700/115, 704/231, 704/251, 725/19
• US Class Current: 382/118
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

A robot apparatus includes face includes a face tracking module (M2) for tracking a face in an image photographed by a CCD camera, a face detecting module (M1) for detecting face data of the face in the image photographed by the image pickup device, based on the face tracking information by the face tracking module (M2) and a face identification module (M3) for identifying a specified face based on the face data as detected by the face data detecting module (M1).

Claims

1. A camera comprising:

image pickup means;

face data tracking means for tracking a face changing in an image photographed by said image pickup means;

face data detecting means for detecting face data of the face in the image photographed by said image pickup means, based on the face tracking information by said face tracking information;

face identification means for identifying a specified face based on said face data as detected by said face data detection means; and

learning means for using a difference between registered face data previously obtained and face data detected by said face data detection means to acquire a learned difference value to establish a characteristic space by said learned difference value.

2. The camera according to claim 1 wherein said face data detecting means is a support vector machine for discriminating the face and the non-face.

3. The camera according to claim 1 wherein said face tracking means tracks at least one of the movement and the shape change of said face in said image as face changes in said image.

4. The camera according to claim 1 wherein said face tracking means is object tracking means for tracking an object in the image based on color and for tracking the so specified object;

said object tracking means tracking an object specified by a preset color and tracking said object as said face.

5. The camera according to claim 4 wherein said face tracking means tracks said face by exploiting color distribution.

6. The camera according to claim 5 wherein said face tracking means tracks said face by normal distribution obtained on normalizing said color distribution.

7. The camera according to claim 1 wherein said face identification means identifies a specified face based on the results of comparison between registered face data previously obtained and said face data detected by said face data detection means.

8. The camera according to claim 7 wherein said person identification means identifies the specified face based on statistics of a plurality of results of comparison as obtained on a plurality of face data chronologically output by said face data detection means.

9. The camera according to claim 7 wherein said face identification means identifies the specified face based on a detected difference value obtained on taking the difference between the totality of registered face data previously obtained and said face data detected by said face data detection means.

10. The camera according to claim 9

wherein said face identification means identifying a specified person based on said detected difference value in said characteristic space.

11. The camera according to claim 7 further comprising:

storage means in which said registered face data is stored as database; and

image pickup mode image pickup means for storing a face image photographed in the image pickup mode in said database as registered face data.

12. A camera comprising:

registered face image storage means having a face image stored therein;

image inputting means for being fed with a preset image from outside;

face picture tracking means for tracking a face image fed from said image inputting means based on the color information;

face detection means for detecting a face using a support vector machine for an estimated face position of said input face image calculated from tracked results by said face image tacking means;

person identification means for identifying a person by comparing a face detected by said face detection means with a face image stored in said registered face image storage means; and

learning means for using a difference between registered face data previously obtained and face data detected by said face data detection means to acquire a learned difference value to establish a characteristic space by said learned difference value.