Face image processing apparatus and method

• US 7,502,496 B2
• Filed: 12/06/2007
• Issued: 03/10/2009
• Est. Priority Date: 12/12/2002
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Yuasa, Mayumi, Kozakaya, Tatsuo
• Primary Examiner(s): Hung; Yubin
• Application Number:
  US11/987,931
• Publication Number:
  US 20080137919A1
• Time in Patent Office: 460 Days
• Field of Search: 382115-118, 382/154, 382/164, 358/538
• US Class Current: 382/118
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation

Abstract

A face image processing apparatus, includes: a face region detecting unit configured to detect a face feature point of a person from a plurality of images picked up by a plurality of imaging units respectively, to detect a face region; a face feature extracting unit configured to extract a face feature from an image of the face region detected by the face region detecting unit; a person recognizing unit configured to calculate a similarity measure based on a face feature of a specific person being previously registered and the face feature extracted by the face feature extracting unit to recognize the person; and an output apparatus which outputs a recognition result in the person recognizing unit.

Claims

1. A method for face image processing using a plurality of imaging units, the plurality of imaging units providing a first plurality of images of a face of a person to be identified, the method comprising:

detecting, using a detecting unit, a face feature point from each of the first plurality of images, respectively, to detect a face region;

extracting a face feature from each of a second plurality of images each corresponding to the detected face region, to thereby extract a plurality of face features;

comparing a first one of the extracted face features with a second one of the extracted features to judge whether a subject of the first plurality of images is a photograph;

calculating a similarity measure based on a face feature of a specific person previously registered and a face feature determined from the extracted face features to recognize the person to be identified; and

providing a recognition result based on the similarity measure.

2. A certification method using a plurality of imaging units, the plurality of imaging units providing a first plurality of images of a face of a first person, the method comprising:

detecting, using a detecting unit, a face feature point of the first person from each of the first plurality of images to detect a face region corresponding to the face feature point;

extracting a face feature from each of a second plurality of images each corresponding to the detected face region, to thereby extract a plurality of face features;

comparing the plurality of face features with each other to judge whether a subject of the first plurality of images is a photograph; and

calculating a similarity measure between a face feature of a specific person being previously registered and a face feature determined from the extracted face features to recognize the first person.

3. The method of claim 2, further comprising converting an inclination of one of the plurality of face features to compare the one of the plurality of face features with another one of the plurality of face features.

4. A certification method using a plurality of imaging units, the plurality of imaging units providing a plurality of images of a first person, the method comprising:

extracting, using an extracting unit, a face feature point from each of the plurality of images, to thereby extract a plurality of face feature points;

judging whether an identical person is indicated by first and second ones of the extracted face feature points; and

recognizing a person according to the first and second face feature points when the identical person is indicated.