Facial expression recognition apparatus, image sensing apparatus, facial expression recognition method, and computer-readable storage medium

• US 8,780,221 B2
• Filed: 03/31/2009
• Issued: 07/15/2014
• Est. Priority Date: 04/09/2008
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Kaneda, Yuji
• Primary Examiner(s): HERNANDEZ, NELSON D
• Application Number:
  US12/936,227
• Publication Number:
  US 20110032378A1
• Time in Patent Office: 1,932 Days
• Field of Search: 348/222.1, 348345-357
• US Class Current: 348/222.1
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G06V 40/174 Facial expression recognition
• CPC Class Codes: G06V 40/175 Static expression
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: H04N 21/44218 Detecting physical presence or behaviour of the user, e.g. using sensors to detect if the user is leaving the room or changes his face expression during a TV program methods or arrangements for recognising human body or animal bodies or body parts G06V40/10; methods or arrangements for acquiring or recognising human faces, facial parts, facial sketches, facial expressions G06V40/16; methods or arrangements for recognising movements or behaviour G06V40/20; arrangements for identifying users in broadcast systems H04H60/45
• CPC Class Codes: H04N 2101/00 Still video cameras
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body

Abstract

A facial expression recognition apparatus (10) detects a face image of a person from an input image, calculates a facial expression evaluation value corresponding to each facial expression from the detected face image, updates, based on the face image, the relationship between the calculated facial expression evaluation value and a threshold for determining a facial expression set for the facial expression evaluation value, and determines the facial expression of the face image based on the updated relationship between the facial expression evaluation value and the threshold for determining a facial expression.

Claims

1. An apparatus comprising:

an image input unit configured to input an image;

a face detection unit configured to detect a face image of a person from an image input by said image input unit;

a calculation unit configured to calculate a first facial expression evaluation value corresponding to a first facial expression and a second facial expression evaluation value corresponding to a second facial expression for the detected face based on the face image detected by said face detection unit;

a holding unit configured to hold a relationship between the first facial expression evaluation value and the second facial expression evaluation value;

a first determination unit configured to determine a first priority, of the first facial expression, and a second priority, of the second facial expression, based on the held relationship;

a weighting unit configured to weight at least one of the first facial expression evaluation value, the second facial expression evaluation value, and a threshold for determining the facial expression, using the determined respective priority; and

a second determination unit configured to determine a facial expression of the face image based on the first facial expression evaluation value, the second facial expression evaluation value, and the threshold.

2. The apparatus according to claim 1, wherein

each facial expression is classified into a category, and

said first determination unit determines, for each category into which each facial expression is classified, the priority of the respective facial expression evaluation value by a comparison of the respective facial expression evaluation value of each facial expression belonging to the category.

3. The apparatus according to claim 1, further comprising:

an image sensing unit configured to perform image capturing based on the facial expression of the face image determined by said second determination unit.

4. The apparatus according to claim 1, wherein at least one of the first facial expression and the second facial expression is a smile.

5. The apparatus according to claim 1, wherein the calculation unit further calculates eye open/closed degree evaluation values.

6. An image sensing apparatus comprising:

an image input unit configured to input an image;

a face detection unit configured to detect a face image of a person from an image input by said image input unit;

an estimation unit configured to estimate an attribute of the person based on the detected face image of the person;

a calculation unit configured to calculate a facial expression evaluation value corresponding to a facial expression based on the face image detected by said face detection unit;

a first determination unit configured to determine priority corresponding to the facial expression evaluation value, based on the estimated attribute;

a second determination unit configured to determine a facial expression of the face image based on the calculated facial expression evaluation value and a threshold for determining a facial expression; and

an image sensing unit configured to perform image capturing based on the facial expression of the face image determined by said second determination unit,

wherein said image sensing unit performs image capturing based on a relationship between facial expression evaluation values respectively corresponding to a first facial expression and a second facial expression, which are calculated by said calculation unit, and a threshold for determining a facial expression set for each facial expression evaluation value.

7. The apparatus according to claim 6, wherein said attribute is related to an individual, said first determination unit determines the priority corresponding to each facial expression evaluation value based on a detecting history of each facial expression of the individual estimated by said estimation unit.

8. The apparatus according to claim 6, wherein said attribute is related to an age, said first determination unit updates determines the priority corresponding to each facial expression evaluation value based on the age estimated by said estimation unit.

9. The apparatus according to claim 6, wherein said attribute is related to a sex, said first determination unit determines the priority corresponding to each facial expression evaluation value based on the sex estimated by said estimation unit.

10. The apparatus according to claim 6,

wherein said image sensing unit performs image capturing if the facial expression evaluation value of the first facial expression is not less than the threshold for determining a facial expression set for the facial expression evaluation value and the facial expression evaluation value of the second facial expression is less than the threshold for determining a facial expression set for the facial expression evaluation value.

11. A facial expression recognition method comprising:

an image input step of inputting an image;

a face detection step of detecting a face image of a person from an image input in the image input step;

a calculation step of calculating a first facial expression evaluation value corresponding to a first facial expression and a second facial expression evaluation value corresponding to a second facial expression for the detected face based on the face image detected in the face detection step;

a holding step of holding a relationship between the first facial expression evaluation value and the second facial expression evaluation value;

a first determination step of determining a first priority, of the first facial expression, and a second priority, of the second facial expression, based on the held relationship;

a weighting step of weighting at least one of the first facial expression evaluation value, the second facial expression evaluation value, and a threshold for determining the facial expression, using the determined respective priority; and

a second determination step of determining a facial expression of the face image based on the first facial expression evaluation value, the second facial expression evaluation value, and the threshold.

12. A computer-readable storage medium storing a facial expression recognition program for causing a computer to function as

a face detection unit configured to detect a face image of a person from an image,

a calculation unit configured to calculate a first facial expression evaluation value corresponding to a first facial expression and a second facial expression evaluation value corresponding to a second facial expression for the detected face based on the face image detected by the face detection unit,

a holding unit configured to hold a relationship between the first facial expression evaluation value and the second facial expression evaluation value,

a first determination unit configured to determine a first priority of the first facial expression, and a second priority, of the second facial expression, based on the held relationship;

a weighting unit configured to weight at least one of the first facial expression evaluation value, the second facial expression evaluation value, and a threshold for determining the facial expression, using the determined respective priority;

a second determination unit configured to determine a facial expression of the face image based on the first facial expression evaluation value, the second facial expression evaluation value, and the threshold.

13. A method performed by an image sensing apparatus, the method comprising:

an image input step of inputting an image;

a face detection step of detecting a face image of a person from an image input in the image input step;

an estimation step of estimating an attribute of the person based on the detected face image of the person;

a calculation step of calculating a facial expression evaluation value corresponding to a facial expression based on the face image detected in the face detection step;

a first determination step of determining priority corresponding to the facial expression evaluation value, based on the estimated attribute;

a second determination step of determining a facial expression of the face image based on the calculated facial expression evaluation value and a threshold for determining a facial expression; and

an image sensing step of performing image capturing based on the facial expression of the face image determined in the second determination step,

wherein the image sensing step performs image capturing based on a relationship between facial expression evaluation values respectively corresponding to a first facial expression and a second facial expression, which are calculated in the calculation step, and a threshold for determining a facial expression set for each facial expression evaluation value.