FACE RECOGNITION APPARATUS AND METHOD USING PHYSIOGNOMIC FEATURE INFORMATION

• US 20170193284A1
• Filed: 04/04/2016
• Published: 07/06/2017
• Est. Priority Date: 01/05/2016
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: YOON, Ho-Sub, BAN, Kyu-Dae, YOON, Young-Woo, KIM, Jae-Hong
• Granted Patent: US 9,990,538 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships
• CPC Class Codes: G06V 40/169 Holistic features and representations, i.e. based on the facial image taken as a whole
• 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

Abstract

A face recognition technology using physiognomic feature information, which can improve the accuracy of face recognition. For this, the face recognition method using physiognomic feature information includes defining standard physiognomic types for respective facial elements, capturing a facial image of a user, detecting information about facial elements from the facial image, and calculating similarity scores relative to the standard physiognomic types for respective facial elements of the user based on the facial element information.

Claims

1. A face recognition method using physiognomic feature information, comprising:

defining standard physiognomic types for respective facial elements;

capturing a facial image of a user;

detecting information about facial elements from the facial image; and

calculating similarity scores relative to the standard physiognomic types for respective facial elements of the user based on the facial element information.

2. The face recognition method of claim 1, wherein defining the standard physiognomic types is configured such that:

the facial elements include at least one of eyes, a nose, a mouth, a chin, spots, and wrinkles, and

the standard physiognomic types are defined based on at least one of an interocular distance, presence/absence of double eyelids, a size of the eyes, a size and a shape of the nose, a shape of the chin, locations and shapes of the spots, and locations and shapes of the wrinkles.

3. The face recognition method of claim 2, further comprising determining similarities to facial data registered in advance in a face database (DB) based on the calculated similarity scores.

4. The face recognition method of claim 3, further comprising, after capturing the facial image of the user, performing basic face recognition using global features of a face in the facial image and locations of the facial elements,

wherein determining the similarities is configured to determine similarities to the facial data registered in advance in the face DB based on the calculated similarity scores and results of the basic face recognition.

5. The face recognition method of claim 4, wherein determining the similarities is configured to assign weights to the similarity scores and to the results of the basic face recognition, respectively, and to determine similarities to the facial data registered in advance in the face DB.

6. The face recognition method of claim 5, wherein the weights assigned to the similarity scores and to the results of the basic face recognition have values that are greater than 0 and less than 1, and a total sum of the weights assigned to the similarity scores and to the results of the basic face recognition is 1.

7. The face recognition method of claim 2, wherein defining the standard physiognomic types is configured to, when the facial elements correspond to the chin, define at least one of normal chin types including a rounded chin, a branchial chin, a pointed chin, an angular chin, and a square chin, and special chin types including a cleft chin, an asymmetric chin, and a double chin, as the standard physiognomic types for the chin based on preset criteria.

8. The face recognition method of claim 2, wherein defining the standard physiognomic types is configured to, when the facial elements correspond to the spots or wrinkles, define the standard physiognomic types depending on locations, shapes, and a number of spots or wrinkles based on preset criteria.

9. The face recognition method of claim 3, wherein determining the similarities is configured to define standard physiognomic types of the face of the user based on the similarity scores relative to standard physiognomic types, which are calculated for respective facial elements of the user, and determine similarities only to facial data stored in types identical to the defined standard physiognomic types in the face DB.

10. The face recognition method of claim 1, further comprising, after detecting the facial element information, performing preprocessing for normalizing a size of a face in the facial image based on the facial element information,

wherein calculating the similarity scores is configured to calculate similarity scores based on the facial element information of the facial image on which the preprocessing has been performed.

11. The face recognition method of claim 1, wherein capturing the facial image of the user is configured to capture the facial image of the user using a normal camera and a 3D depth camera.

12. A face recognition apparatus using physiognomic feature information, comprising:

a standard type definition unit for defining standard physiognomic types for respective facial elements;

an image-capturing unit for capturing a facial image of a user;

a detection unit for detecting information about facial elements from the facial image; and

a score calculation unit for calculating similarity scores relative to the standard physiognomic types for respective facial elements of the user based on the facial element information.

13. The face recognition apparatus of claim 12, wherein:

the facial elements include at least one of eyes, a nose, a mouth, a chin, spots, and wrinkles, and

the standard type definition unit defines the standard physiognomic types based on at least one of an interocular distance, presence/absence of double eyelids, a size of the eyes, a size and a shape of the nose, a shape of the chin, locations and shapes of the spots, and locations and shapes of the wrinkles.

14. The face recognition apparatus of claim 13, further comprising a similarity determination unit for determining similarities to facial data registered in advance in a face database (DB) based on the similarity scores.

15. The face recognition apparatus of claim 14, further comprising a basic face recognition unit for performing basic face recognition using global features of a face in the facial image and locations of the facial elements,

wherein the similarity determination unit determines similarities to the facial data registered in advance in the face DB based on the calculated similarity scores and results of the basic face recognition.

16. The face recognition apparatus of claim 15, wherein the similarity determination unit assigns weights to the similarity scores and to the results of the basic face recognition, respectively, and determines similarities to the facial data registered in advance in the face DB.

17. The face recognition apparatus of claim 16, wherein the weights assigned to the similarity scores and to the results of the basic face recognition have values that are greater than 0 and less than 1, and a total sum of the weights assigned to the similarity scores and to the results of the basic face recognition is 1.

18. The face recognition apparatus of claim 12, further comprising a normalization unit for normalizing a size of a face in the facial image based on the facial element information,

wherein the score calculation unit calculates similarity scores based on the facial element information of the normalized facial image.

19. The face recognition apparatus of claim 14, wherein the similarity determination unit defines standard physiognomic types of the face of the user based on the similarity scores relative to the standard physiognomic types, which are calculated for respective facial elements of the user, and determines similarities only to facial data stored in types identical to the defined standard physiognomic types in the face DB.