Face Recognition Performance Using Additional Image Features

• US 20150086076A1
• Filed: 12/05/2014
• Published: 03/26/2015
• Est. Priority Date: 10/02/2009
• Status: Active Grant

• Current Assignee: DigitalOptics Corporation Europe Limited (Adeia Inc.)
• Original Assignee: DigitalOptics Corporation Europe Limited (Adeia Inc.)
• Inventors: Bigioi, Petronel, Costache, Gabriel, Drimbarean, Alexandru, Corcoran, Peter
• Granted Patent: US 9,323,979 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships
• CPC Class Codes: G06V 40/167 using comparisons between temporally consecutive images
• CPC Class Codes: G06V 40/173 face re-identification, e.g. recognising unknown faces across different face tracks

Abstract

A technique is provided for recognizing faces in an image stream using a digital image acquisition device. A first acquired image is received from an image stream. A first face region is detected within the first acquired image having a given size and a respective location within the first acquired image. First faceprint data uniquely identifying the first face region are extracted along with first peripheral region data around the first face region. The first faceprint and peripheral region data are stored, and the first peripheral region data are associated with the first face region. The first face region is tracked until a face lock is lost. A second face region is detected within a second acquired image from the image stream. Second peripheral region data around the second face region are extracted. The second face region is identified upon matching the first and second peripheral region data.

Claims

1. A method of recognizing a face in an acquired digital image, comprising:

receiving a first acquired image;

detecting, using a processor, a first face region within the first acquired image having a given size and a respective location within the first acquired image;

extracting first peripheral region data around the first face region;

displaying a first identifier with the first face region;

receiving a second acquired image that has a second face region;

extracting second peripheral region data around the second face region;

comparing the first peripheral region data and the second peripheral region data;

in response to determining that the first peripheral region data matches the second peripheral region data, displaying the same first identifier with the second face region.

2. The method of claim 1, further comprising:

associating the first identifier with the first peripheral region data;

storing the first identifier and the first peripheral region data.

3. The method of claim 1, further comprising:

extracting faceprint data that uniquely identifies a face pattern of a face depicted in the first face region;

selecting the first identifier by performing pattern matching between the faceprint data and faceprint data stored for a set of known persons.

4. The method of claim 1, further comprising:

associating the first peripheral region data with a recognition profile of a face depicted in the first face region;

wherein the recognition profile comprises one or more identification parameters of the face.

5. The method of claim 1, wherein the first identifier comprises a name of a person associated with the first face region and the second face region.

6. The method of claim 1, wherein the first identifier comprises a symbol.

7. The method of claim 1, wherein comparing the first peripheral region data and the second peripheral region data comprises comparing texture information from the first peripheral region data and texture information from the second peripheral region data.

8. One or more non-transitory processor-readable storage media having code embedded therein for programming a processor to perform a method of recognizing a face in an acquired digital image, wherein the method comprises:

receiving a first acquired image;

detecting, using a processor, a first face region within the first acquired image having a given size and a respective location within the first acquired image;

extracting first peripheral region data around the first face region;

displaying a first identifier with the first face region;

receiving a second acquired image that has a second face region;

extracting second peripheral region data around the second face region;

comparing the first peripheral region data and the second peripheral region data;

in response to determining that the first peripheral region data matches the second peripheral region data, displaying the same first identifier with the second face region.

9. The one or more non-transitory processor-readable storage media of claim 8, wherein the method further comprises:

associating the first identifier with the first peripheral region data;

storing the first identifier and the first peripheral region data.

10. The one or more non-transitory processor-readable storage media of claim 8, wherein the method further comprises:

extracting faceprint data that uniquely identifies a face pattern of a face depicted in the first face region;

selecting the first identifier by performing pattern matching between the faceprint data and faceprint data stored for a set of known persons.

11. The one or more non-transitory processor-readable storage media of claim 8, wherein the method further comprises:

associating the first peripheral region data with a recognition profile of a face depicted in the first face region;

wherein the recognition profile comprises one or more identification parameters of the face.

12. The one or more non-transitory processor-readable storage media of claim 8, wherein the first identifier comprises a name of a person associated with the first face region and the second face region.

13. The one or more non-transitory processor-readable storage media of claim 8, wherein the first identifier comprises a symbol.

14. The one or more non-transitory processor-readable storage media of claim 8, wherein comparing the first peripheral region data and the second peripheral region data comprises comparing texture information from the first peripheral region data and texture information from the second peripheral region data.

15. A portable, digital image acquisition device, comprising a lens and image sensor for acquiring digital images, a processor, and a non-transitory processor-readable medium having code embedded therein for programming the processor to perform a method of recognizing a face in an acquired digital image, wherein the method comprises:

receiving a first acquired image;

detecting, using a processor, a first face region within the first acquired image having a given size and a respective location within the first acquired image;

extracting first peripheral region data around the first face region;

displaying a first identifier with the first face region;

receiving a second acquired image that has a second face region;

extracting second peripheral region data around the second face region;

comparing the first peripheral region data and the second peripheral region data;

in response to determining that the first peripheral region data matches the second peripheral region data, displaying the same first identifier with the second face region.

16. The device of claim 15, wherein the method further comprises:

associating the first identifier with the first peripheral region data;

storing the first identifier and the first peripheral region data.

17. The device of claim 15, wherein the method further comprises:

extracting faceprint data that uniquely identifies a face pattern of a face depicted in the first face region;

selecting the first identifier by performing pattern matching between the faceprint data and faceprint data stored for a set of known persons.

18. The device of claim 15, wherein the method further comprises:

associating the first peripheral region data with a recognition profile of a face depicted in the first face region;

wherein the recognition profile comprises one or more identification parameters of the face.

19. The device of claim 15, wherein the first identifier comprises a name of a person associated with the first face region and the second face region.

20. The device of claim 15, wherein the first identifier comprises a symbol.

21. The device of claim 15, wherein comparing the first peripheral region data and the second peripheral region data comprises comparing texture information from the first peripheral region data and texture information from the second peripheral region data.