Single image based multi-biometric system and method

• US 20060050933A1
• Filed: 06/21/2005
• Published: 03/09/2006
• Est. Priority Date: 06/21/2004
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Adam, Hartwig, Neven, Hartmut, Steffens, Johannes B.
• Granted Patent: US 7,697,735 B2
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06V 10/811 the classifiers operating on different input data, e.g. multi-modal recognition
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• 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 40/18 Eye characteristics, e.g. of the iris
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

This disclosure describes methods to integrate face, skin and iris recognition to provide a biometric system with unprecedented level of accuracy for identifying individuals. A compelling feature of this approach is that it only requires a single digital image depicting a human face as source data.

Claims

1. A face recognition method, comprising:

selecting a single image of a face;

locating facial features in the single image;

comparing facial features located in the single image with facial features of a reference image;

comparing iris features in the single image with iris characteristic in the reference image; and

calculating a similarity score between the single image and the reference image based on the facial feature comparison and the iris feature comparison.

2. A face recognition method as defined in claim 1, wherein the single image has an eye distance resolution of at least about 600 pixels.

3. A face recognition method as defined in claim 1, wherein the single image comprises at least about 5 mega pixels.

4. A face recognition method as defined in claim 1, further comprising performing a skin texture analysis by comparing skin characteristics of the face in the single image with skin characteristics of a face in a reference image, wherein the similarity score is further based on the skin texture analysis.

5. A face recognition method as defined in claim 4, wherein the skin texture analysis comprises:

locating skin areas in the face suitable for skin texture analysis;

warping, aligning, and normalizing the located skin areas; and

extracting skin characteristics from the located skin areas.

6. A face recognition method as defined in claim 5, wherein the skin characteristics may consist of pores, wrinkles, and moles.

7. A face recognition method as defined in claim 1, wherein the single image is selected from a video, the facial features are located based on facial feature tracking of the facial features in the video.

8. A face recognition method as defined in claim 1, wherein the facial features are located using elastic bunch graph matching.

9. A face recognition method as defined in claim 1, wherein the facial features are located using Gabor wavelets.

10. A face recognition apparatus, comprising:

means for selecting a single image of a face;

means for locating facial features in the single image;

means for comparing facial features located in the single image with facial features of a reference image;

means for comparing iris features in the single image with iris characteristic in the reference image; and

means for calculating a similarity score between the single image and the reference image based on the facial feature comparison and the iris feature comparison.

11. A face recognition apparatus as defined in claim 10, wherein the single image has an eye distance resolution of at least about 600 pixels.

12. A face recognition apparatus as defined in claim 10, wherein the single image comprises at least about 5 mega pixels.

13. A face recognition apparatus as defined in claim 10, further comprising means for performing a skin texture analysis by comparing skin characteristics of the face in the single image with skin characteristics of a face in a reference image, wherein the similarity score is further based on the skin texture analysis.

14. A face recognition apparatus as defined in claim 13, wherein the means for performing a skin texture analysis comprises:

means for locating skin areas in the face suitable for skin texture analysis;

means for warping, aligning, and normalizing the located skin areas; and

means for extracting skin characteristics from the located skin areas.

15. A face recognition method as defined in claim 14, wherein the skin characteristics may consist of pores, wrinkles, and moles.