Facial Analysis Techniques

• US 20110293189A1
• Filed: 05/28/2010
• Published: 12/01/2011
• Est. Priority Date: 05/28/2010
• Status: Abandoned Application

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Yin, Qi, Cao, Zhimin, Sun, Jian
• Application Number:
  US12/790,173
• Publication Number:
  US 20110293189A1
• Time in Patent Office: Days
• US Class Current: 382/195
• CPC Class Codes: G06F 18/2135 based on approximation criteria, e.g. principal component analysis
• CPC Class Codes: G06V 10/7715 Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation

Abstract

Described herein are techniques for obtaining compact face descriptors and using pose-specific comparisons to deal with different pose combinations for image comparison.

Claims

1. A method of descriptor-based facial recognition, comprising:

obtaining feature descriptors corresponding respectively to pixels of the facial image;

calculating histograms of the feature descriptors, each histogram indicating the number of occurrences of each feature descriptor within a corresponding patch of the facial image;

concatenating the histograms to form a face descriptor;

reducing dimensionality of the face descriptor using one or more statistical vector quantization techniques; and

normalizing the reduced-dimensionality face descriptor.

2. A method as recited in claim 1, wherein obtaining a particular feature descriptor corresponding to a particular pixel comprises:

obtaining multiple feature vectors using different sampling patterns of neighboring pixels;

combining the multiple feature vectors to create the particular feature descriptor.

3. A method as recited in claim 1, further comprising quantizing the feature descriptors using a machine-learned encoding before calculating the histograms.

4. A method as recited in claim 1, wherein the one or more statistical vector quantization techniques comprise feature extraction.

5. A method as recited in claim 1, wherein the one or more statistical vector quantization techniques comprise principle component analysis.

6. A method as recited in claim 1, wherein the one or more statistical vector quantization techniques comprise reducing the dimensionality of the face descriptor to a dimension of 400.

7. A method as recited in claim 1, wherein the normalizing comprises L₁ or L₂ normalization.

8. A method of creating an encoder for use in descriptor-based facial recognition, comprising:

for a plurality of sample facial images, obtaining feature descriptors corresponding respectively to pixels of the facial images;

creating a mapping of the feature descriptors to quantized codes based on statistical dimensionality reduction.

9. A method as recited in claim 8, wherein the statistical dimensionality reduction comprises principal component analysis.

10. A method as recited in claim 8, wherein the statistical dimensionality reduction comprises K-means clustering.

11. A method as recited in claim 8, wherein the statistical dimensionality reduction comprises random-projection tree analysis.

12. A method as recited in claim 8, wherein obtaining a particular feature descriptor corresponding to a particular pixel comprises:

obtaining multiple feature vectors using different sampling patterns of neighboring pixels; and

combining the multiple feature vectors to create the particular feature descriptor.

13. A method of descriptor-based facial recognition, comprising:

extracting component images from a facial image, each component image corresponding to a facial component;

obtaining feature descriptors corresponding respectively to pixels of the component images; and

for each component image, calculating one or more histograms of the feature descriptors within the component image to form a component descriptor corresponding to each of the component images.

14. A method as recited in claim 13, further comprising:

reducing dimensionality of the component descriptors using principal component analysis; and

normalizing the reduced-dimensionality component descriptors.

15. A method as recited in claim 13, further comprising:

quantizing the feature descriptors using a machine-learned encoding before calculating the component descriptors.

16. A method as recited in claim 13, wherein obtaining the feature descriptor corresponding to a particular pixel comprises sampling neighboring pixels.

17. A method as recited in claim 13, wherein obtaining a particular feature descriptor corresponding to a particular pixel comprises:

obtaining multiple feature vectors using different sampling patterns of neighboring pixels; and

combining the multiple feature vectors to create the particular feature descriptor.

18. A method as recited in claim 13, further comprising:

comparing corresponding component descriptors of different facial images to determine similarity between the different facial images.

19. A method as recited in claim 13, further comprising:

comparing corresponding component descriptors of different facial images to determine similarity between the different facial images; and

during the comparing, assigning different weights to different component descriptors depending on the facial poses represented by the different facial images.

20. A method as recited in claim 13, further comprising:

quantizing the feature descriptors using a machine-learned encoding before calculating the component descriptors

reducing dimensionality of the component descriptors using principal component analysis; and

normalizing the reduced-dimensionality component descriptors

determining facial poses of different facial images;

comparing corresponding component descriptors of the different facial images to determine similarity between the different facial images; and

during the comparing, assigning different weights to different component descriptors depending on the facial poses represented by the different facial images.