Image classification and information retrieval over wireless digital networks and the internet

• US 8,897,506 B2
• Filed: 11/10/2012
• Issued: 11/25/2014
• Est. Priority Date: 09/28/2005
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: FaceDouble Incorporated
• Inventors: Myers, Charles A., Shah, Alex
• Primary Examiner(s): PATEL, KANJIBHAI B
• Application Number:
  US13/674,019
• Publication Number:
  US 20130070976A1
• Time in Patent Office: 745 Days
• Field of Search: 382115-118, 382/181, 382/218, 382/305, 382/312, 707/104.1, 707/705, 455/410
• US Class Current: 382/118
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• 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
• CPC Class Codes: G06V 40/173 face re-identification, e.g. recognising unknown faces across different face tracks
• CPC Class Codes: G06V 40/179 metadata assisted face recognition
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

A method and system for matching an unknown facial image of an individual with an image of a celebrity using facial recognition techniques and human perception is disclosed herein. The invention provides a internet hosted system to find, compare, contrast and identify similar characteristics among two or more individuals using a digital camera, cellular telephone camera, wireless device for the purpose of returning information regarding similar faces to the user The system features classification of unknown facial images from a variety of internet accessible sources, including mobile phones, wireless camera-enabled devices, images obtained from digital cameras or scanners that are uploaded from PCs, third-party applications and databases. Once classified, the matching person'"'"'s name, image and associated meta-data is sent back to the user. The method and system uses human perception techniques to weight the feature vectors.

Claims

1. A method for matching an unknown image with a known image, the method comprising:

transmitting an unknown facial image over a cellular network acquired from a mobile communication device to an image classification server;

analyzing the facial image at the image classification server to determine if the unknown facial image is acceptable;

processing the unknown facial image to create a processed image;

comparing the processed image to a plurality of database processed images;

matching the processed image to a database processed image of the plurality of database processed images to create matched images, wherein the matched images comprises the unknown digital facial image and a database processed, wherein the database processed image is another facial image;

determining a perception value of the matched images; and

transmitting the matched images and the perception value to the sender over the Internet.

2. The method according to claim 1 wherein the processed image is processed as a primary feature vector and the plurality of database processed images is a plurality of database feature vectors, and wherein comparing the processed image to a plurality of database processed images comprises comparing the primary feature vector to each of the plurality of database feature vectors.

3. The method according to claim 2 wherein matching the processed image to a database processed image of the plurality of database processed images to create matched images comprises selecting a database feature vector with a value that is most similar to the value of the primary feature vector.

4. The method according to claim 1 wherein the plurality of database processed images comprises at least 10,000 database processed images.

5. The method according to claim 2 wherein comparing the processed image to a plurality of database processed images further comprises applying a statistical model based on human perception as determined by user'"'"'s votes of previous third party matched images.

6. The method according to claim 1 wherein the plurality of database processed images comprises from 50,000 database processed images to 100,000 database processed images.

7. The method according to claim 1 wherein the method occurs within a time period of 60 seconds.

8. The method according to claim 1 further comprising filtering the database processed image to provide a preferred database processed image for the matched images.

9. The method according to claim 2 wherein the primary feature vector and each of the plurality of database feature vectors are based on a plurality of factors comprising facial expression, hair style, hair color, facial pose, eye color, texture of the face, color of the face and facial hair.

10. The method according to claim 1 wherein image classification server comprises an input module, a transmission engine, facial recognition software, an input feed, a feature vector database, a perception engine and an output module.

11. The method according to claim 1 wherein the matched images and perception value are transmitted to a sender'"'"'s web page on a web site.

12. The method according to claim 1 wherein the perception value ranges from 0% to 100%.

13. The method according to claim 1 wherein analyzing the unknown facial image at the image classification server comprises determining if a plurality of facial image factors are acceptable, the plurality of facial image factors comprising the lack of a facial image, the lack of eyes, uneven lighting, the brightness of the facial image, pose angle of the facial image, relative size of the facial image and pixel strength of the facial image.

14. A method for matching an unknown image with a known image, the method comprising:

acquiring on a mobile communication device an unknown digital facial image of an individual;

wirelessly transmitting the unknown digital facial image from the mobile communication device over a wireless network to an image classification server;

processing the digital facial image at the image classification server to create a primary feature vector for the digital facial image;

comparing the primary feature vector to a plurality of database feature vectors, each of the plurality of database feature vectors corresponding to a database processed image;

selecting a database feature vector that best matches the primary feature vector to create matched images, wherein the matched images comprises the unknown digital facial image and a database processed; and

transmitting the matched images to the mobile communication device.

15. A method for matching images, the method comprising:

receiving a digital facial image from a mobile communication device over a wireless network at an image classification server;

processing the digital facial image at the image classification server to create a primary feature vector for the digital facial image;

comparing the primary feature vector to a plurality of database feature vectors, each of the plurality of database feature vectors corresponding to a database processed image;

obtaining matched images from the primary feature vector and database feature vectors, wherein the matched images comprises the unknown digital facial image and a database processed;

sorting the matched images based on predicted human perception;

transmitting the best matched images from the image classification server to the user.

16. The method according to claim 15 wherein sorting the matched images based on human perception comprises analyzing voting results for the matched images.