Digital image search system and method

• US 8,199,980 B2
• Filed: 11/08/2010
• Issued: 06/12/2012
• Est. Priority Date: 09/28/2005
• Status: Active Grant

• Current Assignee: Motorola Solutions, Inc.
• Original Assignee: FaceDouble Incorporated
• Inventors: Shah, Alex, Myers, Charles A.
• Primary Examiner(s): PATEL, KANJIBHAI B
• Application Number:
  US12/941,103
• Publication Number:
  US 20110052014A1
• Time in Patent Office: 582 Days
• Field of Search: 382115-118, 382/181, 382/190, 382/218, 382/232, 382/305, 382/312, 707/705, 455/410
• US Class Current: 382/118
• CPC Class Codes: G06V 10/98 Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation

Abstract

A method and system for matching an unknown facial image of an individual with an image of an unknown twin 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. The method and system uses human perception techniques to weight the feature vectors.

Claims

1. A method for matching a twin of a first image of an individual with a second image of an individual, the method comprising:

analyzing an unknown facial image 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 twin images, wherein the database processed image is a facial image of a twin in appearance to the unknown facial image;

sorting matches based on predicted human perception to generate a best matched images; and

transmitting the best matched images.

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 twin 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 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.

5. 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.

6. The method according to claim 1 further comprising transmitting the unknown facial image from a sender to a server.

7. The method according to claim 1 further comprising acquiring the unknown facial image by a digital camera and transmitting the unknown facial image from a computer over the internet to the server, or acquiring the unknown facial image a camera of a mobile telephone and transmitting the unknown facial image from the mobile telephone over a wireless network to the server.

8. The method according to claim 7 wherein the unknown facial image is a JPEG image transmitted as a MMS.

9. The method according to claim 7 wherein the plurality of best matched images and a perception value are transmitted from the server over a wireless network to the mobile telephone.

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

11. The method according to claim 1 wherein analyzing the unknown facial image at the 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.

12. A method for matching images using a network, the method comprising:

transmitting a digital facial image over a network from a first point of the network to a second point of the network; and

transmitting a best match twin images from the second point of the network to the first point of the network wherein the best match twin images are a primary feature vector of a processed digital facial image of the digital facial image and a database feature vector which corresponds to a database processed image of a plurality of database processed images, wherein the primary feature vector has been compared to the database feature vector.

13. The method according to claim 12 wherein the first point of the network is a mobile communication device and the second point of the network is an image classification server.

14. A method of matching an unknown facial image of a first individual with an image of another individual that is a twin in appearance to the first individual, the method comprising:

processing an 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 database processed image is a facial image of another individual from the another individual'"'"'s web page of a publicly available website, the web page containing personal information of the individual and a uniform resource locator for the web page; and

transmitting the database processed image, the personal information of the individual and the uniform resource locator for the web page.

15. The method according to claim 14 wherein the personal information of the another individual comprises at least one of the another individual'"'"'s name, address, telephone number, email address, age, school, friends, favorite entertainments, and favorite foods.