Organizing images by correlating faces

US9495583B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9495583-B2
Application numberUS-43606909-A
CountryUS
Kind codeB2
Filing dateMay 5, 2009
Priority dateJan 5, 2009
Publication dateNov 15, 2016
Grant dateNov 15, 2016

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A computer-implemented method for organizing images including receiving an image that includes a representation of a human face; generating a correlation value indicating a likelihood that the human face corresponds to a stored facial profile associated with one or more profile images including a human face; evaluating the received image and the generated correlation value to determine, depending on a result of the evaluating, whether the image corresponds to the stored facial profile; associating the received image with the stored facial profile; and storing an indication of the associating.

First claim

Opening claim text (preview).

What is claimed is: 1. A computer-implemented method for organizing images, the computer-implemented method comprising: receiving an image that includes a representation of a human face; generating a correlation value indicating a likelihood that the human face represented in the received image corresponds to a first stored facial profile, where the first stored facial profile is associated with two or more profile images each including a representation of a first human face corresponding to a same individual; evaluating the received image and the generated correlation value to determine, depending on a result of the evaluating, whether the received image corresponds to the first stored facial profile; in response to determining that the received image corresponds to the first stored facial profile, associating the received image with the first stored facial profile; deriving a potential correspondence between an additional human face represented in the received image and the first stored facial profile; and ignoring the derived potential correspondence based on the generated correlation value and the first human face corresponding to the first stored facial profile. 2. The computer-implemented method of claim 1 , wherein the correlation value indicates that the received image corresponds to another stored facial profile, and wherein evaluating further comprises evaluating first metadata of the received image and second metadata of the two or more profile images associated with the first stored facial profile. 3. The computer-implemented method of claim 1 , wherein the two or more profile images associated with the first stored facial profile are obtained from an address book application; and wherein the first stored facial profile is generated based on the two or more profile images and the profile information. 4. The computer-implemented method of claim 1 , further comprising: prompting, based on the evaluating, a user for confirmation that the human face represented in the received image corresponds to the first stored facial profile; and accepting, in response to the prompting, confirmation that the human face represented in the received image corresponds to the first stored facial profile. 5. The computer-implemented method of claim 4 , wherein accepting further comprises accepting via a user interface having an affirmative response option and a negative response option. 6. The computer-implemented method of claim 1 , further comprising: accessing detection information indicating less than a 90% likelihood that the image represents a human face; establishing that the image depicts skin-tone colors and sharp image details; and confirming, based on the establishing, that the image represents a human face. 7. The computer-implemented method of claim 6 , further comprising: selecting the received image as a key image based on one or more of the detection information, the received image, or the correlation value; and displaying the key image as an icon for the first stored facial profile. 8. The computer-implemented method of claim 7 , wherein the received image comprises one or more selected from a group consisting of a sharpness indication, a capture date, and an image resolution of the received image. 9. The computer-implemented method of claim 7 , wherein the detection information comprises one or more selected from a group consisting of a distance from the human face represented in the received image to another human face depicted in the received image, and an angle of the human face relative to the received image. 10. The computer-implemented method of claim 1 , the computer-implemented method further comprising: presenting an indication of the first stored facial profile and an indication of a second stored facial profile in a user interface, wherein the second stored facial profile includes one or more images representing a second human face; receiving an indication in the user interface associating the first stored facial profile with the second stored facial profile; and generating a combined album including one or more images from the first stored facial profile and one or more images from the second stored facial profile. 11. The computer-implemented method of claim 1 , further comprising: receiving unsorted images representing human faces, unsorted image information, and unsorted correlation values indicating likelihoods that the human faces correspond to the stored facial profile; establishing an initial correlation value threshold; grouping the unsorted images based on the initial correlation value threshold and the unsorted correlation values; deriving a revised correlation threshold based on amounts of unsorted images grouped together and a total number of groups of unsorted images; regrouping the unsorted images based on the revised correlation threshold and the unsorted correlation values; and associating one or more groups of unsorted images with the first stored facial profile based on the regrouping. 12. A system comprising: a user interface device; a storage device operable to store executable software instructions and image data; and one or more computers operable to interact with the user interface device and the storage device, and to perform operations comprising: receiving an image that includes a representation of a first human face and a second human face; generating a correlation value indicating a likelihood that the first human face represented in the received image corresponds to a first stored facial profile, where the first stored facial profile is associated with two or more profile images each including a representation of the first human face corresponding to the same individual; deriving a potential correspondence between the second human face and the first stored facial profile; ignoring the derived potential correspondence based on the generated correlation value and the first human face corresponding to the first stored facial profile; evaluating the received image and the generated correlation value to determine, depending on a result of the evaluating, whether the received image corresponds to the first stored facial profile; and in response to determining that the received image corresponds to the first stored facial profile, displaying, using the user interface device, the received image in association with the first stored facial profile. 13. The system of claim 12 , further comprising: an external input operable to receive data, and to perform input operations comprising: obtaining the two or more profile images and profile information associated with the two or more profile images through the external input. 14. The system of claim 13 , the operations further comprising: generating the first stored facial profile based on the obtained two or more profile images and the profile information. 15. The system of claim 13 , wherein the external input comprises an address book application adapter for obtaining the two or more profile images and the profile information from an address book application. 16. The system of claim 12 , the operations further comprising: prompting, based on the determining, a user via the user interface device for confirmation that the first human face represented in the received image corresponds to the first stored facial profile; and accepting, in response to the prompting, confirmation via the user interface device that the first human face represented in the received image corresponds to the first stored facial profile. 17. The system of claim 12

Assignees

Inventors

Classifications

  • G11B27/034Primary

    on discs (G11B27/036, G11B27/038 take precedence) · CPC title

  • Physics · mapped topic

  • used signal is digitally coded · CPC title

  • Indicating arrangements  {(indicating means incorporated in magazine or cassette G11B23/046 and G11B23/0875; indicating measured values in general G01D)} · CPC title

  • by using information signals recorded by the same method as the main recording {(G11B27/22 takes precedence)} · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9495583B2 cover?
A computer-implemented method for organizing images including receiving an image that includes a representation of a human face; generating a correlation value indicating a likelihood that the human face corresponds to a stored facial profile associated with one or more profile images including a human face; evaluating the received image and the generated correlation value to determine, dependi…
Who is the assignee on this patent?
Gilley Greg, Fagans Joshua David, Bhatt Nikhil, and 5 more
What technology area does this patent fall under?
Primary CPC classification G11B27/034. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Nov 15 2016 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 8 related publications on this page (citations in our corpus or others sharing the same primary CPC).