Loading...
Please wait, while we are loading the content...
Visual Storytelling Authentication
| Content Provider | The Lens |
|---|---|
| Abstract | Method, system and media for authenticating a subject as a user. Embodiments generate visual stories specific to the user and for which the subject must select the corresponding images from among a plurality of decoy images. Gaze tracking can be used to determine which images the user has selected without allowing an observer to learn which images have been selected. Images for the visual story can be retrieved from the user's social networking profile, and corresponding text storied generated to indicate which images should be selected. Multiple security levels are possible by varying the number of story images and decoy images. |
| Related Links | https://www.lens.org/lens/patent/010-356-758-730-315/frontpage |
| Language | English |
| Publisher Date | 2019-11-05 |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Patent |
| Jurisdiction | United States of America |
| Date Applied | 2015-10-16 |
| Agent | Erise Ip, P.a. |
| Applicant | Univ Missouri |
| Application No. | 201515517343 |
| Claim | A method of authenticating a subject as a user, comprising the steps of: retrieving a story image associated with the user and metadata associated with the story image; retrieving a plurality of decoy images based on the story image; generating a text story based on the metadata associated with the story image wherein the text story comprises a sentence associated by the user with the story image but not with the decoy images; presenting, to the subject, the text story together with a set of images comprising the story image and the plurality of decoy images; receiving, from the subject, an indication of a selected image of the set of images; and authenticating the subject as the user if the selected image corresponds to the story image. The method of claim 1 , wherein the story image associated with the user and the metadata associated with the story image are retrieved from a source selected from the set consisting of: a social media profile associated with the user and a local data store populated by the user. The method of claim 1 , wherein the story image associated with the user is retrieved from a database in which the story image associated with the user was stored during a user registration process. The method of claim 1 , wherein the story image associated with the user and the plurality of decoy images are presented in a random order. The method of claim 1 , wherein a plurality of story images associated with the user are presented to the subject, and wherein the subject is only authenticated as the user if the subject selects each of the plurality of story images associated with the user. The method of claim 1 , wherein the indication of the selected images of the set of images comprises a gaze directed at the selected image. The method of claim 1 , wherein the indication of the selected images of the set of images comprises further specifies a point within the selected image, and wherein the subject is not authenticated as the user unless the point within the selected image matches a region of interest specified by the story. A system for authenticating a subject as a user, comprising: a display for displaying a story image associated with the user, a text story, and a plurality of decoy images together, wherein the text story comprises a sentence associated by the user with the story image but not with the decoy images; a gaze tracker for detecting a gaze path of the subject as the subject views the display; an eye movement classifier for identifying a fixation point of the gaze path; a region-of-interest mapper for determining an indicated image based on the fixation point; and a scoring engine for determining an authentication score based on the indicated image. The system of claim 8 , further comprising: a story generation engine configured to: retrieve the story image from a profile associated with the user; retrieve the plurality of decoy images from a data store; and generate the text story associated with the story image based on a predefined grammar rule. The system of claim 8 , wherein the display further displays an additional story image associated with the user. The system of claim 8 , wherein the system further comprises a data store storing a plurality of images associated with the user. The system of claim 8 , wherein the story image associated with the user was sourced from a social networking profile of the user. The system of claim 8 , wherein the decoy images are retrieved from a data store storing a plurality of publically accessible images. One or more non-transitory computer-readable media storing computer-executable instructions which, when executed by a processor perform a method of authenticating a subject as a user, comprising steps of: retrieving a plurality of story images from a social media profile of the user and metadata associated with each of the plurality of story images; retrieving a plurality of decoy images based on the plurality of images from the social media profile of the user; generating a text story based on the metadata associated with each of the plurality of story images, wherein the text story comprises a sentence associated by the user with the story images but not with the decoy images; presenting, to the subject, the text story and a set of images comprising the plurality of story images and the plurality of decoy images; tracking the user's gaze on the set of images to obtain a gaze scan path; analyzing the gaze scan path to determine a plurality of fixation points; and authenticating the subject as the user if the plurality of fixation points correspond to the plurality of story images. The media of claim 14 , wherein the text story specifies an order for the story images, wherein the step of analyzing the gaze scan path further produces an order for the fixation points, and wherein the subject is not authenticated as the user unless the order for the fixation points matches the order for the story images. The media of claim 14 , wherein the set of images is presented to the subject in a random order. The media of claim 14 , wherein a fixation point not corresponding to an image of the set of images is discarded. The media of claim 14 , wherein the user is not authenticated if a fixation point of the plurality of fixation points corresponds to a decoy image of the plurality of decoy images. The media of claim 14 , wherein the plurality of story images correspond to one or more of the set consisting of: the user's friends, places associated with the user, and events associated with the user. The media of claim 14 , wherein the plurality of decoy images are sourced from the user's social media profile. |
| CPC Classification | ELECTRIC DIGITAL DATA PROCESSING IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING TRANSMISSION OF DIGITAL INFORMATION; e.g. TELEGRAPHIC COMMUNICATION |
| Examiner | Mohammad W Reza |
| Extended Family | 159-502-050-777-608 098-756-746-928-08X 010-356-758-730-315 |
| Patent ID | 10467400 |
| Inventor/Author | Shyu Chi-ren Cao Hongfei Klaric Matthew Uhlmann Jeffrey |
| IPC | G06F7/04 G06F21/36 G06K9/00 G06K9/72 H04L29/06 |
| Status | Active |
| Owner | The Curators of The University of Missouri |
| Simple Family | 159-502-050-777-608 098-756-746-928-08X 010-356-758-730-315 |
| CPC (with Group) | G06F21/36 G06V10/768 G06V40/19 H04L63/06 |
| Issuing Authority | United States Patent and Trademark Office (USPTO) |
| Kind | Patent/New European patent specification (amended specification after opposition procedure) |
