US 2017/0286787 A1Published application

Systems and methods for authentication based on human teeth pattern

AssigneeTata Consultancy Services Limited

InventorsRobin TOMMY, Reshmi RAVINDRANATHAN, Deen DAYAL MOHAN, Hima JOSE, Sarath SIVAPRASAD

Life of this patent

Estimating the term…

Loading patent…

Abstract

An automated system and method to authenticate one or more users based on capturing one or more images of a set of teeth, obtaining a selected image from the one or more captured images and extracting a portion of the selected image to obtain an extracted image. Each extracted image is converted into a grayscale image and stored in a database along with the username and the user keyword of the one or more users. A unique signature matrix and a pattern vector is generated by processing the grayscale image and stored in the database along with the username. One or more images comprising a set of teeth of at least one user is captured and a unique signature matrix obtained from the same is compared with a set of unique signature matrices previously stored in the database and at least one action is triggered based on the comparison.

Claims20

Dependent claims

A processor implemented method comprising:

(a) capturing, by a hardware processor, a user name, a user keyword and one or more images of a set of teeth of each of one or more users using an image capturing device, to obtain one or more captured images;
(b) obtaining, by said hardware processor, a selected image from said one or more captured images of said one or more users, based on one or more selection parameters being applied to said one or more captured images;
(c) extracting, by said hardware processor, a portion of said selected image of said one or more users to obtain an extracted image of each of said one or more users;
(d) converting, by said hardware processor, said extracted image into a grayscale image and storing said grayscale image in a database along with said username and said user keyword of each of said one or more users;
(e) generating, by said hardware processor, a unique signature matrix from said grayscale image and storing said unique signature matrix in said database along with said username of each of said one or more users;
(f) generating, by said hardware processor, a pattern vector for each of said one or more users by combining a set of alphanumeric characters, said user keyword of each of said one or more users, and a pattern indicator to refer to one of a set of patterns which has been selected for said grayscale image and storing said pattern vector in said database along with said username of each of said one or more users;
(g) obtaining, by said hardware processor, one or more images comprising a set of teeth of at least one user using an image capturing device, to obtain one or more captured images of said at least one user and repeating the steps (b) to (e) to obtain a unique signature matrix for said at least one user;
(h) performing a comparison between said unique signature matrix with a set of unique signature matrices previously stored in said database;
and
(i) triggering at least one action based on said comparison.

7 more elements

A system comprising:

a memory storing instructions and a database;
and
a hardware processor coupled to said memory, wherein said hardware processor is configured by said instructions to:
(a) capture a user name, a user keyword and one or more images of a set of teeth of each of one or more users using an image capturing device, to obtain one or more captured images,
(b) obtain a selected image from said one or more captured images of said one or more users, based on one or more selection parameters being applied to said one or more captured images,
(c) extract a portion of said selected image of said one or more users to obtain an extracted image of each of said one or more users,
(d) convert said extracted image into a grayscale image and storing said grayscale image in a database along with said username and said user keyword of each of said one or more users,
(e) generate a unique signature matrix from said grayscale image and store said unique signature matrix in said database along with said username of each of said one or more users,
(f) generate a pattern vector for each of said one or more users by combining a set of alphanumeric characters, said user keyword of each of said one or more users, and a pattern indicator to refer to one of a set of patterns which has been selected for said grayscale image and store said pattern vector in said database along with said username of each of said one or more users,
(g) obtain one or more images comprising a set of teeth of at least one user using an image capturing device, to obtain one or more captured images of said at least one user and repeating the steps (b) to (e) to obtain a unique signature matrix for said at least one user,
(h) perform a comparison between said unique signature matrix with a set of unique signature matrices previously stored in said database, and
(i) trigger at least one action based on said comparison.

9 more elements

One or more non-transitory machine readable information storage mediums comprising one or more instructions which when executed by one or more hardware processors causes:

(a) capturing, by a hardware processor, a user name, a user keyword and one or more images of a set of teeth of each of one or more users using an image capturing device, to obtain one or more captured images;
(b) obtaining, by said hardware processor, a selected image from said one or more captured images of said one or more users, based on one or more selection parameters being applied to said one or more captured images;
(c) extracting, by said hardware processor, a portion of said selected image of said one or more users to obtain an extracted image of each of said one or more users;
(d) converting, by said hardware processor, said extracted image into a grayscale image and storing said grayscale image in a database along with said username and said user keyword of each of said one or more users;
(e) generating, by said hardware processor, a unique signature matrix from said grayscale image and storing said unique signature matrix in said database along with said username of each of said one or more users;
(f) generating, by said hardware processor, a pattern vector for each of said one or more users by combining a set of alphanumeric characters, said user keyword of each of said one or more users, and a pattern indicator to refer to one of a set of patterns which has been selected for said grayscale image and storing said pattern vector in said database along with said username of each of said one or more users;
(g) obtaining, by a said hardware processor, one or more images comprising a set of teeth of at least one user using an image capturing device, to obtain one or more captured images of said at least one user and repeating the steps (b) to (e) to obtain a unique signature matrix for said at least one user;
(h) performing a comparison between said unique signature matrix with a set of unique signature matrices previously stored in said database;
and
(i) triggering at least one action based on said comparison.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 15/271,971Filed 21 Sep 2016
Priority: IN 20162101087129 Mar 2016
Published: 5 Oct 2017
Term ends: Not estimatedThe source records don’t support an estimate.

Classification5 codes

G06F 21/32
User authentication: using biometric data, e.g. fingerprints, iris scans or voiceprints
G06V 10/70
Arrangements for image or video recognition or understanding: using pattern recognition or machine learning
G06V 40/10
Recognition of biometric, human-related or animal-related patterns in image or video data: human or animal bodies, e.g. vehicle occupants or…
G06F
Computing and data processing

Family

US 9,916,511 B2Related patent
US 2017/0286787 A1This patent

From the US filing history. Foreign family members aren’t listed.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key