Eyelock LLC

Mikhail Teverovskiy

Keith James Hanna

Manoj Aggarwal

Sarvesh Makthal

The present disclosure describes systems and methods for authorization. The method may include accessing, by an authorization engine for a transaction by a user, an activity pattern model of the user from a database. The activity pattern model of the user may be indicative of a geospatial behavior of the user over time. The authorization engine may determine a set of sensors available for facilitating the transaction, each of the sensors assigned with a usability value prior to the transaction. The authorization engine may access an activity pattern model of the sensors, the activity pattern model of the sensors indicative of geospatial characteristics of one or more of the sensors over time. The authorization engine may determine a convenience metric for each of a plurality of subsets of the sensors, using the activity pattern model of the user, the activity pattern model of the sensors, and usability values of corresponding sensors. Each of the plurality of subsets may include corresponding sensors that can be used in combination to facilitate the transaction. The authorization engine may select, using the determined convenience metrics, a subset from the plurality of subsets to use for the transaction.

Model-based prediction of an optimal convenience metric for authorizing transactions

The present disclosure describes systems and methods of using iris data for authentication. A biometric encoder may translate an image of the iris into a rectangular representation of the iris. The rectangular representation may include a plurality of rows corresponding to a plurality of annular portions of the iris. The biometric encoder may extract an intensity profile from at least one of the plurality of rows, the intensity profile modeled as a stochastic process. The biometric encoder may obtain a stationary stochastic component of the intensity profile by removing a non-stationary stochastic component from the intensity profile. The biometric encoder may remove at least a noise component from the stationary component using auto-regressive based modeling, to produce at least a non-linear background signal, and may combine the non-stationary component and the at least the non-linear background signal, to produce a biometric template for authenticating the person.

Growing community of inventors

White Plains, NY, United States of America

Mikhail Teverovskiy