# US 11,443,020 B2 · Method and system for alleviating authenticity of sensors in biometric authentication > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,020 B2 - Document ID: US11443020B2 - Status: Granted - Kind: B2 - Application number: 16/797,028 - Filed: 2020-02-21 - Published: 2021-07-01 - Granted: 2022-09-13 - Earliest claimed: 2019-12-31 - Assignees: Wipro Limited - Applicants: Wipro Limited - Inventors: Rishav Das - Web page: https://patentgrep.com/patent/US11443020B2 ## CPC - G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints - G06F 18/21: Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation - G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06N 20/00: Machine learning - G06V 10/764: using classification, e.g. of video objects - G06V 10/82: using neural networks - G06V 40/12: Fingerprints or palmprints - G06V 40/1347: {Preprocessing; Feature extraction} - G06N 3/044: Recurrent networks, e.g. Hopfield networks - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A method and authentication system for alleviating authenticity of sensors in biometric authentication is disclosed. The authentication system receives fingerprint data from a plurality of sensing devices configured in the authentication system and extract one or more attributes associated with the fingerprint data. An expanded value for each of the one or more attributes is determined based on one or more predefined techniques. The authentication system (101) trains a model associated with authentication of fingerprints using the one or more attributes and corresponding expanded value. Further, one or more errors associated with the fingerprint data are predicted based on fingerprint data received over a period of time in real-time and the model is retrained based on the predicted one or more errors to alleviate authenticity of sensors in biometric authentication. ## Claims ### Claim 1 An authentication system for alleviating authenticity of sensors in biometric authentication, comprising: a processor; and a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to: receive fingerprint data from a plurality of sensing devices configured in the authentication system; extract one or more attributes associated with the fingerprint data; determine an expanded value for each of the one or more attributes based on one or more predefined techniques; train a model associated with authentication of fingerprints using the one or more attributes and corresponding expanded value; predict one or more errors associated with the fingerprint data based on fingerprint data received over a period of time in real-time; and perform retraining of the model based on the predicted one or more errors to alleviate authenticity of sensors in biometric authentication. ### Claim 2 (depends on 1) The authentication system as claimed in claim 1, wherein the one or more attributes comprises pixel values, patterns values, pre-defined template values, numerical and integers. ### Claim 3 (depends on 1) The authentication system as claimed in claim 1, wherein the one or more attributes corresponds to a type of the plurality of sensing devices and one or more external environment parameters. ### Claim 4 (depends on 1) The authentication system as claimed in claim 1, wherein the processor determines the expanded value by identifying an upper limit and a lower limit for the one or more attributes along with a plurality of distortion angles. ### Claim 5 (depends on 1) The authentication system as claimed in claim 1, wherein the processor authenticates fingerprints of a user in real-time. ### Claim 6 (depends on 1) The authentication system as claimed in claim 1, wherein the processor predicts the one or more errors by: determining at least one error in the fingerprint data over the period of time based on actual stored fingerprint data associated with the user; and performing one or more modification in the model associated with authentication of fingerprints based on the at least one error in the fingerprint data. ### Claim 7 A non-transitory computer readable medium including instruction stored thereon that when processed by at least one processor cause an authentication system to perform operation comprising: receiving fingerprint data from a plurality of sensing devices configured in the authentication system; extracting one or more attributes associated with the fingerprint data; determining an expanded value for each of the one or more attributes based on one or more predefined techniques; training a model associated with authentication of fingerprints using the one or more attributes and corresponding expanded value; predicting one or more errors associated with the fingerprint data based on fingerprint data received over a period of time in real-time; and performing retraining of the model based on the predicted one or more errors to alleviate authenticity of sensors in biometric authentication. ### Claim 8 (depends on 7) The medium as claimed in claim 7, wherein the one or more attributes comprises pixel values, patterns values, pre-defined template values, numerical and integers. ### Claim 9 (depends on 7) The medium as claimed in claim 7, wherein the one or more attributes corresponds to a type of the plurality of sensing devices and one or more external environment parameters. ### Claim 10 (depends on 7) The medium as claimed in claim 7, wherein the instructions causes the processor to determine the expanded value comprises identifying an upper limit and a lower limit for the one or more attributes along with a plurality of distortion angles. ### Claim 11 (depends on 7) The medium as claimed in claim 7, wherein the instructions causes the processor to authenticate fingerprints of a user in real-time. ### Claim 12 (depends on 7) The medium as claimed in claim 7, wherein the instructions causes the processor to predict the one or more errors by: determine at least one error in the fingerprint data over the period of time based on actual stored fingerprint data associated with the user, and one or more modification in the model associated with authentication of fingerprints based on the at least one error in the fingerprint data. ### Claim 13 A method of alleviating authenticity of sensors in biometric authentication, the method comprising: receiving, by an authentication system, fingerprint data from a plurality of sensing devices configured in the authentication system; extracting, by the authentication system, one or more attributes associated with the fingerprint data; determining, by the authentication system, an expanded value for each of the one or more attributes based on one or more predefined techniques; training, by the authentication system, a model associated with authentication of fingerprints using the one or more attributes and corresponding expanded value; predicting, by the authentication system, one or more errors associated with the fingerprint data based on fingerprint data received over a period of time in real-time; and performing, by the authentication system, retraining of the model based on the predicted one or more errors to alleviate authenticity of sensors in biometric authentication. ### Claim 14 (depends on 13) The method as claimed in claim 13, wherein the one or more attributes comprises pixel values, patterns values, pre-defined template values, numerical and integers. ### Claim 15 (depends on 13) The method as claimed in claim 13, wherein the one or more attributes corresponds to a type of the plurality of sensing devices and one or more external environment parameters. ### Claim 16 (depends on 13) The method as claimed in claim 13, wherein determining the expanded value comprises identifying an upper limit and a lower limit for the one or more attributes along with a plurality of distortion angles. ### Claim 17 (depends on 13) The method as claimed in claim 13 further comprising authenticating fingerprints of a user in real-time. ### Claim 18 (depends on 13) The method as claimed in claim 13, wherein predicting the one or more errors comprises: determining, by the authentication system (101), at least one error in the fingerprint data over the period of time based on actual stored fingerprint data associated with the user; performing, by the authentication system (101), one or more modification in the model (207) associated with authentication of fingerprints based on the at least one error in the fingerprint data.