# US 10,769,261 B2 · User image verification > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,769,261 B2 - Document ID: US10769261B2 - Status: Granted - Kind: B2 - Application number: 15/975,282 - Filed: 2018-05-09 - Published: 2019-11-14 - Granted: 2020-09-08 - Earliest claimed: 2018-05-09 - Assignees: Futurewei Technologies, Inc. - Applicants: Futurewei Technologies, Inc. - Inventors: Wei Jiang; Wei Wang - Web page: https://patentgrep.com/patent/US10769261B2 ## CPC - G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints - G06N 3/045: Combinations of networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/084: Backpropagation, e.g. using gradient descent - G06N 3/09: Supervised learning - G06V 10/454: {Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]} - G06V 10/764: using classification, e.g. of video objects - G06V 10/82: using neural networks - G06V 40/168: {Feature extraction; Face representation} - G06V 40/172: {Classification, e.g. identification} - G06V 40/40: Spoof detection, e.g. liveness detection - H04L 63/0861: {using biometrical features, e.g. fingerprint, retina-scan (cryptographic mechanisms or cryptographic arrangements for entity authentication using biological data H04L9/3231)} - H04L 63/102: {Entity profiles} - H04L 63/12: {Applying verification of the received information (cryptographic mechanisms or cryptographic arrangements for data integrity or data verification H04L9/32)} - 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 - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract A computer-implemented method verifies an image based authentication via one or more processors performing operations including receiving image data corresponding to a face identified by a facial recognition system, processing the received raw image data via a deep neural network trained on training data that includes images of both verified and fake faces to perform a temporal facial analysis, and generating a verification signal in response to the temporal facial analysis to indicate whether the raw image data is fake. ## Claims ### Claim 1 A computer-implemented method for verifying an image based authentication executed by one or more processors performing operations comprising: receiving raw image data corresponding to a face identified by a facial recognition system; processing the received raw image data via a neural network trained on training data that includes images of both verified and fake faces to perform a temporal facial analysis; and generating a verification signal in response to the temporal facial analysis to indicate whether the raw image data is fake, wherein the raw image data comprises identified face data and features of the identified face data and wherein the deep neural network comprises a first deep neural network to process the identified face data and a second, deep neural network to process the identified feature data, and wherein the first and second deep neural networks generate respective first and second data cubes, and wherein the deep neural network further comprises a third deep neural network, the operations further comprising merging the first and second data cubes to form a merged data cube, wherein the merged data cube is processed by the third deep neural network to generate the verification signal. ### Claim 2 (depends on 1) The computer-implemented method of claim 1 and further comprising granting access to one or more resources in response to the verification signal. ### Claim 3 (depends on 1) The computer-implemented method of claim 1 wherein the first and second data cubes w×h×d (width, height, and depth) dimensional data cubes, and wherein the first and second data cubes are concatenated to form the merged data cube. ### Claim 4 (depends on 1) The computer-implemented method of claim 1 wherein the neural network is trained by computing a loss, and using back propagation of the loss to update the neural network. ### Claim 5 (depends on 1) The computer-implemented method of claim 1 wherein the training data comprises temporally related real and fake labeled face images. ### Claim 6 (depends on 1) The computer-implemented method of claim 1 wherein the neural network comprises deep convolutional network. ### Claim 7 A device comprising: a memory storage comprising instructions; and one or more processors in communication with the memory storage, wherein the one or more processors execute the instructions to perform operations to verify an image based authentication comprising: receiving raw image data corresponding to a face identified by a facial recognition system; processing the received raw image data via a deep neural network trained on training data that includes images of both verified and fake faces to perform a temporal facial analysis; and generating a verification signal in response to the temporal facial analysis to indicate whether the raw image data is fake, wherein the raw image data comprises identified face data and features of the identified face data and wherein the deep neural network comprises a first deep neural network to process the identified face data and a second, deep neural network to process the identified feature data, and wherein the first and second deep neural networks generate respective first and second data cubes, and wherein the deep neural network further comprises a third deep neural network, the operations further comprising merging the first and second data cubes to form a merged data cube, wherein the merged data cube is processed by the third deep neural network to generate the verification signal. ### Claim 8 (depends on 7) The device of claim 7 and further comprising granting access to the device in response to the verification signal. ### Claim 9 (depends on 7) The device of claim 7 wherein the deep neural network is trained by computing a loss, and using back propagation of the loss to update the neural network and wherein the training data comprises temporally related real and fake labeled face images. ### Claim 10 (depends on 7) The device method of claim 7 wherein the deep neural network comprises deep convolutional network. ### Claim 11 (depends on 7) The device of claim 7 wherein the first and second data cubes w×h×d (width, height, and depth) dimensional data cubes, and wherein the first and second data cubes are concatenated to form the merged data cube. ### Claim 12 A non-transitory computer-readable media storing computer instructions for verifying an image based authentication, that when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving raw image data corresponding to a face identified by a facial recognition system; processing the received raw image data via a deep neural network trained on training data that includes images of both verified and fake to perform a temporal facial analysis; and generating a verification signal in response to the temporal facial analysis to indicate whether the raw image data was fake or not, wherein the raw image data comprises identified face data and features of the identified face data and wherein the deep neural network comprises a first deep neural network to process the identified face data and a second, deep neural network to process the identified feature data, and wherein the first and second deep neural networks generate respective first and second data cubes, and wherein the deep neural network further comprises a third deep neural network, the operations further comprising merging the first and second data cubes to form a merged data cube, wherein the merged data cube is processed by the third deep neural network to generate the verification signal. ### Claim 13 (depends on 12) The non-transitory computer-readable media of claim 12 wherein the operations further comprise granting access to the device in response to the verification signal. ### Claim 14 (depends on 12) The non-transitory computer-readable media of claim 12 wherein the deep neural network is trained by computing a loss, and using back propagation of the loss to update the neural network and wherein the training data comprises temporally related real and fake labeled face images. ### Claim 15 (depends on 12) The non-transitory computer-readable media method of claim 12 wherein the deep neural network comprises deep convolutional network. ### Claim 16 (depends on 15) The non-transitory computer-readable media of claim 15 wherein the first and second data cubes w×h×d (width, height, and depth) dimensional data cubes, and wherein the first and second data cubes are concatenated to form the merged data cube.