# US 10,769,543 B2 · Double-layered image classification endpoint solution > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,769,543 B2 - Document ID: US10769543B2 - Status: Granted - Kind: B2 - Application number: 16/052,014 - Filed: 2018-08-01 - Published: 2020-02-06 - Granted: 2020-09-08 - Earliest claimed: 2018-08-01 - Assignees: Forcepoint LLC - Applicants: Forcepoint LLC - Inventors: Gal Itach; Shai Ungar; Ran Geler; Ayval Ron; Uri Elias - Web page: https://patentgrep.com/patent/US10769543B2 ## CPC - G06V 10/454: {Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]} - G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting - G06F 18/24: Classification techniques - G06F 21/36: by graphic or iconic representation - G06F 21/6218: {to a system of files or objects, e.g. local or distributed file system or database} - G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks - G06N 3/0464: Convolutional networks [CNN, ConvNet] - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06N 3/096: Transfer learning - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06V 10/764: using classification, e.g. of video objects - G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting - G06V 10/7796: {based on specific statistical tests} - G06V 10/82: using neural networks - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A system for image classification is disclosed that includes a central system configured to provide high reliability image data processing and recognition and a plurality of endpoint systems, each configured to provide image data processing and recognition with a lower reliability than the central system and to generate probability data. A decision switch disposed at each of the plurality of endpoint systems is configured to receive the probability data and to determine whether to deny access, grant access or generate a referral message to the central system, wherein the referral message includes at least a set of image data generated at the endpoint system. ## Claims ### Claim 1 A system for image classification, comprising: a central system configured to provide high reliability image data processing and recognition; a plurality of endpoint systems, each configured to provide image data processing and recognition with a lower reliability than the central system and to generate probability data; and a decision switch disposed at each of the plurality of endpoint systems, the decision switch configured to receive the probability data and to determine whether to deny access, grant access or generate a referral message to the central system, wherein the referral message includes at least a set of image data generated at the endpoint system. ### Claim 2 (depends on 1) The system of claim 1 wherein the central system further comprises a TensorFlow Inception V3 neural network. ### Claim 3 (depends on 1) The system of claim 1 wherein each of the endpoint systems further comprises a Mobilenet neural network. ### Claim 4 (depends on 1) The system of claim 1 wherein the decision switch further comprises a policy engine configured to receive an output from a neural network and to determine whether the output is greater than a first threshold or less than a second threshold. ### Claim 5 (depends on 4) The system of claim 4 further comprising an incident system configured to receive a control signal from the policy engine if the output is greater than the first threshold and to deny access to a resource. ### Claim 6 (depends on 4) The system of claim 4 further comprising an approval system configured to receive a control signal from the policy engine if the output is less than the second threshold and to allow access to a resource in response. ### Claim 7 (depends on 4) The system of claim 4 further comprising an uncertainty analysis system configured to receive a control signal from the policy engine if the output is less than the first threshold and greater than a second threshold and to generate a control signal for the central system in response. ### Claim 8 A system for image classification, comprising: a central system configured to provide high reliability image data processing and recognition; a plurality of endpoint systems, each configured to provide image data processing and recognition with a lower reliability than the central system and to generate probability data; and means for receiving the probability data and determining whether to deny access, grant access or generate a referral message to the central system, wherein the referral message includes at least a set of image data generated at the endpoint system. ### Claim 9 (depends on 8) The system of claim 8 wherein the central system further comprises a TensorFlow Inception V3 neural network. ### Claim 10 (depends on 8) The system of claim 8 wherein each of the endpoint systems further comprises a Mobilenet neural network. ### Claim 11 (depends on 8) The system of claim 8 further comprising means for receiving an output from a neural network and determining whether the output is greater than a first threshold or less than a second threshold. ### Claim 12 (depends on 11) The system of claim 11 further comprising an incident system configured to receive a control signal from the policy engine if the output is greater than the first threshold and to deny access to a resource. ### Claim 13 (depends on 11) The system of claim 11 further comprising an approval system configured to receive a control signal from the policy engine if the output is less than the second threshold and to allow access to a resource in response. ### Claim 14 (depends on 11) The system of claim 11 further comprising an uncertainty analysis system configured to receive a control signal from the policy engine if the output is less than the first threshold and greater than a second threshold and to generate a control signal for the central system in response.