Multiple-factor recognition and validation for security systems
A security system can conditionally grant or deny access to a protected area using an artificial intelligence system to analyze images. In an example, an access control method can include receiving candidate information about a face and gesture from a first individual and receiving other image information from or about a second individual. The candidate information can be analyzed using a neural network-based recognition processor that can provide a first recognition result indicating whether the first individual corresponds to a first enrollee of the security system, and can provide a second recognition result indicating whether the second individual corresponds to a second enrollee of the security system. The example method can include receiving a passcode, such as from the first individual. Access can be conditionally granted or denied based on the passcode and the recognition results.
1. A system to conditionally grant or deny access to a protected area using image-based recognition, the system comprising:
an imaging device;
a sensor configured to collect audio or visual context information;
a first recognition processor configured to receive image information from the imaging device; and
an access control processor configured to execute instructions that configure the access control processor to:
receive candidate face information corresponding to a first individual from the imaging device;
receive other information from or about a second individual in proximity of the first individual;
receive audio or visual context information from a proximity of the protected area from the sensor;
provide the candidate face information to the first recognition processor;
provide a first recognition result using the first recognition processor and an authentication threshold that is based on the audio or visual context information, wherein providing the first recognition result includes providing a positive result when the authentication threshold is low and providing a negative result when the authentication threshold is high;
provide the other information from or about the second individual to a second recognition processor and, in response, receive a second recognition result indicating an access risk metric; and
conditionally grant or deny access to the protected area based on the first recognition result and the second recognition result.
2. The system of claim 1 , wherein the first recognition processor and the second recognition processor are a single, same recognition processor.
3. The system of claim 1 , wherein the instructions to receive other information from or about the second individual include instructions to receive face information corresponding to the second individual from the imaging device.
4. The system of claim 1 , wherein the audio or visual context information includes information about an environment of the protected area.
5. The system of claim 4 , wherein the environment includes one or more of: a factory, a building, a residence, a multiple-unit dwelling, or a neighborhood.
6. The system of claim 1 , wherein the audio or visual context information includes information about a vehicle at or near the protected area.
7. The system of claim 1 , wherein the instructions further configure the access control processor to:
prompt the first individual for a passcode after a specified time delay; and
receive the passcode from the first individual, wherein to conditionally grant or deny access to the protected area is based on the first recognition result and the second recognition result and on the passcode.
8. The system of claim 7 , wherein the access control processor prompts the first individual for the passcode after receiving the first recognition result and the second recognition result.
9. The system of claim 1 , wherein the sensor is one of a plurality of sensors, wherein each sensor of the plurality of sensors is registered with the system, and wherein the system further comprises a sensor interface configured to:
identify each sensor of the plurality of sensors; and
access data from each sensor of the plurality of sensors.
10. The system of claim 9 , wherein the plurality of sensors includes one or more of: an audio sensor, a microphone, an imaging sensor separate from the imaging device, a biometric sensor, or a physiologic sensor.
11. A non-transitory computer-readable medium, with instructions stored thereon that, when executed by a processor of a computing device, cause the processor to:
receive candidate face information corresponding to a first individual from an imaging device;
receive other information from or about a second individual in proximity of the first individual;
receive audio or visual context information from a proximity of a protected area from a sensor;
provide the candidate face information to a first recognition processor;
provide a first recognition result using the first recognition processor and an authentication threshold that is based on the audio or visual context information, wherein providing the first recognition result includes providing a positive result when the authentication threshold is low and providing a negative result when the authentication threshold is high;
provide the other information from or about a second individual to a second recognition processor and, in response, receiving a second recognition result indicating an access risk metric; and
conditionally grant or deny access to the protected area based on the first recognition result and the second recognition result.
12. The non-transitory computer-readable medium of claim 11 , wherein the instructions further cause processor to:
prompt the first individual for a passcode after a specified time delay; and
receive the passcode from the first individual, wherein to conditionally grant or deny access to the protected area is based on the first recognition result and the second recognition result and on the passcode.
13. The non-transitory computer-readable medium of claim 12 , wherein the processor prompts the first individual for the passcode after receiving the first recognition result and the second recognition result.
14. The non-transitory computer-readable medium of claim 11 , wherein the first recognition processor and the second recognition processor are a single, same neural network-based recognition processor.
15. The non-transitory computer-readable medium of claim 11 , wherein the audio or visual context information includes information about an environment of the protected area.
16. The non-transitory computer-readable medium of claim 15 , wherein the information about the environment includes one or more of: a factory, a building, a residence, a multiple-unit dwelling, or a neighborhood.
17. A method for using a security system to conditionally grant or deny access to a protected area using image-based recognition, the method comprising:
receiving image information at or near the protected area;
providing first image information to a neural network-based recognition processor and, in response, receiving a first recognition result indicating whether a recognized first individual is enrolled with the security system, wherein the first recognition result is based in part on audio or visual context information in or proximal to the protected area;
providing second image information to the neural network-based recognition processor and, in response, receiving an access risk metric based on a recognized second individual who is in or proximal to the protected area; and
conditionally granting or denying access to the protected area based on the first recognition result and the access risk metric.
18. The method of claim 17 , comprising determining an authentication threshold using the audio or visual context information, and wherein the first recognition result indicates a positive result when the authentication threshold is low and the first recognition result indicates a negative result when the authentication threshold is high.
19. The method of claim 17 , comprising:
receiving a code from the recognized first individual;
determining whether the code received from the recognized first individual indicates a duress code; and
generating an access control signal based on the first recognition result, the access risk metric, and a determined type of the duress code.
20. The method of claim 19 , comprising:
generating an alert based on the determined type of the duress code; and
providing the access control signal to a barrier of the protected area, wherein the access control signal grants or denies entry to the protected area via the barrier based on the determined type of the duress code.