Security system for facility access control
A facility access control system and corresponding method are provided. The facility access control system includes a camera configured to capture an input image of a subject attempting to enter or exit a restricted facility. The facility access control system further includes a memory storing a deep learning model configured to perform multi-task learning for a pair of tasks including a liveness detection task and a face recognition task. The facility access control system also includes a processor configured to apply the deep learning model to the input image to recognize an identity of the subject in the input image regarding being authorized for access to the facility and a liveness of the subject. The liveness detection task is configured to evaluate a plurality of different distracter modalities corresponding to different physical spoofing materials to prevent face spoofing for the face recognition task.
1. A facility access control system, comprising:
a camera configured to capture an input image of a subject attempting to enter or exit a restricted facility;
a memory storing a deep learning model configured to perform multi-task learning for a pair of tasks including a liveness detection task and a face recognition task; and
a processor configured to apply the deep learning model to the input image to recognize an identity of the subject in the input image regarding being authorized for access to the facility and a liveness of the subject, and wherein the liveness detection task is configured to evaluate a plurality of different distractor modalities corresponding to different physical spoofing materials to prevent face spoofing for the face recognition task.
2. The facility access control system of claim 1 , wherein the processor is configured to selectively permit or restrict access to the facility, responsive to results of the liveness detection task and the face recognition task.
3. The facility access control system of claim 1 , wherein the processor is configured to lock a door to keep the subject out of the facility, responsive to results of the liveness detection task and the face recognition task.
4. The facility access control system of claim 1 , wherein the processor is configured to lock a door to keep the subject in the facility for detainment, responsive to results of the liveness detection task and the face recognition task.
5. The facility access control system of claim 4 , wherein the processor is configured to generate an alarm to indicate that the subject is an intruder in the facility, responsive to results of the liveness detection task and the face recognition task.
6. The facility access control system of claim 1 , wherein the different physical spoofing materials comprise spoofing materials selected from the group consisting of a 3D mask, a printed image, and an electronic display.
7. The facility access control system of claim 1 , wherein the processor is further configured to perform data preprocessing on the input image selected from the group consisting of image contrast enhancements, data augmentation, and cropping.
8. The facility access control system of claim 1 , wherein the processor is further configured to apply an image contrast enhancement to the input image by randomly adding one or more Gaussian distributed instances to an original RGB value of the input image.
9. The facility access control system of claim 1 , wherein the processor is further configured to apply an image contrast enhancement to the input images by adding one or more Gaussian distributed instances to a Hue, Saturation, and Value (HSV) domain and multiplying two or more coefficients in the HSV domain to further adjust the Saturation and the Value of the input image.
10. The facility access control system of claim 1 , wherein the processor is further configured to perform random central cropping on the input image.
11. The facility access control system of claim 1 , wherein the processor is further configured to perform a data augmentation process on the input images to augment data in the images and increase a generality of the deep learning model to the different distractor modalities.
12. The facility access control system of claim 1 , wherein the deep learning model is formed to include a plurality of layers, and the processor is further configured to train the deep learning model by freezing each of the plurality of layers except a last fully connected layer therein, and performing multi-task training by combining the liveness detection task and the face recognition task, wherein during the multi-task training, all weights of the plurality of layers are unfrozen.
13. The facility access control system of claim 1 , wherein the deep learning model is formed using an inception structure configured to multiply an output of a convolution layer of the deep learning model with the input image to produce a new image having amplified extracted features relative to the input image.
14. The facility access control system of claim 1 , wherein the deep learning model is formed using a loss structure that includes a face liveness penalty and a face recognition penalty.
15. A computer-implemented method for facility access control, the method comprising:
capturing, by a camera, an input image of a subject attempting to enter or exit a restricted facility;
storing, in a memory, a deep learning model configured to perform multi-task learning for a pair of tasks including a liveness detection task and a face recognition task; and
applying, by a processor, the deep learning model to the input image to recognize an identity of the subject in the input image regarding being authorized for access to the facility and a liveness of the subject, and wherein the liveness detection task is configured to evaluate a plurality of different distractor modalities corresponding to different physical spoofing materials to prevent face spoofing for the face recognition task.
16. The computer-implemented method of claim 15 , further comprising selectively permitting or restricting access to the facility, responsive to results of the liveness detection task and the face recognition task.
17. The computer-implemented method of claim 15 , further comprising locking a door to keep the subject out of the facility, responsive to results of the liveness detection task and the face recognition task.
18. The facility access control system of claim 15 , further comprising locking a door to keep the subject in the facility for detainment, responsive to results of the liveness detection task and the face recognition task.
19. The facility access control system of claim 18 , wherein the processor is configured to generate an alarm to indicate that the subject is an intruder in the facility, responsive to results of the liveness detection task and the face recognition task.
20. A computer program product for facility access control, the computer program product comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising:
capturing, by a camera, an input image of a subject attempting to enter or exit a restricted facility;
storing, in a memory, a deep learning model configured to perform multi-task learning for a pair of tasks including a liveness detection task and a face recognition task; and
applying, by a processor, the deep learning model to the input image to recognize an identity of the subject in the input image regarding being authorized for access to the facility and a liveness of the subject, and wherein the liveness detection task is configured to evaluate a plurality of different distractor modalities corresponding to different physical spoofing materials to prevent face spoofing for the face recognition task.