Systems and methods for facial recognition in a campus setting
A security system includes a camera having a field of vision. The camera sends image frames to a machine readable memory. A processor is accessible to the machine readable memory. The processor performs acts of receiving from the camera a plurality of frames; detecting an object entering the field of vision; determining whether the object is a person; tracking a moving path of the person; and performing facial recognition on the person using at least one of the plurality of frames.
1. A computing system, comprising
a camera having a field of vision, the camera sending image frames to a machine readable memory;
a processor accessible to the machine readable memory, the processor performing:
receiving from the camera a plurality of frames;
detecting an object entering the field of vision;
determining whether the objects a person;
if the object is a person, performing facial recognition on the person using at least one of the plurality of frames to determine the identification of the person;
comparing the identification of the person to a first database of persons to watch and if the person is in the first database, generating a security alert; and
if the person is not in the first database, comparing the identification of the person to a second database of expected persons, and if the person is not in the database of expected persons, generating a security alert;
wherein a first size of the first database is smaller than a second size of the second database and the second size of the second database is smaller than a third size of a third database containing all persons such that the speed of the search is increased by comparing the person to a smaller database first.
2. The computing system according to claim 1 , the processor further performing:
using one of the plurality of frames as a presented image; and
comparing a plurality of facial features of the presented image with a stored image.
3. The computing system according to claim 2 , wherein the stored image is stored in a first machine readable memory that stores recurring persons.
4. The computing system according to claim 3 , wherein the recurring persons are expected to be in the field of vision of the camera.
5. The computing system according to claim 2 , wherein the stored image is stored in a second machine readable memory that stores watched persons.
6. The computing system according to claim 2 , the processor performing
determining whether the presented image has a resolution of facial features higher than the stored image.
7. The computing system according to claim 6 , the processor performing
replacing the stored image with the presented image.
8. The computing system according to claim 2 , the processor performing
determining whether a second image from the plurality of frames has a resolution of facial features higher than the stored image; and
replacing the stored image with the second image.