Human facial detection and recognition system
Aspects of the present disclosure provide an image-based face detection and recognition system that processes and/or analyzes portions of an image using “image strips” and cascading classifiers to detect faces and/or various facial features, such an eye, nose, mouth, cheekbone, jaw line, etc.
1. A method comprising:
receiving, by at least one processor, live, high-definition video data from at least one camera, the high-definition data comprising a sequence of images and storing the sequence of images in a database;
detecting, by the at least one processor, at least a portion of a face from the sequence of images;
generating, by the at least one processor, a mapping of facial points corresponding to the at least the portion of the face from the sequence of images by generating a plurality of points on an image plane corresponding to the sequence of images and determining a distance between each point to the plurality of points, each point corresponding to at least one of an edge-like feature of the face and a ridge-like feature of the face;
cross-referencing, by the at least one processor, the mapping of facial points with a set of pre-stored and previously recognized facial images to identify a match, the match identified when a match rate percentage is greater than a particular percentage; and
triggering, by the at least one processor, an alert of the match and transmitting the alert for display to a computer device.
2. The method of claim 1 , further comprising receiving the live, high-definition video data from a first high-definition IP camera and a second high-definition IP camera.
3. The method of claim 2 , further comprising receiving the live, high-definition video data from a surveillance system associated with the first high-definition IP camera and the second high-definition IP camera, the first high-definition IP camera and the second high-definition IP camera capturing human interactions.
4. The method of claim 1 , further comprising comparing the mapping of facial points with each facial image of the set of pre-stored and previously recognized facial images until a match representing at least 90% of the facial points is satisfied.
5. The method of claim 1 , further comprising triggering the alert of the match, the alert of the match comprising a camera name, a terminal number, a time stamp, and a representative image from the sequence of images.
6. The method of claim 1 , further comprising generating a report based on the alert of the match and transmitting the report to the computer device as a markup document.
7. The method of claim 1 , further comprising reducing three-dimensional pose variations by generating the plurality of points of the image plane and projecting the plurality of points from the image plane to a surface of a mean shape.
8. A system comprising:
memory storing computer-readable instructions; and
at least one processor to execute the computer-readable instructions to:
receive live, high-definition video data from at least one camera, the high-definition data comprising a sequence of images and storing the sequence of images in a database;
detect at least a portion of a face from the sequence of images;
generate, by the at least one processor, a mapping of facial points corresponding to the at least the portion of the face from the sequence of images by generating a plurality of points on an image plane corresponding to the sequence of images and determining a distance between each point to the plurality of points, each point corresponding to at least one of an edge-like feature of the face and a ridge-like feature of the face;
cross-reference the mapping of facial points with a set of pre-stored and previously recognized facial images to identify a match, the match identified when a match rate percentage is greater than a particular percentage; and
trigger an alert of the match and transmit the alert for display to a computer device.
9. The system of claim 8 , the at least one processor further to receive the live, high-definition video data from a first high-definition IP camera and a second high-definition IP camera.
10. The system of claim 9 , the at least one processor further to receive the live, high-definition video data from a surveillance system associated with the first high-definition IP camera and the second high-definition IP camera, the first high-definition IP camera and the second high-definition IP camera capturing human interactions.
11. The system of claim 8 , the at least one processor further to compare the mapping of facial points with each facial image of the set of pre-stored and previously recognized facial images until a match representing at least 90% of the facial points is satisfied.
12. The system of claim 8 , the at least one processor further to trigger the alert of the match, the alert of the match comprising a camera name, a terminal number, a time stamp, and a representative image from the sequence of images.
13. The system of claim 8 , the at least one processor further to generate a report based on the alert of the match and transmit the report to the computer device as a markup document.
14. The system of claim 8 , the at least one processor further to reduce three-dimensional pose variations by generating the plurality of points of the image plane and projecting the plurality of points from the image plane to a surface of a mean shape.
15. A non-transitory computer-readable medium having instructions stored thereon, the instructions when executed by at least one processor, cause the processor to perform operations comprising:
receiving live, high-definition video data from at least one camera, the high-definition data comprising a sequence of images and storing the sequence of images in a database;
detecting at least a portion of a face from the sequence of images;
generating a mapping of facial points corresponding to the at least the portion of the face from the sequence of images by generating a plurality of points on an image plane corresponding to the sequence of images and determining a distance between each point to the plurality of points, each point corresponding to at least one of an edge-like feature of the face and a ridge-like feature of the face;
cross-referencing the mapping of facial points with a set of pre-stored and previously recognized facial images to identify a match, the match identified when a match rate percentage is greater than a particular percentage; and
triggering an alert of the match and transmitting the alert for display to a computer device.
16. The non-transitory computer-readable medium of claim 15 , the operations further comprising receiving the live, high-definition video data from a first high-definition IP camera and a second high-definition IP camera.
17. The non-transitory computer-readable medium of claim 16 , the operations further comprising receiving the live, high-definition video data from a surveillance system associated with the first high-definition IP camera and the second high-definition IP camera, the first high-definition IP camera and the second high-definition IP camera capturing human interactions.
18. The non-transitory computer-readable medium of claim 15 , the operations further comprising comparing the mapping of facial points with each facial image of the set of pre-stored and previously recognized facial images until a match representing at least 90% of the facial points is satisfied.
19. The non-transitory computer-readable medium of claim 15 , the operations further comprising triggering the alert of the match, the alert of the match comprising a camera name, a terminal number, a time stamp, and a representative image from the sequence of images.
20. The non-transitory computer-readable medium of claim 15 , the operations further comprising generating a report based on the alert of the match and transmitting the report to the computer device as a markup document.
21. The non-transitory computer-readable medium of claim 15 , the operations further comprising reducing three-dimensional pose variations by generating the plurality of points of the image plane and projecting the plurality of points from the image plane to a surface of a mean shape.