Human facial detection and recognition system

• US 10,438,055 B2
• Filed: 03/13/2019
• Issued: 10/08/2019
• Est. Priority Date: 10/24/2013
• Status: Active Grant

• Current Assignee: Blue Line Security Solutions, LLC
• Original Assignee: Blue Line Security Solutions, LLC
• Inventors: Silva, Marcos
• Primary Examiner(s): Braniff, Christopher
• Application Number:
  US16/352,170
• Publication Number:
  US 20190213395A1
• Time in Patent Office: 209 Days
• Field of Search: None
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06V 10/446 using Haar-like filters, e.g. using integral image techniques
• CPC Class Codes: G06V 10/7553 based on shape, e.g. active shape models [ASM]
• CPC Class Codes: G06V 40/165 using facial parts and geometric relationships
• CPC Class Codes: G06V 40/166 using acquisition arrangements
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

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.

Claims

1. A method comprising:

receiving, by at least one processor, high-definition video data from at least one camera associated with a surveillance system, 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 each facial image of a set of pre-stored and previously recognized facial images to perform one of recognizing the face and not recognizing the face; and

automatically generating, by the at least one processor, information associated with the face and transmitting the information associated with the face.

2. The method of claim 1, further comprising receiving the 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 high-definition video data from the 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 face is recognized as a match representing at least 90% of the facial points.

5. The method of claim 1, further comprising automatically generating the information, the information 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 including the information associated with the face and transmitting the report to a computer device as a Portable Document Format 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 high-definition video data from at least one camera associated with a surveillance system, the high-definition data comprising a sequence of images and store 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 each facial image of a set of pre-stored and previously recognized facial images to perform one of recognize the face and not recognize the face; and

automatically generate information associated with the face and transmit the information associated with the face.

9. The system of claim 8, the at least one processor further to receive the 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 high-definition video data from the 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 face is recognized as a match representing at least 90% of the facial points.

12. The system of claim 8, the at least one processor further to automatically generate the information, the information 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 including the information associated with the face and transmit the report to a computer device as a Portable Document Format 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 high-definition video data from at least one camera associated with a surveillance system, 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 each facial image of a set of pre-stored and previously recognized facial images to perform one of recognizing the face and not recognizing the face; and

automatically generating information associated with the face and transmitting the information associated with the face.

16. The non-transitory computer-readable medium of claim 15, the operations further comprising receiving the 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 high-definition video data from the 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 face is recognized as a match representing at least 90% of the facial points.

19. The non-transitory computer-readable medium of claim 15, the operations further comprising automatically generating the information, the information 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 including the information associated with the face and transmitting the report to a computer device as a Portable Document Format 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.