Facial recognition for multi-stream video using high probability group and facial network of related persons

Patent metadata

Field	Value
Publication number	US-11010599-B2
Application number	US-201916400303-A
Country	US
Kind code	B2
Filing date	May 1, 2019
Priority date	May 1, 2019
Publication date	May 18, 2021
Grant date	May 18, 2021

Abstract

Techniques are provided for facial recognition using a high probability group database and a facial network of related persons. One method comprises maintaining a probability-based database of facial images comprising a subset of individuals from a first database of facial images of a plurality of individuals based on a probability of individuals appearing in sequences of image frames at a given time; applying a face detection algorithm to at least one sequence of image frames to identify one or more faces in the sequences of image frames; maintaining a facial network of related persons associated with the probability-based database by obtaining facial images of one or more additional individuals from the first database that satisfy a predefined related person criteria with respect to individuals identified in at least one sequence of image frames; and applying a facial recognition to at least sequence of image frames using at least the probability-based database and the facial network of related persons to identify individuals in the sequence of image frames.

First claim

What is claimed is:

1. A method, comprising:
maintaining a probability-based database of facial images comprising a subset of individuals from a first database of facial images of a plurality of individuals, wherein the subset is obtained based on a probability of individuals appearing in one or more sequences of image frames at a given time;
applying a face detection algorithm to at least one of the sequences of image frames to identify one or more faces in the one or more sequences of image frames;
maintaining a facial network of related persons associated with the probability-based database by obtaining one or more facial images of one or more additional individuals from the first database of images that satisfy one or more predefined related person criteria with respect to one or more individuals identified in at least one of the sequences of image frames, wherein the one or more facial images of the one or more additional individuals from the first database of images are obtained based on at least one of: a network size of the facial network and a number of edges of the facial network; and
applying facial recognition to at least one of the sequences of image frames using at least the probability-based database and the facial network of related persons to identify one or more individuals in the at least one sequence of image frames,
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

2. The method of claim 1 , wherein the one or more facial images of the one or more additional individuals from the first database of images are obtained further based on a community name.

3. The method of claim 1 , wherein the probability-based database of facial images is comprised of facial images of one or more individuals that appeared in one or more prior image frames and is stored in one or more of a local memory, a cache, an edge device, a cloud device and an Internet device.

4. The method of claim 1 , wherein a new image frame is processed to associate a face in the new image frame with a face that has previously been tracked if a facial image in the new image frame satisfies a predefined similarity metric with respect to the face that has previously been tracked.

5. The method of claim 1 , wherein a new image frame is processed to assign a name to a facial image in the new image frame if the facial image satisfies a predefined similarity metric with a given face in the probability-based database.

6. The method of claim 1 , wherein a new image frame is processed to add a facial image in the new image frame to the probability-based database if the facial image does not satisfy a predefined similarity metric with a given face in the probability-based database.

7. The method of claim 1 , further comprising the step of matching one or more images of a face of an unnamed person in the probability-based database to images of known faces in the first database to obtain a name of the unnamed person.

8. A computer program product, comprising a non-transitory machine-readable storage medium having encoded therein executable code of one or more software programs, wherein the one or more software programs when executed by at least one processing device perform the following steps:
maintaining a probability-based database of facial images comprising a subset of individuals from a first database of facial images of a plurality of individuals, wherein the subset is obtained based on a probability of individuals appearing in one or more sequences of image frames at a given time;
applying a face detection algorithm to at least one of the sequences of image frames to identify one or more faces in the one or more sequences of image frames;
maintaining a facial network of related persons associated with the probability-based database by obtaining one or more facial images of one or more additional individuals from the first database of images that satisfy one or more predefined related person criteria with respect to one or more individuals identified in at least one of the sequences of image frames, wherein the one or more facial images of the one or more additional individuals from the first database of images are obtained based on at least one of: a network size of the facial network and a number of edges of the facial network; and
applying facial recognition to at least one of the sequences of image frames using at least the probability-based database and the facial network of related persons to identify one or more individuals in the at least one sequence of image frames.

9. The computer program product of claim 8 , wherein the one or more facial images of the one or more additional individuals from the first database of images are obtained further based on a community name.

10. The computer program product of claim 8 , wherein a new image frame is processed to associate a face in the new image frame with a face that has previously been tracked if a facial image in the new image frame satisfies a predefined similarity metric with respect to the face that has previously been tracked.

11. The computer program product of claim 8 , wherein a new image frame is processed to assign a name to a facial image in the new image frame if the facial image satisfies a predefined similarity metric with a given face in the probability-based database.

12. The computer program product of claim 8 , wherein a new image frame is processed to add a facial image in the new image frame to the probability-based database if the facial image does not satisfy a predefined similarity metric with a given face in the probability-based database.

13. An apparatus, comprising:
a memory; and
at least one processing device, coupled to the memory, operative to implement the following steps:
maintaining a probability-based database of facial images comprising a subset of individuals from a first database of facial images of a plurality of individuals, wherein the subset is obtained based on a probability of individuals appearing in one or more sequences of image frames at a given time;
applying a face detection algorithm to at least one of the sequences of image frames to identify one or more faces in the one or more sequences of image frames;
maintaining a facial network of related persons associated with the probability-based database by obtaining one or more facial images of one or more additional individuals from the first database of images that satisfy one or more predefined related person criteria with respect to one or more individuals identified in at least one of the sequences of image frames, wherein the one or more facial images of the one or more additional individuals from the first database of images are obtained based on at least one of: a network size of the facial network and a number of edges of the facial network; and
applying facial recognition to at least one of the sequences of image frames using at least the probability-based database and the facial network of related persons to identify one or more individuals in the at least one sequence of image frames.

14. The apparatus of claim 13 , wherein the one or more facial images of the one or more additional individuals from the first database of images are obtained further based on a community name.

15. The apparatus of claim 13 , wherein a new image frame is processed to associate a face in the new image frame with a face that has previously been tracked if a facial image in the new image frame satisfies a predefined similarity metric with respect to the face that has previously been tracked.

16. The apparatus of claim 13 , wh

Assignees

• Emc Ip Holding Co Llc

Inventors

• Gefen Avitan
• Savir Amihai
• Sagi Omer

Classifications

• G06V40/173 Primary

  face re-identification, e.g. recognising unknown faces across different face tracks · CPC title

• G06V20/30

  in albums, collections or shared content, e.g. social network photos or video · CPC title

• G06V40/50

  Maintenance of biometric data or enrolment thereof · CPC title

• G06V20/41

  Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49) · CPC title

• G06V40/161

  Detection; Localisation; Normalisation · CPC title