Face authentication based smart access control system

1. A method comprising:

detecting, by a motion detection module, a motion by a subject within a predetermined area of view;

assigning a unique session identification number to the subject detected within the predetermined area of view;

detecting a facial area of the subject detected within the predetermined area of view;

generating an image of the facial area of the subject;

assessing a quality of the image of the facial area of the subject;

determining an identity of the subject based on the image of the facial area of the subject;

identifying an intent of the subject; and

authorizing access to a point of entry based on the determined identity of the subject and based on the intent of the subject, wherein identifying an intent of the subject comprises:

upon detecting the facial area in a bounding box, commencing authentication of the subject;

calculating a directional vector of a face of the subject;

determine an intent of the subject to gain access to the point of entry based on the directional vector of the face of the subject; and

granting the access to the point of entry based on authentication of the subject and based on determining the intent of the subject.

2. The method of claim 1 , further comprising:

determining one or more additional subjects within the predetermined area of view; and

assigning a unique session identification number to each of the one or more additional subjects detected within a predetermined area of view.

3. The method of claim 1 , wherein the assessing a quality of the image of the facial area of the subject comprises:

assessing whether the quality of the image of the facial area of the object equates predetermined metric of quality; and

upon determining that the quality of the image of the facial area of the object is inferior to the predetermined metric of quality, discarding the image of the facial area of the subject and generating a second image of the facial area of the subject.

4. The method of claim 1 , further comprising:

detecting whether the facial area of the subject is photographic image; and

upon detecting that the facial area of the subject is a photographic image, generating a warning and restrict access to the point of entry.

5. The method of claim 1 , further comprising:

conducing an incremental training of the image of the facial area of the subject.

6. The method of claim 5 , wherein conducing an incremental training of the image of the facial area of the subject comprises:

capturing a first image of the facial area having facial landmarks;

converting the first image of the facial area into a first numeric vector;

capturing a second image of the facial area having facial landmarks;

converting the second image of the facial area into a second numeric vector;

calculating a weighted mean of the first numeric vector and the second numeric vector, wherein the weighted mean represents a change in a facial area; and

storing the weighted mean in the database.

7. The method of claim 1 , wherein determining an identity of the subject based on the image of the facial area of the subject comprises:

comparing the image of the facial area of the subject with a plurality of images stored in a database; and

authenticating the subject.

8. A non-transitory computer readable medium having program instructions stored thereon, that in response to execution by a computing device cause the computing device to perform operations comprising:

detecting a motion by a subject within a predetermined area of view;

assigning a unique session identification number to the subject detected within the predetermined area of view;

detecting a facial area of the subject detected within the predetermined area of view;

generating an image of the facial area of the subject;

assessing a quality of the image of the facial area of the subject;

determining an identity of the subject based on the image of the facial area of the subject;

identifying an intent of the subject; and

authorizing access to a point of entry based on the determined identity of the subject and based on the intent of the subject, wherein identifying an intent of the subject comprises:

upon detecting the facial area in a bounding box, commencing authentication of the subject;

calculating a directional vector of a face of the subject;

determine an intent of the subject to gain access to the point of entry based on the directional vector of the face of the subject; and

granting the access to the point of entry based on authentication of the subject and based on determining the intent of the subject.

9. The non-transitory computer readable medium of claim 8 , further comprising:

determining one or more additional subjects within the predetermined area of view; and

assigning a unique session identification number to each of the one or more additional subjects detected within a predetermined area of view.

10. The non-transitory computer readable medium of claim 8 , wherein the assessing a quality of the image of the facial area of the subject comprises:

assessing whether the quality of the image of the facial area of the object equates predetermined metric of quality; and

upon determining that the quality of the image of the facial area of the object is inferior to the predetermined metric of quality, discarding the image of the facial area of the subject and generating a second image of the facial area of the subject.

11. The non-transitory computer readable medium of claim 8 , further comprising:

detecting whether the facial area of the subject is photographic image; and

upon detecting that the facial area of the subject is a photographic image, generating a warning and restrict access to the access point.

12. The non-transitory computer readable medium of claim 8 , further comprising:

conducing an incremental training of the image of the facial area of the subject.

13. The non-transitory computer readable medium of claim 12 , wherein conducing an incremental training of the image of the facial area of the subject comprises:

capturing a first image of the facial area having facial landmarks;

converting the first image of the facial area into a first numeric vector;

capturing a second image of the facial area having facial landmarks;

converting the second image of the facial area into a second numeric vector;

calculating a weighted mean of the first numeric vector and the second numeric vector, wherein the weighted mean represents a change in a facial area; and

storing the weighted mean in the database.

14. An apparatus for face recognition comprising:

a processor; and

a memory to store computer program instructions, the computer program instructions when executed on the processor cause the processor to perform operations comprising:

detecting a motion by a subject within a predetermined area of view;

assigning a unique session identification number to the subject detected within the predetermined area of view;

detecting a facial area of the subject detected within the predetermined area of view;

generating an image of the facial area of the subject;

assessing a quality of the image of the facial area of the subject;

determining an identity of the subject based on the image of the facial area of the subject;

identifying an intent of the subject; and

authorizing access to a point of entry based on the determined identity of the subject and based on the intent of the subject, wherein identifying an intent of the subject comprises:

upon detecting the facial area in a bounding box, commencing authentication of the subject;

calculating a directional vector of a face of the subject;

determine an intent of the subject to gain access to the point of entry based on the directional vector of the face of the subject; and

granting the access to the point of entry based on authentication of the subject and based on determining the intent of the subject.

15. The apparatus of claim 14 , further comprising:

determining one or more additional subjects within the predetermined area of view; and

assigning a unique session identification number to each of the one or more additional subjects detected within a predetermined area of view.

16. The apparatus of claim 14 , wherein the assessing a quality of the image of the facial area of the subject comprises:

assessing whether the quality of the image of the facial area of the object equates predetermined metric of quality; and

upon determining that the quality of the image of the facial area of the object is inferior to the predetermined metric of quality, discarding the image of the facial area of the subject and generating a second image of the facial area of the subject.

17. The apparatus of claim 14 , further comprising:

detecting whether the facial area of the subject is photographic image; and

upon detecting that the facial area of the subject is a photographic image, generating a warning and restrict access to the access point.

18. The apparatus of claim 14 , further comprising:

conducing an incremental training of the image of the facial area of the subject.

19. The apparatus of claim 14 , wherein conducing an incremental training of the image of the facial area of the subject comprises:

capturing a first image of the facial area having facial landmarks;

converting the first image of the facial area into a first numeric vector;

capturing a second image of the facial area having facial landmarks;

converting the second image of the facial area into a second numeric vector;

calculating a weighted mean of the first numeric vector and the second numeric vector, wherein the weighted mean represents a change in a facial area; and

storing the weighted mean in the database.