Automatic authentification for MES system using facial recognition

An authentication method comprising:

• training at least one neural network to produce first feature vectors from facial features extracted from a population of first facial images and using the at least one neural network to generate augmented first feature vectors with semantic variables corresponding to elements separate from facial characteristics;
• training a discriminative classifier to identify closely matching ones of the first feature vectors;
• using the at least one neural network to produce a second feature vector from facial features extracted from a second facial image;
• using the discriminative classifier to identify whether at least one augmented first feature vector and the second feature vector meet a correlation threshold indicating a presence of the separate elements in the second feature vector;
• and
• allowing a user, from whom the second facial image was acquired, access if the correlation threshold is met.

An authentication system comprising:

• a database management system including a processor, a non-transitory computer readable medium, and one or more programs stored on the computer readable medium, wherein the processor, under control of the programs implements:
• at least one neural network trained to produce first feature vectors from facial features extracted from a population of first facial images and configured to produce a second feature vector from facial features extracted from a second facial image;
• the at least one neural network configured to generate augmented first feature vectors with semantic variables corresponding to elements separate from facial characteristics;
• and
• a discriminative classifier trained to identify closely matching ones of the first feature vectors and configured to identify whether at least one augmented first feature vector and the second feature vector meet a correlation threshold indicating a presence of the separate elements in the second feature vector;
• a data collection station including:
• a camera for acquiring one or more of the first facial images of the population of first facial images;
• a face detector for detecting a face in the one or more first facial images;
• and
• a feature extractor for producing the facial features extracted from the one or more first facial images;
• and
• an access control station including:
• a camera for acquiring the second facial image;
• a face detector for detecting a face in the second facial image;
• a feature extractor for producing the facial features extracted from the second facial image;
• and
• an access interface, controlled by the access control station for providing access to equipment.