Face recognition in a residential environment

A electronic device, comprising:

• one or more processors;
• and
• memory for storing instructions, the instructions, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
• capturing a set of one or more images of an individual's head and face while the individual is present in a residential environment, wherein the residential environment comprises a plurality of home devices, at least one of the one or more images captured by one or more of the plurality of home devices;
• inputting the one or more images to a machine learning model that has been trained to identify the individual as one of different residents from a group of known residents of the residential environment;
• identifying the individual as one of the different residents using the machine learning model, wherein identifying the individual comprises calculating a similarity between the one or more images and reference images of heads and faces of the different residents, and wherein calculating the similarity comprises:
• calculating distance metrics between the one or more images and the reference images, and
• calculating a weighted combination based on the distance metrics;
• and
• in response to identifying the individual as one of the different residents, generating an operating instruction for one of the home devices based on a preference of the identified resident, said one of the home devices configured to operate according to the operating instruction.

A non-transitory computer-readable storage medium storing instructions, the instructions, when executed by one or more processors of an electronic device, cause the one or more processors to perform operations comprising:

• capturing one or more images of an individual's head and face while the individual is present in a residential environment, the residential environment comprising a plurality of home devices;
• inputting the one or more images to a machine learning model that has been trained to identify the individual from among a group of different persons associated with the residential environment;
• identifying the individual using the machine learning model, wherein the machine learning model outputs an identity of the individual by calculating a similarity between the one or more images and reference images of heads and faces of the different persons, and wherein calculating the similarity comprises:
• calculating distance metrics between the one or more images and the reference images, and
• calculating a weighted combination based on the distance metrics;
• and
• generating an operating instruction for one of the home devices based on the identity of the individual output by the machine learning model.

A non-transitory computer-readable storage medium storing instructions, the instructions, when executed by one or more processors of an electronic device, cause the one or more processors to perform operations comprising:

• capturing one or more images of an individual's head and face while the individual is present in a residential environment, wherein the residential environment comprises a plurality of home devices, at least one of the one or more images captured by one or more of the plurality of home devices;
• inputting the one or more images to a machine learning model that has been trained to identify the individual as one of different residents from a group of known residents of the residential environment;
• identifying the individual as one of the different residents using the machine learning model, wherein identifying the individual comprises calculating a similarity between the one or more images and reference images of heads and faces of the different residents and calculating the similarity comprises:
• calculating distance metrics between the one or more images and the reference images, and
• calculating a weighted combination based on the distance metrics;
• and
• in response to identifying the individual as one of the different residents, generating an operating instruction for one of the home devices based on a preference of the identified resident, said one of the home devices configured to operate according to the operating instruction.