Neural network based facial analysis using facial landmarks and associated confidence values

A system comprising:

• one or more processors to perform operations including:
• generating, using one or more machine learning models (MLMs) and based at least on image data corresponding to one or more portions of an image, one or more predictions corresponding to confidence levels that indicate degrees of visibility of landmark points of a subject as depicted in the image;
• selecting, using the confidence levels, a first subset of the landmark points based at least on the degrees of visibility indicating that the first subset corresponds to a higher degree of visibility in the image than a second subset of the landmark points;
• based at least on the selecting, computing one or more properties of the subject based at least on analyzing the first subset of the landmark points, the one or more properties corresponding to a subset of the image that depicts the first subset based at least on the selecting of the first subset;
• and
• initiating one or more operations of a machine based at least on the one or more properties of the subject.

One or more hardware processors comprising:

• one or more circuits to initiate one or more operations of a machine based at least on one or more properties of a subject depicted in an image, the one or more properties being computed based at least on:
• one or more values determined using one or more machine learning models (MLMs) and based at least on image data corresponding to one or more portions of the image, the one or more values corresponding to landmark points of the subject depicted in the image, and corresponding to confidence levels that indicate degrees of visibility of the landmark points as depicted in the image;
• and
• an analysis of a subset of the landmark points, the subset selected using the one or more values and based at least on the degrees of visibility indicated by the confidence levels.