Methods and apparatuses for half-face detection

A volatile or non-volatile computer-readable storage medium storing instructions which, when executed by one or more processors, cause the processors to perform steps comprising:

• determining a left-face probability based at least in part on an application of one or more left-face classifiers to an image;
• determining a right-face probability based at least in part on an application of one or more right-face classifiers to the image;
• selecting a particular characterization of the image, from a plurality of supported characterizations of the image, based at least in part on both the left-face probability and the right-face probability, wherein the plurality of supported characterizations include at least:
• (a) the image contains a left face without a visible right face, and
• (b) the image contains a right face without a visible left face.

A digital camera comprising:

• an image capturing and storing module;
• a left-face classifier module that determines a left-face probability based at least in part on an application of one or more left-face classifiers to an image;
• a right-face classifier module that determines a right-face probability based at least in part on an application of one or more right-face classifiers to the image;
• and
• an image labeling module that selects a particular characterization of the image, from a plurality of supported characterizations of the image, based at least in part on both the left-face probability and the right-face probability, wherein the plurality of supported characterizations include at least:
• (a) the image contains a left face without a visible right face, and
• (b) the image contains a right face without a visible left face.

A method comprising steps of:

• determining a left-face probability based at least in part on an application of a particular left-face classifier of a plurality of left-face classifiers to an image,
• wherein each left-face classifier of the plurality of left-face classifiers includes a left-face classifier threshold,
• wherein the particular left-face classifier includes a first left-face classifier threshold that is different than a second left-face classifier threshold;
• determining whether the left-face probability is equal to or greater than the first left-face classifier threshold;
• determining a right-face probability based at least in part on an application of a particular right-face classifier of a plurality of right-face classifiers to the image,
• wherein each right-face classifier of the plurality of right-face classifiers includes a right-face classifier threshold,
• wherein the particular right-face classifier includes a first right-face classifier threshold that is different than a second right-face classifier threshold;
• determining whether the right-face probability is equal to or greater than the first right-face classifier threshold;
• based at least in part whether the left-face probability is equal to or greater than the first left-face classifier threshold and whether the right-face probability is equal to or greater than the first right-face classifier threshold, determining which one of the following is true relative to the image:
• (a) the image contains a full face,
• (b) the image contains a left face without a right face,
• (c) the image contains a right face without a left face, or
• (d) the image does not contain a face;
• wherein the steps are performed by an automated device.