Methods, systems, and media for automatically classifying face images

A system for automatically classifying a face image, comprising:

• at least one processor that:
• selects at least two features of the face image to be classified for an attribute of face images of different faces, wherein each of the two features corresponds to a different region of the face image and specifies at least one of a type of pixel data to be evaluated for the region, a normalization to be applied for the region, and an aggregation to be applied for the region;
• classifies the face image with respect to the attribute based on the at least two features of the image;
• assigns the attribute and a confidence value to the face image based on the classifying;
• receives a query from a user;
• identifies the attribute as corresponding to the query;
• determines that the face image corresponds to the attribute;
• and
• identifies to the user the face image as corresponding to the query.

A non-transitory computer-readable medium containing computer-executable instructions that, when executed by a processor, cause the processor to perform a method for automatically classifying a face image, the method comprising:

• selecting at least two features of the face image to be classified for an attribute of face images of different faces, wherein each of the two features corresponds to a different region of the face image and specifies at least one of a type of pixel data to be evaluated for the region, a normalization to be applied for the region, and an aggregation to be applied for the region;
• classifying the face image with respect to the attribute based on the at least two features of the image;
• assigning the attribute and a confidence value to the face image based on the classifying;
• receiving a query from a user;
• identifying the attribute as corresponding to the query;
• determining that the face image corresponds to the attribute;
• and
• identifying to the user the face image as corresponding to the query.