Landmark localization via visual search

A system comprising:

• a processor for executing instructions stored in computer-readable medium on one or more devices,
• the instructions comprising one or more modules configured to perform the steps comprising:
• receiving a test image having a face and a plurality of object images, each one of the object images depicting a face detected to be similar to the face depicted in the test image;
• identifying a plurality of landmark indicators associated with each one of the object images, each landmark indicator indicating a location of a landmark in the object depicted in the object image;
• and
• computing a test image landmark location of each test image landmark that corresponds to one of the landmark indicators based at least in part on generating a plurality of similarity voting maps between the test image and each one of the object images.

A method comprising:

• identifying feature matches between each of a plurality of object image and a test image, each of the feature matches between a feature of a respective object image and a matching feature of the test image, wherein there is a spatial relationship between each respective object image feature and a first landmark of the object image, the first landmark at a known location in the object image;
• estimating a plurality of locations for a second landmark for the test image, the estimated locations based at least in part on the feature matches and the spatial relationships;
• and
• estimating a final location for the second landmark from the plurality of locations for the second landmark for the test image,
• wherein identifying the feature matches, estimating the plurality of locations, and estimating the final location are performed by a processor of a computing device executing instructions.