Facial feature detection

A computer-readable storage device storing instructions for causing at least one processor of a computing device to perform operations comprising:

• storing a plurality of removable facial feature templates and a plurality of non-removable facial feature templates;
• weighting each of the plurality of removable facial feature templates and the plurality of non-removable facial feature templates so that facial feature templates that are erroneously classified by a given classifier are more likely to be selected for further training than facial feature templates that were correctly classified;
• capturing, by a camera of the computing device, an image including at least a face of a user;
• calculating a face template of the face of the user in the image;
• determining, by the computing device, whether the face template includes a removable facial feature that decreases a level of distinctiveness between two faces based at least in part on a weighted sum of similarity scores between the face template and the each of the plurality of removable facial feature templates;
• determining, by the computing device, whether the face template includes a non-removable facial feature that decreases a level of distinctiveness between two faces based at least in part on a weighted sum of similarity scores between the face template and the each of the plurality of non-removable facial feature templates;
• responsive to determining that the face includes the removable facial feature, outputting, by a graphical user interface of the computing device, a notification for the user to remove the removable facial feature;
• and
• responsive to determining that the face includes the non-removable facial feature, adjusting a first similarity score threshold to a second similarity score threshold.

A computing device comprising:

• a memory configured to store a plurality of removable facial feature templates and a plurality of non-removable facial feature templates;
• at least one processor;
• at least one camera operable by the at least one processor to capture a first image including at least a first face of a user;
• and
• at least one output device operable by the processor,
• wherein the at least one processor is configured to weight each of the plurality of removable facial feature templates and the plurality of non-removable facial feature templates so that facial feature templates that are erroneously classified by a given classifier are more likely to be selected for further training than facial feature templates that were correctly classified, calculate a face template of the face of the user in the image, determine whether the face template includes a removable facial feature that decreases a level of distinctiveness between two faces based at least in part on a weighted sum of similarity scores between the face template and the each of the plurality of removable facial feature templates, and determine whether the face template includes a non-removable facial feature that decreases a level of distinctiveness between two faces based at least in part on a weighted sum of similarity scores between the face template and the each of the plurality of non-removable facial feature templates,
• wherein the at least one output device is configured to, responsive to the at least one processor determining that the face includes the removable facial feature, output a notification for the user to remove the removable facial feature, and wherein responsive to determining that the face includes the non-removable facial feature, the processor adjusts a first similarity score threshold to a second similarity score threshold.

A method, comprising:

• storing a plurality of non-removable facial feature templates;
• weighting each of the plurality of non-removable facial feature templates so that non-removable facial feature templates that are erroneously classified by a given classifier are more likely to be selected for further training than non-removable facial feature templates that were correctly classified;
• capturing, by a computing device, an image including at least a face of a user;
• calculating, by the computing device, a face template of the face of the user in the image;
• comparing, by the computing device, the face template to each of the plurality of non-removable facial feature templates;
• determining, by the computing device, whether the face template includes a non-removable facial feature that decreases a level of distinctiveness between two faces based at least in part on a weighted sum of similarity scores between the face template and the each of the plurality of non-removable facial feature templates;
• and
• responsive to determining that the face includes the non-removable facial feature, adjusting, by the computing device, a first similarity score threshold to a second similarity score threshold.