Fitting glasses frames to a user

1. A system for fitting glasses frames to a user, comprising:

a processor configured to:

compare user head measurements determined from a set of images with at least some of a plurality of sets of glasses frame measurements to generate fit scores corresponding to respective ones of at least a subset of the plurality of sets of glasses frame measurements, wherein the set of images corresponds to a user's head at one or more orientations, wherein to generate a fit score comprises to:

compare a first feature distance to a corresponding first user head measurement to obtain a first penalty;

compare a second feature distance to a corresponding second user head measurement to obtain a second penalty;

determine a penalty value based on the first penalty weighed by a first weight and the second penalty weighed by a second weight, the first weight being different from the second weight; and

generate the fit score based on the penalty value;

select a glasses frames corresponding to a set of glasses frame measurements from the plurality of sets of glasses frame measurements based at least in part on the fit scores; and

display information associated with the selected glasses frames; and

a memory coupled to the processor and configured to provide the processor with instructions.

2. The system of claim 1 , wherein an image of the set of images comprises an image selected from at least two recorded images corresponding to the user's head at one orientation of the one or more orientations.

3. The system of claim 1 , wherein the processor is further configured to generate a 3D model of the user's head based at least in part on the set of images.

4. The system of claim 3 , wherein generating the 3D model of the user's head comprises determining a set of reference points associated with the user's head based at least in part on the set of images.

5. The system of claim 4 , wherein generating the 3D model of the user's head further comprises adjusting an initial 3D model based at least in part on the set of reference points associated with the user's head.

6. The system of claim 5 , wherein the initial 3D model is determined based at least on references points corresponding to a set of users.

7. The system of claim 3 , wherein the user head measurements are determined based at least in part from the 3D model of the user's head.

8. The system of claim 1 , wherein a first image of the set of images comprises an image of a scaling reference object of a predetermined size configured to be used to scale a second image of the set of images.

9. The system of claim 1 , wherein selecting the glasses frames comprises comparing the fit score corresponding to the glasses frames with a threshold associated with a quality of fit.

10. The system of claim 1 , wherein displaying information associated with the selected glasses frames comprises rendering the selected glasses frames over an image of the set of images.

11. The system of claim 1 , wherein the one or more orientations are determined by comparing the set of images of the user's head to models of each orientation and categorizing each image as one of the one or more orientations.

12. A method for fitting glasses frames to a user, comprising:

comparing, using a processor, user head measurements determined from a set of images with at least some of a plurality of sets of glasses frame measurements to generate fit scores corresponding to respective ones of at least a subset of the plurality of sets of glasses frame measurements, wherein the set of images corresponds to a user's head at one or more orientations, wherein the generating of a fit score comprises:

comparing a first feature distance to a corresponding first user head measurement to obtain a first penalty;

comparing a second feature distance to a corresponding second user head measurement to obtain a second penalty;

determining a penalty value based on the first penalty weighed by a first weight and the second penalty weighed by a second weight, the first weight being different from the second weight; and

generating the fit score based on the penalty value;

selecting a glasses frames corresponding to a set of glasses frame measurements from the plurality of sets of glasses frame measurements based at least in part on the fit scores; and

displaying information associated with the selected glasses frames.

13. The method of claim 12 , wherein an image of the set of images comprises an image selected from at least two recorded images corresponding to the user's head at one orientation of the one or more orientations.

14. The method of claim 12 , further comprising generating a 3D model of the user's head based at least in part on the set of images.

15. The method of claim 14 , wherein generating the 3D model of the user's head comprises determining a set of reference points associated with the user's head based at least in part on the set of images.

16. The method of claim 15 , wherein generating the 3D model of the user's head further comprises adjusting an initial 3D model based at least in part on the set of reference points associated with the user's head.

17. The method of claim 16 , wherein the initial 3D model is determined based at least on references points corresponding to a set of users.

18. The method of claim 12 , wherein displaying information associated with the selected glasses frames comprises rendering the selected glasses frames over an image of the set of images.

19. A computer program product for fitting glasses frames to a user, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

comparing user head measurements determined from a set of images with at least some of a plurality of sets of glasses frame measurements to generate fit scores corresponding to respective ones of at least a subset of the plurality of sets of glasses frame measurements, wherein the set of images corresponds to a user's head at one or more orientations, wherein the generating of a fit score comprises:

comparing a first feature distance to a corresponding first user head measurement to obtain a first penalty;

comparing a second feature distance to a corresponding second user head measurement to obtain a second penalty;

determining a penalty value based on the first penalty weighed by a first weight and the second penalty weighed by a second weight, the first weight being different from the second weight; and

generating the fit score based on the penalty value;

selecting a glasses frames corresponding to a set of glasses frame measurements from the plurality of sets of glasses frame measurements based at least in part on the fit scores; and

displaying information associated with the selected glasses frames.

20. The system of claim 1 , wherein:

the obtaining of the first penalty is based on a first penalty function; and

the obtaining of the second penalty is based on a second penalty function.