US 12,469,254 B2
Interpupillary distance estimation method
Cristian Cascetta, Milan (IT); Fabio Mazzarella, Busto Arsizio (IT); and Luca Mazzocchi, Legnano (IT)
Assigned to LUXOTTICA GROUP S.P.A., Milan (IT)
Filed by LUXOTTICA GROUP S.P.A., Milan (IT)
Filed on Dec. 19, 2022, as Appl. No. 18/083,692.
Claims priority of application No. 102021000032711 (IT), filed on Dec. 27, 2021.
Prior Publication US 2023/0206598 A1, Jun. 29, 2023
Int. Cl. G06V 10/74 (2022.01); G06T 7/62 (2017.01); G06V 40/18 (2022.01)
CPC G06V 10/761 (2022.01) [G06T 7/62 (2017.01); G06V 40/193 (2022.01); G06T 2207/20024 (2013.01); G06T 2207/30201 (2013.01); G06T 2207/30204 (2013.01); G06V 2201/07 (2022.01)] 9 Claims
OG exemplary drawing
 
1. Interpupillary distance estimation method implementable by an electronic computer provided with a memory for storing data, said interpupillary distance estimation method comprising the steps of:
acquiring a plurality of two-dimensional (2D) images of a user's face;
locating on the at least one 2D image acquired two reference points corresponding to the pupils of the user;
measuring the distance in pixels between the two reference points corresponding to the user's pupils (IPDp);
measuring the diameter in pixels of the user's iris (DIp);
calculating the pixel-to-millimetre conversion ratio between a predetermined iris diameter expressed in metric units and the iris diameter measured in pixels, said predetermined iris diameter being set equal to the value of the iris diameter most widespread in the world population according to data contained in an anthropometric database;
determining a first estimation of the interpupillary distance expressed in metric units (IPD) by multiplying the distance in pixels between the two reference points corresponding to the user's pupils (IPDp) by the pixel-to-millimetre ratio calculated previously,
wherein said interpupillary distance estimation method comprises the step of:
calculating an average value of the first estimations; and
before calculating the average value of the first estimations, performing a filtering step wherein for each 2D image acquired, the 2D image is evaluated as reliable or unreliable and the 2D image is discarded from the step of calculating the average value when it is evaluated as unreliable,
wherein the filtering step comprising for each 2D image acquired the steps of:
locating on the 2D image a plurality of marker points corresponding to specific features of the user's face comprising at least the eyelids;
determining a ratio representative of the degree of eyelid opening, where such ratio is called eye aspect ratio;
comparing the eye aspect ratio with a predefined image acceptability threshold value;
when the eye aspect ratio is greater than the image acceptability threshold value, considering the 2D image as acceptable;
when the eye aspect ratio is lower than the image acceptability threshold value, considering the 2D image as unacceptable.