Method and apparatus for determining interpupillary distance (IPD)

Patent metadata

Field	Value
Publication number	US-10979696-B2
Application number	US-201916684736-A
Country	US
Kind code	B2
Filing date	Nov 15, 2019
Priority date	Nov 29, 2016
Publication date	Apr 13, 2021
Grant date	Apr 13, 2021

Abstract

A method and apparatus for determining an interpupillary distance (IPD) are provided. To determine an IPD of a user, three-dimensional (3D) images for candidate IPDs may be generated, and user feedback on the 3D images may be received. A final IPD may be determined based on the user feedback.

First claim

What is claimed is:

1. A method for determining an interpupillary distance (IPD), the method comprising:
detecting eye coordinates of eyes of a user in a user image;
acquiring a normal vector of a line connecting pupils of the eyes, from the user image;
generating test three-dimensional (3D) images respectively for candidate IPDs, based on the candidate IPDs, the detected eye coordinates and the acquired normal vector;
merging the generated test 3D images into a single composite test image;
outputting the single composite test image into which the test 3D images are merged;
receiving, from the user, a selection of an image among the test 3D images merged into the output single composite test image; and
obtaining a final IPD of the user, based on one of the candidate IPDs corresponding to the selected image.

2. The method of claim 1 , wherein the candidate IPDs are obtained based on a standard IPD and a scale value.

3. The method of claim 1 , wherein the generating the test 3D images comprises:
obtaining 3D positions of the eyes for each of the candidate IPDs, based on the candidate IPDs, the detected eye coordinates and the acquired normal vector; and
generating the test 3D images respectively for the obtained 3D positions of the eyes for each of the candidate IPDs.

4. The method of claim 1 , wherein the generating the test 3D images comprises:
generating a first two-dimensional (2D) image for one from among a left eye and a right eye, the first 2D image comprising pixels, wherein each of the pixels has a random intensity value;
generating a second 2D image having a pattern that is complementary to a pattern of the generated first 2D image; and
generating one of the test 3D images, based on the generated first 2D image and the generated second 2D image.

5. The method of claim 1 , wherein the obtaining the final IPD comprises:
identifying whether a number of times feedback is received from the user exceeds a preset number;
based on the number of times feedback is received being identified to not exceed the preset number, updating the candidate IPDs, based on the one of the candidate IPDs corresponding to the selected image; and
based on the number of times feedback is received being identified to exceed the preset number, obtaining the final IPD, based on the one of the candidate IPDs corresponding to the selected image, and
wherein the generating the test 3D images comprises generating the test 3D images respectively for the updated candidate IPDs, based on the updated candidate IPDs, the detected eye coordinates and the acquired normal vector.

6. The method of claim 5 , wherein the updating the candidate IPDs comprises:
adjusting either one or both of a standard IPD and a scale value, based on the one of the candidate IPDs corresponding to the selected image; and
updating the candidate IPDs, based on either one or both the adjusted standard IPD and the adjusted scale value.

7. The method of claim 6 , wherein the adjusting either one or both of the standard IPD and the scale value comprises:
obtaining an average value of one or more of the candidate IPDs corresponding to one or more of the test 3D images that are selected by the user, from the output single composite test image; and
adjusting the standard IPD, based on the obtained average value.

8. The method of claim 6 , wherein the adjusting either one or both of the standard IPD and the scale value comprises:
obtaining a weight of each of one or more the candidate IPDs corresponding to one or more of the test 3D images that are selected by the user, from the output single composite test image, based on an order in which the one or more of the test 3D images are selected; and
adjusting the standard IPD, based on the obtained weight each of the one or more the candidate IPDs and the one or more of the candidate IPDs.

9. The method of claim 1 , wherein the selected image is a relatively bright image among the test 3D images merged into the output single composite test image.

10. The method of claim 1 , further comprising:
determining the user, based on the user image;
identifying whether the determined user is associated with an associated IPD;
based on the determined user being identified to be associated with the associated IPD, obtaining the associated IPD as the final IPD,
wherein the obtaining the final IPD comprises, based on the determined user being identified to not be associated with the associated IPD, obtaining the final IPD, based on the one of the candidate IPDs corresponding to the selected image; and
associating the obtained final IPD with the determined user.

11. A non-transitory computer-readable storage medium storing a program for causing a processor to perform the method of claim 1 .

12. An apparatus for determining an interpupillary distance (IPD), the apparatus comprising:
a memory configured to store a program; and
a processor configured to execute the program to at least:
detect eye coordinates of eyes of a user in a user image;
acquire a normal vector of a line connecting pupils of the eyes, from the user image;
generate test three-dimensional (3D) image images respectively for candidate IPDs, based on the candidate IPDs, the detected eye coordinates and the acquired normal vector;
merge the generated test 3D images into a single composite test image;
control to output the single composite image into which the test 3D images are merged;
receive, from the user, a selection of an image among the test 3D images merged into the output single composite test image; and
obtain a final IPD of the user, based on one of the candidate IPDs corresponding to the selected image.

13. The apparatus of claim 12 , further comprising a camera configured to generate the user image.

14. The apparatus of claim 12 , further comprising a display configured to output the single composite image into which the test 3D images are merged.

15. The apparatus of claim 12 , wherein the selected image is a relatively bright image among the test 3D images merged into the output single composite test image.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Hwang Hyoseok
• Kang Dongwoo
• Kang Byong Min
• Park Juyong
• Nam Dong Kyung

Classifications

• G06V40/193

  Preprocessing; Feature extraction · CPC title

• G06V40/19

  Sensors therefor · CPC title

• A61B3/14

  Arrangements specially adapted for eye photography · CPC title

• A61B3/111 Primary

  for measuring interpupillary distance · CPC title

• A61B3/0025 Primary

  characterised by electronic signal processing, e.g. eye models · CPC title