US 12,243,352 B2
Methods and systems for adaptive binarization thresholding for pupil segmentation
Calvin John Rubens, Ottawa (CA); and Sean Braley, Orillia (CA)
Assigned to HUAWEI TECHNOLOGIES CO., LTD., Shenzhen (CN)
Filed by Calvin John Rubens, Ottawa (CA); and Sean Braley, Orillia (CA)
Filed on Nov. 1, 2022, as Appl. No. 17/978,717.
Prior Publication US 2024/0144722 A1, May 2, 2024
Int. Cl. G06V 40/18 (2022.01); G06T 5/20 (2006.01); G06T 5/40 (2006.01); G06T 7/13 (2017.01); G06V 10/25 (2022.01); G06V 10/28 (2022.01); G06V 10/46 (2022.01)
CPC G06V 40/193 (2022.01) [G06T 5/20 (2013.01); G06T 5/40 (2013.01); G06T 7/13 (2017.01); G06V 10/25 (2022.01); G06V 10/28 (2022.01); G06V 10/46 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining an eye image captured by a camera;
computing an eye image histogram that represents a frequency distribution of a plurality of pixel values within the eye image, each bar in the eye image histogram corresponding to a respective pixel count;
identifying a pupil region in the eye image histogram;
identifying an iris region in the eye image histogram; and
determining a pupil binarization threshold based on a second derivative function of the eye image histogram, the identified pupil region in the eye image histogram and the identified iris region in the eye image histogram.