| CPC G06T 7/11 (2017.01) [G06N 3/045 (2023.01); G06N 20/00 (2019.01); G06T 7/0012 (2013.01); G06T 17/205 (2013.01); G06T 19/20 (2013.01); G16H 30/20 (2018.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30036 (2013.01); G06T 2210/41 (2013.01); G06T 2219/2012 (2013.01)] | 28 Claims |

|
1. A method comprising:
generating a plurality of two-dimensional (2D) images from a first three-dimensional (3D) model of a subject's dentition;
adjusting one or more image attributes of the plurality of 2D image to produce one or more modified 2D images;
projecting each of the modified 2D images onto the first 3D model to form a segmented 3D model, wherein conflicts between segmentation boundaries when projecting the modified 2D images onto the first 3D model are resolved statistically on a per-location basis; and
outputting the segmented 3D model.
|