Back to results
US 2022/0012890 A1Published application
Model-Based Deep Learning for Globally Optimal Surface Segmentation
AssigneeUniversity of Iowa Research Foundation
InventorsXiaodong Wu, Leixin Zhou, John M Buatti, Hui Xie
Life of this patent
Estimating the term…
Abstract
An automated method for segmentation includes steps of receiving at a computing device an input image representing at least one surface and performing by the computing device image segmentation on the input image based on a graph surface segmentation model with deep learning. The deep learning may be used to parameterize the graph surface segmentation model.
Claims18
An automated method for segmentation, the method comprising:
- receiving at a computing device an input image representing at least one surface;
- performing by the computing device image segmentation on the input image based on a graph surface segmentation model with deep learning.
An automated method for segmentation, the method comprising:
- receiving at a computing device an input image representing at least one surface;
- performing by the computing device image segmentation on the input image based on a graph surface segmentation model with deep learning, wherein the image segmentation is globally optimal.
Dependencies are inferred from the claim text.