Back to results
US 2022/0020155 A1Published application
Image segmentation method using neural network based on mumford-shah function and apparatus therefor
AssigneeKorea Advanced Institute of Science and Technology
InventorsJongChul Ye, Boah Kim
Life of this patent
Estimating the term…
Abstract
Disclosed is an image segmentation method including receiving an image to be segmented and segmenting the received image by using a neural network learned through a Mumford-Shah function-based loss function.
Claims17
An image segmentation method, the method comprising:
- receiving an image to be segmented;
- and
- segmenting the received image by using a neural network learned through a Mumford-Shah function-based loss function.
An image segmentation method, the method comprising:
- defining a Mumford-Shah function-based loss function;
- learning a neural network by using the defined Mumford-Shah function-based loss function;
- receiving an image to be segmented;
- and
- segmenting the received image by using the neural network learned through the Mumford-Shah function-based loss function.
2 more elements
An image segmentation apparatus, the apparatus comprising:
- a receiving unit configured to receive an image to be segmented;
- and
- a segmenting unit configured to segment the received image by using a neural network learned through a Mumford-Shah function-based loss function.
Dependencies are inferred from the claim text.