Image processing apparatus, image processing method, and non-transitory computer-readable storage medium
AssigneeCanon Kabushiki Kaisha
InventorsDaisuke Furukawa, Fukashi Yamazaki, Keita Nakagomi
Life of this patent
Estimating the term…
Abstract
An image processing apparatus includes a first extraction unit configured to extract a first target region from an image using a trained classifier, a setting unit configured to set region information to be used in a graph cut segmentation method based on a first extraction result including the first target region, a second extraction unit configured to extract a second target region using the graph cut segmentation method based on the set region information, and a generation unit configured to generate a ground truth image corresponding to the image based on a second extraction result including the second target region.
Claims25
An image processing apparatus comprising:
- a first extraction unit configured to input a medical image to a trained classifier so as to extract a target region, wherein the trained classifier is configured to output information indicating whether or not a pixel of an input medical image belongs to the target region;
- a setting unit configured to set region information including seed information to be used in a graph cut segmentation method using a first extraction result including the target region;
- a second extraction unit configured to extract the target region using the graph cut segmentation method based on the region information;
- and
- a generation unit configured to generate a ground truth image corresponding to the medical image based on a second extraction result including the target region,
- wherein a pixel constituting the ground truth image has a value indicating whether or not the pixel belongs to the target region as a pixel value.
An image processing method comprising:
- inputting a medical image to a trained classifier to extract a target region, wherein the trained classifier outputs information indicating whether or not a pixel of an input medical image belongs to the target region;
- setting region information including seed information to be used in a graph cut segmentation method, using a first extraction result including the target region;
- extracting the target region using the graph cut segmentation method based on the region information;
- and
- generating a ground truth image corresponding to the medical image, based on a second extraction result including the target region,
- wherein a pixel constituting the ground truth image has a value indicating whether or not the pixel belongs to the target region as a pixel value.
A non-transitory computer-readable storage medium storing a program for causing a computer to execute a process comprising:
- inputting a medical image to a trained classifier to extract a target region, wherein the trained classifier outputs information indicating whether or not a pixel of an input medical image belongs to the target region;
- setting region information including seed information to be used in a graph cut segmentation method, using a first extraction result including the target region;
- extracting the target region using the graph cut segmentation method based on the region information;
- and
- generating a ground truth image corresponding to the medical image, based on a second extraction result including the target region,
- wherein a pixel constituting the ground truth image has a value indicating whether or not the pixel belongs to the target region as a pixel value.
Dependencies are inferred from the claim text.