System and method for determining compactness in images
AssigneeSiemens Medical Solutions USA, Inc.
InventorMatthias Wolf
Life of this patent
Estimating the term…
Abstract
An image processing system for recognizing image features in three dimensional images, which can be medical images, uses a mask generator for generating masks that are used by a candidate searcher to search for candidate images in the three dimensional image. The candidate searcher applies the mask to a section of a foreground region of the image to determine the presence of a structure/object by counting the number of intersections between the mask and the section of the foreground region.
Claims15
An image processing system for recognizing objects in three dimensional images, the system comprising:
- a mask generator for generating at least one mask, wherein the mask comprises a three dimensional image including a plurality of voxels and having a plurality of faces, wherein at least one of the voxels has a masking value;
- and
- a candidate searcher for searching at least one candidate object similar to at least one predetermined object in at least one three dimensional image, the candidate searcher applying the mask to a predetermined region of a foreground image section of the three dimensional image by overlaying the mask on the predetermined region to determine an intersection count between the mask voxels and the predetermined region to search for the candidates.
An image processing system for recognizing presence of medical objects, the system comprising:
- an image capture device for capturing a three dimensional image of a part of a living organism;
- a image processing system for segmenting the three dimensional image into a foreground image and a background image,
- the image processing system including a mask generator for generating at least one mask having a three dimensional image including a plurality of voxels and having a plurality of faces, wherein at least one of the voxels has a masking value;
- the image processing system applying at least one mask on a selected region of the foreground image by overlaying the mask on the selected region to determine the presence of at least one of the medical objects by counting the intersections between the mask voxels and the selected region.
A method of detecting objects in a three dimensional image, the method comprising the steps of:
- capturing the three dimensional image using an image capture device;
- segmenting the three dimensional image into a foreground region and a background region;
- generating at least one three dimensional mask;
- and
- searching for candidates in the foreground region of the three dimensional image by overlaying the three dimensional mask over a predetermined part of the foreground region of the three dimensional image;
- counting the number of intersections between the mask and the predetermined part of the foreground region;
- and
- determining the presence of the object that is searched if the intersections are less than two.
A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for searching candidates from a set of objects, the method steps comprising:
- generating at least one mask having a three dimensional image including a plurality of voxels and a plurality of faces, wherein at least one of the voxels has a masking value;
- and searching for candidates similar to a predetermined object in the set of objects in a three dimensional image by overlaying the mask on a predetermined region of the three dimensional image to determine an intersection count between the mask voxels and the predetermined region.
Dependencies are inferred from the claim text.