Granted Patent B2

US 7,564,999 · App. 11/188,422 · Granted Jul 21, 2009

Abstract

Claims (27)

1. A method for automatically recognizing a marker generated at the same time a radiographic image is generated and having semantic meaning specifying associated image information in the radiographic image, comprising using a computer to perform the following steps comprising the steps of:

accessing the radiographic image in digital form;

segmenting the digital image into a plurality of regions;

detecting a marker region from the plurality of regions; and

recognizing the marker generated at the same time a radiographic image is generated and having semantic meaning specifying associated image information disposed within the marker region to determine the marker's semantic meaning.

2. The method of claim 1 , further comprising the step of associating the marker's semantic meaning with the radiographic image.

3. The method of claim 2 , wherein the step of associating is accomplished by storing the semantic meaning in a DICOM format.

4. The method of claim 1 , wherein the step of detecting the marker region is accomplished by the steps of:

labeling each of the plurality of regions; and

identifying the marker region by locating the marker within one of the plurality of labeled regions.

5. The method of claim 1 , wherein the step of recognizing the marker is accomplished using optical character recognition or a marker image match.

6. The method of claim 5 , wherein the step of recognizing the marker using the marker image match is accomplished by the steps of:

extracting the marker region from the digital image;

transforming the marker region into a standard position;

aligning the marker region with a target marker;

computing a similarity measure between the marker region and the target marker;

repeating the steps of aligning and computing with other target markers; and

determining which one of the target markers computes the highest similarity measure.

7. The method of claim 6 , wherein the step of computing the similarity measure is accomplished by calculating a correlation coefficient or a confidence level from a neural network or fuzzy inference engine.

8. The method of claim 6 , wherein a database is provided to manage the plurality of target markers and the method further comprises the steps of:

transforming and storing the plurality of target markers in digital form to generate associated information;

maintaining the associated information in the database;

outputting the associated information needed for image storage and management.

9. The method of claim 1 , further comprising the step of using the semantic meaning of the marker to display the image.

10. The method of claim 1 , further comprising the step of using the semantic meaning to arrange the radiographic image relative to other radiographic images.

11. The method of claim 1 , further comprising the step of using the semantic meaning to render the radiographic image.

12. A computer readable storage medium having computer instructions stored therein causing one or more computers to perform the method of claim 1 .

Assignments (13)