Method for processing data structures

• US 7,574,053 B2
• Filed: 01/10/2007
• Issued: 08/11/2009
• Est. Priority Date: 12/14/1999
• Status: Expired due to Term

• Current Assignee: Definiens AG (Astrazeneca PLC)
• Original Assignee: Definiens AG (Astrazeneca PLC)
• Inventors: Baatz, Martin, Schäpe, Arno, Schmidt, Günter
• Primary Examiner(s): Chen; Wenpeng
• Application Number:
  US11/652,427
• Publication Number:
  US 20070112823A1
• Time in Patent Office: 944 Days
• Field of Search: 382/224
• US Class Current: 382/224
• CPC Class Codes: G06T 2207/10032 Satellite or aerial image; Remote sensing
• CPC Class Codes: G06T 2207/30181 Earth observation
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/174 involving the use of two or more images
• CPC Class Codes: G06V 10/422 for representing the structure of the pattern or shape of an object therefor
• CPC Class Codes: G06V 20/13 Satellite images
• CPC Class Codes: Y10S 707/99931 Database or file accessing

Abstract

A method for processing data structures with the aid of networked semantic units includes: acquiring a data structure, and generating, modifying, deleting and storing semantic structure units and networking them on the basis of the acquired data structure while using a knowledge base comprised of a network of semantic knowledge units. Semantic structure units and their network are classified in iterative steps. Based on this classification, a specific processing is activated which modifies a respective semantic structure unit and a particular partial network.

Claims

1. A system for generating an application that analyzes image information, comprising:

a computer readable storage medium; and

a computer program stored on the storage medium comprising;

a set of algorithms, wherein each algorithm of the set of algorithms represents an operation performable by the application;

a plurality of neighborhood descriptions, wherein each of the plurality of neighborhood descriptions represents a subset of a data object network, and wherein the data object network is generated by segmenting the image information; and

a graphical user interface that is used to generate a processing object network, wherein the processing object network includes a parent process and a plurality of child processes, wherein the parent process comprises one of the plurality of neighborhood descriptions and one algorithm of the set of algorithms, and wherein the algorithm performs the operation on the subset of the data object network represented by the neighborhood description.

2. The system of claim 1, wherein a digital image comprises the image information, and wherein the computer program displays on the graphical user interface the data object network as an overlay over the digital image.

3. The system of claim 1, wherein the parent process and the plurality of child processes are linked with each other to form an execution control for the application.

4. The system of claim 1, wherein the plurality of child processes are linked with each other, and wherein the application executes one of the plurality of child processes as a sub-process.

5. The system of claim 1, wherein the subset of the data object network comprises data objects, and wherein the application executes the parent process several times, each time processing additional data objects.

6. The system of claim 1, wherein the computer program generates a semantic cognition network, and wherein the semantic cognition network comprises the data object network, the processing object network, and a class object network.

7. The system of claim 6, wherein the class object network comprises a class domain, and wherein the parent process is unambiguously defined by the one of the plurality of neighborhood descriptions, the one algorithm of the set of algorithms, and the class domain.

8. The system of claim 6, wherein the application performs a morphological operation using the one algorithm of the set of algorithms to combine data objects of the subset of the data object network with additional data objects to create secondary data objects.

9. The system of claim 8, wherein the application compares the secondary data objects with the class domain.

10. The system of claim 1, wherein the data object network and the processing object network are linked together by link objects that are dynamically generated by the application based on the one of the plurality of neighborhood descriptions.

11. The system of claim 1, wherein the parent process extracts a subset of data objects from the data object network and applies the one algorithm of the set of algorithms to each data object in the subset of data objects.

12. A system for generating an application that analyzes digital image data, comprising:

a computer readable storage medium; and

a computer program stored on the storage medium comprising;

a set of algorithms, wherein each algorithm of the set of algorithms represents an operation performable by the application;

a plurality of neighborhood descriptions, wherein each of the plurality of neighborhood descriptions represents a subset of a data object network, and wherein the data object network is generated by segmenting the digital image data; and

means for generating a processing object network, wherein the processing object network includes a parent process and a plurality of child processes, wherein the parent process comprises one of the plurality of neighborhood descriptions and one algorithm of the set of algorithms, and wherein the algorithm performs the operation on the subset of the data object network represented by the data domain.

13. The system of claim 12, wherein the subset of the data object network comprises data objects, and wherein the application executes the parent process several times, each time processing additional data objects.

14. The system of claim 12, wherein the parent process extracts a subset of data objects from the data object network and applies the one algorithm of the set of algorithms to each data object in the subset of data objects.

15. A method for generating an application that analyzes an image, comprising:

adding a new processing object to a processing object network using a graphical user interface, wherein the processing object network includes a parent processing object and a child processing object, and wherein the image is displayed on the graphical user interface;

designating that the new processing object is appended to the child processing object;

selecting a data domain and adding the data domain to the new processing object; and

selecting an algorithm and adding the algorithm to the new processing object, wherein the application uses the new processing object to identify a portion of the image that is to be highlighted on the graphical user interface.

16. The method of claim 15, further comprising:

configuring parameters of the algorithm.

17. The method of claim 15, wherein the data domain represents a subset of a data object network, and wherein the algorithm performs an operation on the subset of the data object network.

18. The method of claim 17, wherein the image comprises image information, and wherein the data object network is generated by segmenting the image information, further comprising:

displaying the data object network as an overlay over the image.