Method for processing data structures with networked semantic units

• US 7,437,004 B2
• Filed: 12/13/2000
• Issued: 10/14/2008
• Est. Priority Date: 12/14/1999
• Status: Expired due to Term

• Current Assignee: Definiens AG (Astrazeneca PLC)
• Original Assignee: Definiens AG (Astrazeneca PLC)
• Inventors: Schmidt, Gunter, Baatz, Martin, Schape, Arno
• Primary Examiner(s): Chen; Wenpeng
• Application Number:
  US10/168,276
• Publication Number:
  US 20030115175A1
• Time in Patent Office: 2,862 Days
• Field of Search: 707/3, 707/103.R, 707/5, 707/1, 345/764, 703/2, 703/6, 706/10, 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. The method 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. The method uses 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 computer-implemented method for processing data structures, said method comprising:

generating a network of semantic knowledge units, wherein each semantic knowledge unit classifies a physical object;

generating a network of processing objects, wherein each processing object contains an algorithm;

acquiring a data structure, wherein the data structure is a digital image comprising datapoint objects;

segmenting the acquired data structure at various degrees of resolution;

generating a hierarchy of semantic structure units on the basis of the acquired data structure and the network of semantic knowledge units, wherein each algorithm of each processing object modifies those semantic structure units that are classified to the semantic knowledge units linked to the processing object; and

iteratively applying at least one of the following methods on a set of the semantic structure units, wherein the applied method depends on a classification of the semantic structure units, and each of the following methods is applicable to a class of the semantic structure units;

(a) generating new semantic structure units,

(b) analyzing the semantic structure units,

(c) modifying the semantic structure units,

(d) classifying whether each of the modified semantic structure units belongs to the classification,

(e) modifying the semantic structure units based on the classification,

(f) deleting the semantic structure units, and

(g) storing the semantic structure units.

2. The computer-implemented method of claim 1, wherein each of the semantic structure units is a portion of the digital image.

3. The computer-implemented method of claim 2, wherein the classifying in (d) is performed based on a property of the modified semantic structure units, and wherein the property is taken from the group consisting of:

a color, a texture, a shape, a position, a size and a length of an edge in common with a contiguous semantic structure unit.

4. The computer-implemented method of claim 1, wherein the datapoint objects are pixel values.

5. The computer-implemented method of claim 1, wherein the digital image is a satellite photograph.

6. The computer-implemented method of claim 1, wherein the digital image is acquired by a satellite optical sensor.

7. The computer-implemented method of claim 1, further comprising:

displaying a modified semantic structure unit classified in (d).

8. The computer-implemented method of claim 7, wherein the classified modified semantic structure unit depicts urban greenlands in the digital image.

9. The computer-implemented method of claim 7, wherein the classified modified semantic structure unit depicts land cover in a digital image.

10. The computer-implemented method of claim 1, wherein the data structure is an n-dimensional table of data.

11. The computer-implemented method of claim 10, wherein the datapoint objects occupy two dimensions of the n-dimensional table of data.

12. The computer-implemented method of claim 1, wherein the semantic structure units provide a condensed representation of the acquired data structure, further comprising:

discarding the datapoint objects from the hierarchy of semantic structure units and thereby performing data compression on the hierarchy of semantic structure units.

13. The computer-implemented method of claim 1, wherein the data structure is acquired by scanning one line of datapoint objects of a document at a time.

14. The computer-implemented method of claim 1, wherein the network of semantic knowledge units forms a knowledge base.

15. The computer-implemented method of claim 1, wherein each semantic knowledge unit comprises a feature object, and wherein the classifying in (d) whether the modified semantic structure unit belongs to the classification is performed according to the feature object.