Compilable plain english-like language for extracting objects from an image using a primitive image map

• US 6,724,931 B1
• Filed: 11/13/1998
• Issued: 04/20/2004
• Est. Priority Date: 12/02/1996
• Status: Expired due to Term

• Current Assignee: Shin-Yi Hsu
• Original Assignee: Shin-Yi Hsu
• Inventors: Hsu, Shin-yi
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): CHAWAN, SHEELA C
• Application Number:
  US09/191,394
• Time in Patent Office: 1,985 Days
• Field of Search: 382/113, 382/310, 382/230, 382/218, 382/190, 382/155, 345/333, 345/968, 345/964, 707/1-6, 707/4, 707/102, 707/104.1, 348/119
• US Class Current: 382/155
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition
• CPC Class Codes: G06F 18/40 Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor
• CPC Class Codes: Y10S 707/99934 Query formulation, input preparation, or translation
• CPC Class Codes: Y10S 707/99936 Pattern matching access
• CPC Class Codes: Y10S 707/99943 Generating database or data structure, e.g. via user interface
• CPC Class Codes: Y10S 715/968 interface for database querying and retrieval

Abstract

The invention features a method wherein a recognition environment utilizers pseudo-English as a programming language to extract simple and complex objects with image—and/or map—data as inputs. Based on this human/computer interface in which pseudo-English is a programming language, the object—recognition system has three major logic modules: (1) an input data module; (2) an information—processing module, coupled with the above—noted human computer interface (HCI) module; and (3) an output module that has a feedback mechanism back to the main information—processing and the input—data module. A physical phenomenon (i.e., one that is visible, audible, tactile, etc.) Is analyzed by the information—processing module to determine weather it is susceptible to description or articulation. If not, the phenomenon is matched or compared, via the output module, to a know articulatable, physical-phenomenon model and recognizable features are extracted.

Claims

1. A method of training a user to become an expert in identifying an object in an image, by querying a computer system comprising a lexicon of photo-interpreters, and formulating object extraction rules, the steps comprising:

a) providing a programming language comprising information supplied by at least one expert photo analyst, and information provided by user queries, said programming language comprising a set of predetermined vocabulary and syntax;

b) identifying an object in an image;

c) creating image files based on said queries of said user that aid in identifying an object; and

d) extracting said object from said image.

2. The method of training a user to become an expert in identifying an object in an image in accordance with claim 1, wherein said image files are presented on a graphical display.

3. The method of training a user to become an expert in identifying an object in an image in accordance with claim 1, wherein said image files comprise computer text files.

4. The method of training a user to become an expert in identifying an object in an image in accordance with claim 1, wherein said information provided by said user comprises one from the group of images, scenes, maps and computer text.

5. The method of training a user to become an expert in identifying an object in an image in accordance with claim 1, wherein said programming language comprises a text editor.

6. The method of training a user to become an expert in identifying an object in an image in accordance with claim 1, wherein said programming language comprises an expert system.

7. The method of training a user to become an expert in identifying an object in an image in accordance with claim 1, wherein said programming language comprises an expert editor.

8. The method of training a user to become an expert in identifying an object in an image in accordance with claim 1, wherein said programming language is a pseudo-human language.

9. The method of training a user to become an expert in identifying an object in an image in accordance with claim 8, wherein said pseudo-human language is pseudo-English.

10. The method of training a user to become an expert in identifying an object in an image in accordance with claim 8, wherein said vocabulary of said programming language comprises any one of the group of principles:

Tone, Texture, Size, Shape, Shadow, Pattern, Associated Features, and Stereo Scopic characteristics.

11. The method of training a user to become an expert in identifying an object in an image in accordance with claim 1, the steps further comprising:

d) marking an object on a display; and

e) directing the computer system to generate descriptive words, phrases, extraction rules, and image and text files for defining said object.

12. The method of training a user to become an expert in identifying an object in an image in accordance with claim 1, wherein said programming language further comprises extraction rule sets that are dependent upon said information supplied by said at least one expert.

13. The method of training a user to become an expert in identifying an object in an image in accordance with claim 1, further comprising matching means in said programming language for allowing a user to compare an observed object with stored prototypical objects.

14. A method of processing data to identify an object in an image, by querying a computer system comprising a lexicon of photo-interpreters, and formulating object extraction rules, comprising executing a computer program comprising (i) information supplied by at least one expert photo analyst, (ii) extraction rules that are dependent upon said information, and (iii) information input by a user, said computer program comprising a predetermined vocabulary for facilitating descriptions of objects to be identified.

15. The method of processing data in accordance with claim 14, wherein said information input by said user comprises one from the group of images, scenes, maps and computer text.

16. The method of processing data in accordance with claim 15, wherein the computer programming language is pseudo-English.

17. The method of processing data in accordance with claim 14, the steps further comprising:

marking an object on a display; and

directing the computer system to generate descriptive words, phrases, extraction rules and image and text files for defining said object.

18. A method of training a user to become an expert in identifying an observed object in an image, by querying a computer system comprising a lexicon of photo-interpreters, and formulating object extraction rules, the steps comprising:

a) providing a programming language comprising information supplied by at least one expert photo analyst, and information input by a user, said programming language comprising a set of predetermined vocabulary and syntax; and

b) using said programming language to analyze at least one portion of an image or data representative thereof, and determining whether an observed object in said image is articulatable by using descriptors therefor; and

c) matching said observed object to a known, articulatable object and generating a first confidence level based on said matching step, if said object is not articulatable.

19. The method of training a user in accordance with claim 18, the steps further comprising;

d) extracting recognizable features from said observed object, and assigning a second confidence level thereto, if said object is articulatable.

20. The method of training a user in accordance with claim 19, the steps further comprising:

e) combining said confidence levels of said observed objects to generate a composite confidence level thereof.

21. The method of training a user in accordance with claim 18, wherein said user is a machine.

22. A method of training a user to become an expert in performing a task in a predetermined subject, by querying a computer system comprising a lexicon of words and phrases, and formulating rules, the steps comprising:

a) providing a programming language comprising information supplied by at least one expert, said programming language comprising a set of predetermined vocabulary and syntax; and

b) using said programming language to analyze at least one task or data representative thereof, and determining whether said task is articulatable by using descriptors therefor; and

c) matching said task to a known, articulatable task and generating a first confidence level based on said matching step, if said task is not articulatable.

23. The method of training a user in accordance with claim 22, the steps further comprising:

d) recognizing the task and assigning a second confidence level thereto, if said task is articulatable.

24. The method of training a user in accordance with claim 23, the steps further comprising:

e) combining said confidence levels of said tasks to generate a composite confidence level thereof.

25. The method of training a user in accordance with claim 22, wherein said user is a machine.