PATENTSCOPE will be unavailable a few hours for maintenance reason on Tuesday 19.11.2019 at 4:00 PM CET
Search International and National Patent Collections
Some content of this application is unavailable at the moment.
If this situation persists, please contact us atFeedback&Contact
1. (WO2007005937) GRAMMATICAL PARSING OF DOCUMENT VISUAL STRUCTURES
Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

CLAIMS

What is claimed is:

1. A system that facilitates recognition, comprising:
a receiving component that receives an input associated with a visual structure of a document; and
a grammar component that employs, at least in part, a grammatical hierarchical structure model of the visual structure of the document to facilitate in grammatically parsing the input.

2. The system of claim 1, the grammar component further comprising a document structure extraction component that extracts a layout structure associated with the document utilizing local and/or global features.

3. The system of claim 2, the document structure extraction component utilizes machine learning, image scoring, parse learning boosting, and/or fast features to facilitate in extracting the document layout structure.

4. The system of claim 1, the grammar component further comprising:
a parsing component that employs at least one classifier to facilitate in determining an optimal parse from a global search.

5. The system of claim 4, the parsing component employs the classifier to facilitate in determining a grammatical cost function.

6. The system of claim 5, the classifier comprising a classifier trained via a conventional machine learning technique.

7. The system of claim 6, the machine learning technique comprising, at least in part, a perceptron-based technique.

8. The system of claim 1, the grammar component utilizes a grammatical parsing process based on, at least in part, a discriminative grammatical model.

9. The system of claim 1, the grammar component employs, at least in part, dynamic programming to determine the optimal parse tree for the structured layout.

10. A method for facilitating recognition, comprising:
receiving an input associated with a visual structure of a document; and
applying a grammatical parsing process to an inference of the document visual structure.

11. The method of claim 10 further comprising:
employing, at least in part, a grammatical hierarchical structure model of the visual structure of the document to facilitate in grammatically parsing the document visual structure input.

12. The method of claim 10, the grammatical parsing process based on a discriminative grammatical model.

13. The method of claim 10 further comprising:
parsing the input based on a grammatical cost function; the grammatical cost function derived, at least in part, via a machine learning technique that facilitates in determining an optimal parse from a global search.

14. The method of claim 13 further comprising:
representing at least one parse as an image; and
scoring the image to facilitate the grammatical cost function in determining the optimal parse.

15. The method of claim 14 further comprising: computing integral images of at least one document feature and/or computing at least one constellation of a plurality of integral images to facilitate in parsing the input.

16. The method of claim 13 further comprising:
utilizing AdaBoost to facilitate in parsing the input.

17. A system that facilitates recognition, comprising:
means for receiving an input associated with a visual structure of a document; and
means for employing, at least in part, a grammatical model of the visual structure of the document to facilitate in grammatically parsing the visual structure input.

18. The system of claim 17 further comprising:
means for parsing the visual structure input utilizing at least one classifier trained via a machine learning technique.

19. A device employing the method of claim 10 comprising at least one selected from the group consisting of a computer, a server, and a handheld electronic device.

20. A recognition system employing the system of claim 1 to facilitate in importing and/or exporting document visual structures.