Method of pre-analysis of a machine-readable form image
View Patent ↗In one embodiment, the invention provides a method for a machine to perform machine-readable form pre-recognition analysis. The method comprises preliminarily assigning at least one graphic image in a form for identification of form type, preliminarily creating at least one model of the said graphic image for identification of the form type, parsing a form image into regions, determining an image form type for the form image, comprising: (a) detecting on the form image at least one of said graphic images for identification of the form type, (b) performing a primary identification of the form image type based on a comparison of the detected graphic image with the said model, and(c) performing a profound analysis using a supplementary data said-primary identification results in multiple possibilities for the form image type.
1. A method for a machine to perform machine-readable form pre-recognition analysis comprising:
preliminarily assigning at least one graphic image in a form for identification of form type;
preliminarily creating at least one model of the said graphic image for identification of the form type; and
determining an image form type for a form image, comprising:
detecting on the form image at least one of said graphic images for identification of the form type,
performing a primary identification of the form image type based on a comparison of the detected graphic image with the said model, and
performing a profound analysis using a supplementary data when said primary identification results in multiple possibilities for the form image type,
wherein the profound analysis comprises:
assigning to the form at least one supplementary form element;
creating a profound analysis model using the said model of the said graphic image plus at least one said supplementary assigned form element; and
performing the profound analysis of the form image using said profound analysis model.
2. The method as recited in claim 1 , wherein determining the form image type comprises setting up and examining hypotheses and corresponding matching reliability estimations.
3. The method as recited in claim 1 , wherein determining the form image type is performed using a minimum possible set of objects, defining the form type.
4. The method as recited in claim 1 , wherein the at least one graphic image comprises a non-text image.
5. The method as recited in claim 1 , wherein the at least one graphic image comprises a text image.
6. The method as recited in claim 5 , wherein said text image is additionally recognized as a first step in the pre-recognition analysis.
7. The method as recited in claim 6 , wherein the recognized text is used as supplementary data in a form type definition process.
8. The method as recited in claim 2 , wherein the matching reliability estimation is performed on all steps of the pre-recognition analysis.
9. The method as recited in claim 1 , wherein assigning comprises assigning a group of graphic images.
10. The method as recited in claim 4 , wherein at least one form object comprises an element of empty region type.
11. The method as recited in claim 4 , wherein at least one form object is of dividing line type.
12. The method as recited in claim 1 , wherein the profound analysis is performed using any other supplementary data.
13. The method as recited in claim 9 , wherein the entire group of graphic images is used for determining the form type.
14. The method as recited in claim 1 , wherein the said graphic image is used for identifying the form type.
15. The method as recited in claim 1 , further comprising
parsing the form image into regions, wherein the regions contain at least one of text objects images, data input fields, special reference points, and lines.
16. A system, comprising:
a processor; and
a memory coupled to the processor, the memory storing instructions which when executed by the processor, cause the system to perform a method for machine-readable form pre-recognition analysis comprising:
preliminarily assigning at least one graphic image in a form for identification of form type,
preliminarily creating at least one model of the said graphic image for identification of the form type, and
determining an image form type for the form image, comprising:
detecting on the form image at least one of said graphic images for identification of the form type,
performing a primary identification of the form image type based on a comparison of the detected graphic image with the said model, and
performing a profound analysis using a supplementary data when said primary identification results in multiple possibilities for the form image type,
wherein the profound analysis comprises:
assigning to the form at least one supplementary form element:
creating a profound analysis model using the said model of the said graphic image plus at least one said supplementary assigned form element; and
performing a profound analysis of the form image using said profound analysis model.
17. The system as recited in claim 16 , wherein determining the form image type comprises setting up and examining hypotheses and corresponding matching reliability estimations.
18. The system as recited in claim 16 , wherein determining the form image type is performed using a minimum possible set of objects, defining the form type.