System and method for preprocessing images to improve OCR efficacy

1. A system to preprocess images to increase accuracy of optical character recognition (OCR), the system comprising:

a processor;

a memory coupled to the processor;

the processor configured to

scan an electronically stored representation of a whole or partial document;

identify an image in the electronically stored representation of a whole or partial document;

recognize row-based text within the electronically stored representation of a whole or partial document;

align the row-based text vertically by calculating a first text bounding rectangle for a first portion of the row-based text;

generate a resultant electronically stored representation of a whole or partial document having the row-based text aligned; and

save the resultant electronically stored representation of a whole or partial document electronically for subsequent OCR processing.

2. The system of claim 1 , wherein the electronically stored representation of a whole or partial document contains at least one image of a format type including but not limited to JPG, TIF, GIF, PNG, BMP, or any combination thereof.

3. The system of claim 1 , wherein the resultant electronically stored representation of a whole or partial document contains at least one image of a format type including but not limited to JPG, TIF, GIF, PNG, BMP, or any combination thereof.

4. The system of claim 1 , wherein the system is configured to operate using on-demand, continuous, single, or bulk image conversions, or any combination thereof.

5. The system of claim 1 , wherein the row-based text is vertically aligned using top, center or bottom alignment, or any combination thereof.

6. A non-transitory processor readable medium having processor instructions that are executable to cause a processor coupled to a memory to:

scan an electronically stored representation of a whole or partial document;

identify one or more images in the electronically stored representation of a whole or partial document;

recognize row-based text within the electronically stored representation of a whole or partial document;

align the row-based text vertically by calculating a first text bounding rectangle for a first portion of the row-based text;

generate a resultant electronically stored representation of a whole or partial document having the row-based text aligned; and

save the resultant representation of a whole or partial document electronically for subsequent optical character recognition (OCR) processing.

7. The non-transitory processor readable medium of claim 6 , wherein the electronically stored representation of a whole or partial document contains at least one image of a format type including but not limited to JPG, TIF, GIF, PNG, BMP, or any combination thereof.

8. The non-transitory processor readable medium of claim 6 , wherein the resultant electronically stored representation of a whole or partial document contains at least one image of a format type including but not limited to JPG, TIF, GIF, PNG, BMP, or any combination thereof.

9. The non-transitory processor readable medium of claim 6 , wherein the processor is configured to operate using on-demand, continuous, single, or bulk image conversions, or any combination thereof.

10. The non-transitory processor readable medium of claim 6 , wherein the row-based text is vertically aligned using top, center or bottom alignment, or any combination thereof.

11. A method to preprocess images to increase accuracy of optical recognition (OCR), the method comprising:

scanning a representation of a whole or partial document electronically stored in a memory;

identifying an image in the electronically stored representation of a whole or partial document using a processor coupled to the memory;

recognizing row-based text within the electronically stored representation of a whole or partial document using the processor;

aligning the row-based text vertically by calculating a first text bounding rectangle for a first portion of the row-based text using the processor; and

saving the resultant electronically stored representation of a whole or partial document in the memory for subsequent OCR processing.

12. The method of claim 11 , wherein the electronically stored representation of a whole or partial document contains at least one image of a format type including but not limited to JPG, TIF, GIF, PNG, BMP, or any combination thereof.

13. The method of claim 11 , wherein the resultant electronically stored representation of a whole or partial document contains at least one image of a format type including but not limited to JPG, TIF, GIF, PNG, BMP, or any combination thereof.

14. The method of claim 11 , wherein the processor is configured to operate using on-demand, continuous, single or bulk image conversions, or any combination thereof.

15. The method of claim 11 , wherein the row-based text is vertically aligned using top, center or bottom alignment, or any combination thereof.

16. The method of claim 11 , wherein aligning the row-based text vertically comprises calculating a distance needed to align the first text bounding rectangle to an above adjacent text bounding rectangle.

17. The method of claim 16 , wherein aligning the row-based text vertically comprises determining whether the distance is greater than zero and less than a threshold distance.

18. The method of claim 17 , wherein aligning the row-based text vertically comprises top justifying the first text bounding rectangle to a top of the above adjacent text bounding rectangle by moving the first text bounding rectangle upwards when the distance is greater than zero and less than the threshold distance.

19. The method of claim 18 , wherein aligning the row-based text vertically comprises shifting text pixels encompassed within the first text bounding rectangle.