Enhanced multilayer compression of image files using OCR systems

1. A method for processing a document image, the method comprising:

segmenting the document image into a picture component and a non-picture component;

identifying a text block in the non-picture component, wherein the background layer includes a background color for the text block in the non-picture component;

for the non-picture component constructing a background layer, a chromatic layer and a monochrome mask;

compressing at least a portion of the non-picture component;

saving at least one of the compressed non-picture component and the compressed picture component in memory; and

forming a recomposed image based on at least one of the compressed picture component and the compressed non-picture component.

2. The method of claim 1 , wherein the non-picture component includes characters.

3. The method of claim 1 , wherein the monochrome mask acts as a switch to control when a pixel in the recomposed image would be rendered based on the background and chromatic layers.

4. The method of claim 1 , wherein the compressing of the picture component is done based on a preliminary defined compression ratio.

5. The method of claim 1 , wherein the compressing of the picture component includes a non-lossy compression algorithm.

6. The method of claim 1 , wherein segmenting the document image into the picture component includes identifying each picture in the document image based on one or more chromaticity changes.

7. The method of claim 1 , wherein the method further comprises performing optical character recognition on any text of the text block.

8. The method of claim 1 , wherein constructing the background layer includes reducing a complexity of the background layer recursively using information about a color of known surrounding pixels to compute a fill color for respective unknown pixels.

9. The method of claim 1 , wherein the compressing of at least the portion of the non-picture component is based on a background feature of the non-picture component.

10. The method of claim 1 , wherein the method further comprises:

compressing the picture component.

11. The method of claim 1 , wherein said compressing the non-picture component includes vectorizing the background layer, wherein vectorizing includes use of a geometric shape.

12. The method of claim 1 , wherein the background layer is constructed by applying vectorization of an object, wherein an object is represented as a composition of one or more geometric shapes.

13. The method of claim 1 , wherein the chromatic layer is constructed by filling areas around one or more characters of the text block with a color derived from a respective character, wherein filling is performed by calculating one or more color pixels for each unknown region and filling the unknown region.

14. The method of claim 13 , wherein filling the unknown region is performed in a recursive manner.

15. The method of claim 13 , wherein the method further comprises:

compressing the background layer via use of a limited palette of detected colors.

16. The method of claim 1 , wherein the method further comprises:

analyzing the background layer for a colored area, wherein the colored area includes one or more colors.

17. The method of claim 16 , wherein analyzing the background layer includes detecting a shape of the said text block in the non-picture component.

18. The method of claim 16 , wherein the colored area is vectorized.

19. The method of claim 1 , wherein background layer or a portion of the background is compressed by a lossy compression method.

20. A system for processing an image of a document, the 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:

segment the image of the document into a picture component and a non-picture component;

from the non-picture component, constructing a background layer, a chromatic layer and a monochrome mask for the non-picture component;

identify a text block in the non-picture component; wherein the background layer includes a background color for the text block in the non-picture component;

compress the picture component;

compress the non-picture component based on a background feature of the non-picture component;

save at least one of the compressed non-picture component and the compressed picture component in memory; and

form a recomposed image based on at least the significant picture component and the compressed non-picture component.

21. The system of claim 20 , wherein the non-picture component includes characters.

22. The system of claim 20 , wherein the monochrome mask acts as a switch to control when a pixel in the recomposed image would be rendered based on the background and chromatic layers.

23. The system of claim 20 , wherein the compressing of the picture component is done based on a preliminarily defined compression ratio.

24. The system of claim 20 , wherein the compressing of the picture component involves a non-lossy compression algorithm.

25. The system of claim 20 , wherein segmenting the document image into the picture component includes identifying each picture in the document image based on one or more chromaticity changes.

26. The system of claim 20 , wherein the instructions further cause the system to:

perform optical character recognition on any characters identified in the non-picture component.

27. The system of claim 20 , wherein constructing the background layer includes reducing a complexity of the background layer recursively using information about a color of known surrounding pixels to compute a fill color for respective unknown pixels.

28. The system of claim 20 , wherein the background layer includes a background color for the identified text block.