Optical character recognition segmentation

1. An optical character recognition segmentation and processing method comprising:

receiving, by a processor of a hardware device, a document for processing;

detecting, by said processor, different types of text data of said document;

dividing, by said processor, said document into a plurality of text regions associated with said different types of said text data, wherein each text region of said plurality of text regions comprises a single type of said text data;

removing, by said processor, optical noise from each said text region, wherein said removing said optical noise from each said text region comprises:

encoding, by said processor, each said text region as a total semantic vector of each said text region;

enabling, by said processor, a 3×3 window to divide each said text region into multiple sub-regions such that each sub-region of said multiple sub-regions is encoded as a 1×300 vector; and

generating, by said processor based on said total semantic vector, a dot product for each said sub-region, wherein each said dot product comprises a specific score representing an importance level for each said sub-region;

selecting, by said processor, differing optical character recognition software code for application to each said text region and

executing, by said processor in response to said selecting, said differing optical character recognition software code with respect to each said text region resulting in extractable computer readable text within each said text region.

2. The method of claim 1 , further comprising:

classifying, by said processor, each said text region with respect to said single type of said text data, wherein said selecting is executed based on results of said classifying.

3. The method of claim 1 , wherein said removing said optical noise from each said text region further comprises:

comparing, by said processor, each said specific score to a score threshold; and

deleting, by said processor based on results of said comparing, all pixels of each sub-region exceeding said score threshold to perform said removing.

4. The method of claim 1 , wherein said optical noise comprises unnecessary background text and images of said document.

5. The method of claim 1 , wherein each said differing optical character recognition software code comprises self-learning software code stored in a specialized database.

6. The method of claim 1 , wherein said extractable computer readable text within each said text region is configured for usage with respect to a cut or copy and paste function.

7. The method of claim 1 , wherein said different types of text data are comprised by a format selected from the group consisting of a table format, a watermark format, a handwriting format, and a rotated text format.

8. The method of claim 1 , further comprising:

providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable code in the hardware device, said code being executed by the computer processor to implement: said receiving, said detecting, said dividing, said removing, said selecting, and said executing.

9. A computer program product, comprising a computer readable hardware storage device storing a computer readable program code, said computer readable program code comprising an algorithm that when executed by a processor of a hardware device implements an optical character recognition segmentation and processing method, said method comprising:

receiving, by said processor, a document for processing;

detecting, by said processor, different types of text data of said document;

dividing, by said processor, said document into a plurality of text regions associated with said different types of said text data, wherein each text region of said plurality of text regions comprises a single type of said text data;

removing, by said processor, optical noise from each said text region, wherein said removing said optical noise from each said text region comprises:

encoding, by said processor, each said text region as a total semantic vector of each said text region;

enabling, by said processor, a 3×3 window to divide each said text region into multiple sub-regions such that each sub-region of said multiple sub-regions is encoded as a 1×300 vector; and

generating, by said processor based on said total semantic vector, a dot product for each said sub-region, wherein each said dot product comprises a specific score representing an importance level for each said sub-region;

selecting, by said processor, differing optical character recognition software code for application to each said text region and

executing, by said processor in response to said selecting, said differing optical character recognition software code with respect to each said text region resulting in extractable computer readable text within each said text region.

10. The computer program product of claim 9 , wherein said method further comprises:

classifying, by said processor, each said text region with respect to said single type of said text data, wherein said selecting is executed based on results of said classifying.

11. The computer program product of claim 9 , wherein said removing said optical noise from each said text region further comprises:

comparing, by said processor, each said specific score to a score threshold; and

deleting, by said processor based on results of said comparing, all pixels of each sub-region exceeding said score threshold to perform said removing.

12. The computer program product of claim 9 , wherein said optical noise comprises unnecessary background text and images of said document.

13. The computer program product of claim 9 , wherein each said differing optical character recognition software code comprises self-learning software code stored in a specialized database.

14. The computer program product of claim 9 , wherein said extractable computer readable text within each said text region is configured for usage with respect to a cut or copy and paste function.

15. The computer program product of claim 9 , wherein said different types of text data are comprised by a format selected from the group consisting of a table format, a watermark format, a handwriting format, and a rotated text format.

16. A hardware device comprising a processor coupled to a computer-readable memory unit, said memory unit comprising instructions that when executed by the processor implements an optical character recognition segmentation and processing method comprising:

receiving, by said processor, a document for processing;

detecting, by said processor, different types of text data of said document;

dividing, by said processor, said document into a plurality of text regions associated with said different types of said text data, wherein each text region of said plurality of text regions comprises a single type of said text data;

removing, by said processor, optical noise from each said text region, wherein said removing said optical noise from each said text region comprises:

encoding, by said processor, each said text region as a total semantic vector of each said text region;

enabling, by said processor, a 3×3 window to divide each said text region into multiple sub-regions such that each sub-region of said multiple sub-regions is encoded as a 1×300 vector; and

generating, by said processor based on said total semantic vector, a dot product for each said sub-region, wherein each said dot product comprises a specific score representing an importance level for each said sub-region;

selecting, by said processor, differing optical character recognition software code for application to each said text region and

executing, by said processor in response to said selecting, said differing optical character recognition software code with respect to each said text region resulting in extractable computer readable text within each said text region.

17. The hardware device of claim 16 , wherein said method further comprises:

classifying, by said processor, each said text region with respect to said single type of said text data, wherein said selecting is executed based on results of said classifying.

18. The hardware device of claim 16 , wherein said removing said optical noise from each said text region further comprises:

comparing, by said processor, each said specific score to a score threshold; and

deleting, by said processor based on results of said comparing, all pixels of each sub-region exceeding said score threshold to perform said removing.