Claims

1. A computer implemented method for correcting distortion in an image of a page with a content, the method comprising: identifying a set of high quality words including at least one high quality word in an undistorted region of one or more images of one or more pages having content related to the content of the page; identifying at least one distorted word in the image the page, each distorted word of said at least one distorted word corresponding to a high quality word from the set of high quality words; generating a global transformation function for application to the image of the page so as to substantially tranform a distorted word of said at least one distorted word to its corresponding high quality word; and applying the global transformation function to pixels of the image of the page.

2. A method as claimed in claim 1, wherein said at least one distorted word comprises at least two distorted words, and wherein generating a global transformation function for application to the image of the page comprises: generating at least two local transformation functions, each local transformation function of said at least two local transformation functions applicable to a corresponding distorted word of said at least two distorted words so as to substantially transform the corresponding disorted word to its corresponding high quality word; and fitting a global function to said at least two local transformation functions.

3. A method as claimed in claim 2, wherein said at least two local transformation functions comprise polynomial functions.

4. A method as claimed in claim 1, wherein the global transformation function comprises a polynomial function.

5. A method as claimed in claim 1, wherein generating the global transformation function comprises application of an optical flow technique.

6. A method as claimed in claim 1, comprising segmenting the image of the page or said one or more images of one or more pages into words.

7. A method as claimed in claim 1, comprising applying a binarization technique to the image of the page or to said one or more images of one or more pages.

8. A computer program product stored on a non-transitory tangible computer readable storage medium for correcting distortion in an image of a page with a content, the computer program including code for: identifying a set of high quality words including at least one high quality word in an undistorted region of one or more images of one or more pages having content related to the content of the page; identifying at least one distorted word in the image the page, each distorted word of said at least one distorted word corresponding to a high quality word from the set of high quality words; generating a global transformation function for application to the image of the page so as to substantially tranform a distorted word of said at least one distorted word to its corresponding high quality word; and applying the global transformation function to pixels of the image of the page.

9. A computer program product as claimed in claim 8, wherein said at least one distorted word comprises at least two distorted words, and wherein the code for generating a global transformation function for application to the image of the page comprises code for: generating at least two local transformation functions, each local transformation function of said at least two local transformation functions applicable to a corresponding distorted word of said at least two distorted words so as to substantially transform the corresponding disorted word to its corresponding high quality word; and fitting a global function to said at least two local transformation functions.

10. A computer program product as claimed in claim 9, wherein said at least two local transformation functions comprise polynomial functions.

11. A computer program product as claimed in claim 8, wherein the global transformation function comprises a polynomial function.

12. A computer program product as claimed in claim 8, wherein the code for generating the global transformation function comprises code for application of an optical flow technique.

13. A computer program product as claimed in claim 8, comprising code for segmenting the image of the page or said one or more images of one or more pages into words.

14. A method as claimed in claim 1, comprising code for applying a binarization technique to the image of the page or to said one or more images of one or more pages.

15. A data processing system comprising: a processor; a computer usable medium connected to processor, wherein the computer usable medium contains a set of instructions for correcting distortion in an image of a page with a content, wherein the processor is designed to carry out a set of instructions to: identify a set of high quality words including at least one high quality word in an undistorted region of one or more images of one or more pages having content related to the content of the page; identify at least one distorted word in the image the page, each distorted word of said at least one distorted word corresponding to a high quality word from the set of high quality words; generate a global transformation function for application to the image of the page so as to substantially tranform a distorted word of said at least one distorted word to its corresponding high quality word; and apply the global transformation function to pixels of the image of the page.

16. A data processing system as claimed in claim 15, wherein said at least one distorted word comprises at least two distorted words, and wherein the instructions to generate a global transformation function for application to the image of the page comprise instructions to: generate at least two local transformation functions, each local transformation function of said at least two local transformation functions applicable to a corresponding distorted word of said at least two distorted words so as to substantially transform the corresponding disorted word to its corresponding high quality word; and fit a global function to said at least two local transformation functions.

17. A data processing system as claimed in claim 16, wherein said at least two local transformation functions comprise polynomial functions.

18. A data processing system as claimed in claim 15, wherein the global transformation function comprises a polynomial function.

19. A data processing system as claimed in claim 15, wherein the instructions for generating the global transformation function comprise instructions to apply an optical flow technique.

20. A data processing system as claimed in claim 15, comprising instructions to segment the image of the page or said one or more images of one or more pages into words.

21. A data processing system as claimed in claim 15, comprising instructions to apply a binarization technique to the image of the page or to said one or more images of one or more pages.