Method and apparatus for cropping images

1. A method for determining the boundaries of a received digital document, comprising:

using a processor to perform the steps of:

identifying the largest connected component in the received digital document and assigning the boundaries of the largest connected component as the boundaries of the received digital document;

determining if the largest connected component has expected boundaries within a confidence range; and

if the largest connected component does not have boundaries within the confidence range, using a row by row and column by column analysis of the received digital document to identify horizontal and vertical bands in the digital image having pixels with a value opposite to the value of pixels of a background of the received digital document and assigning the horizontal and vertical bands to be the boundaries of the received digital document.

2. The method of claim 1 , wherein identifying the largest connected component in the received digital document comprises:

finding the connected components in the image and creating an array of connected components from the found connected components;

determining which connected component is the largest;

creating a rectangle that encloses the largest connected component;

eliminating small connected components from the array; and

determining the boundaries of the largest connected component.

3. The method of claim 2 , further comprising expanding the rectangle to include connected components in the array that are not alone prior to determining the boundaries of the largest connected component.

4. The method of claim 1 wherein the row by row and column by column analysis includes using the horizontal and vertical bands to eliminate horizontal and vertical bands in the digital image having the value of pixels of the background of the received digital document.

5. The method of claim 4 wherein the eliminated horizontal bands are less than about 60 pixels in height and the eliminated vertical bands are less than about 60 pixels in width.

6. The method of claim 4 further comprising eliminating horizontal and vertical bands that are within a predetermined distance from a border of the received digital document.

7. The method of claim 1 , wherein assigning the horizontal and vertical bands to be the boundaries of the received digital document comprises determining the horizontal bands that are furthest apart and the vertical bands that are furthest apart for pixels having values opposite of the background of the received digital document.

8. A method for determining the boundaries of a received digital document, comprising:

using a processor to perform the steps of:

identifying the largest connected component in the received digital document and assigning the boundaries of the largest connected component as the boundaries of the received digital document;

identifying, using a row by row and column by column analysis of the received digital document, horizontal and vertical bands in the digital image having pixels with a value opposite to the value of pixels of a background of the received digital document and assigning the horizontal and vertical bands to be the boundaries of the received digital document;

determining which of the boundaries identified in the respective identifying steps best approximates expected boundaries within a confidence range; and

assigning the boundaries identified in said determining step as the boundaries of the received digital document.

9. The method of claim 8 , wherein identifying the largest connected component in the received digital document comprises:

finding the connected components in the image and creating an array of connected components from the found connected components;

determining which connected component is the largest;

creating a rectangle that encloses the largest connected component;

eliminating small connected components from the array; and

determining the boundaries of the largest connected component.

10. The method of claim 9 , further comprising expanding the rectangle to include connected components in the array that are not alone prior to determining the boundaries of the largest connected component.

11. The method of claim 8 wherein the row by row and column by column analysis includes using the horizontal and vertical bands to eliminate the horizontal and vertical bands in the digital image having the value of pixels of the background of the received digital document.

12. The method of claim 11 wherein the eliminated horizontal bands are less than about 60 pixels in height and the eliminated vertical bands are less than about 60 pixels in width.

13. The method of claim 11 further comprising eliminating horizontal and vertical bands that are within a predetermined distance from a border of the received digital document.

14. The method of claim 8 wherein the identifying steps are performed in parallel.

15. A non-transitory computer readable storage medium having instructions stored thereon that when processed by a processor cause the processor to implement a method of identifying boundaries of a received digital document by causing said processor to identify a largest connected component in the received digital document by performing the steps of:

finding the connected components in the image and creating an array of connected components from the found connected components;

determining which connected component is the largest;

creating a rectangle that encloses the largest connected component;

eliminating small connected components from the array; and

determining the boundaries of the largest connected component as the boundaries of the received digital document.

16. The medium of claim 15 , further comprising instructions that cause said processor to expand the rectangle to include connected components in the array that are not alone prior to determining the boundaries of the largest connected component.

17. A non-transitory computer readable storage medium having instructions stored thereon that when processed by a processor cause the processor to implement a method of identifying boundaries of a received digital document by causing said processor to identify vertical and horizontal boundaries of the received digital document by performing the steps of:

performing a the row by row analysis of the received digital document to identify horizontal bands in the digital image having pixels with a value opposite to the value of pixels of a background of the received digital document;

eliminating horizontal bands that are less than a first predetermined number of pixels in height;

assigning the horizontal bands as vertical boundaries of the received digital document that are furthest apart yet border pixels having the value of the background of the received digital document;

performing a the column by column analysis of the received digital document to identify vertical bands in the digital image having pixels with a value opposite to the value of pixels of a background of the received digital document;

eliminating vertical bands that are less than a second predetermined number of pixels in width; and

assigning the vertical bands as horizontal boundaries of the received digital document that are furthest apart yet border pixels having the value of the background of the received digital document.

18. The medium of claim 17 wherein the eliminated horizontal bands are less than about 60 pixels in height and the eliminated vertical bands are less than about 60 pixels in width.

19. The medium of claim 17 further comprising eliminating horizontal and vertical bands that are within a predetermined distance from a border of the received digital document.

20. An apparatus adapted to identify the boundaries of a received digital document, comprising:

a scanner that scans a document to obtain the received digital document; and

a processor adapted to identify the largest connected component in the received digital document and to assign the boundaries of the largest connected component as the boundaries of the received digital document and adapted to perform a row by row and column by column analysis of the received digital document to identify horizontal and vertical bands in the digital image having pixels with a value opposite to the value of pixels of a background of the received digital document and to assign the horizontal and vertical bands to be the boundaries of the received digital document.

21. An apparatus as in claim 20 , wherein said processor is further adapted to determine if the largest connected component has expected boundaries within a confidence range and, if not, to use the boundaries of the received digital document as determined by the row by row and column by column analysis of the received digital document.

22. An apparatus as in claim 20 , wherein said processor is further adapted to determine which of the boundaries identified in the respective identifying steps best approximates expected boundaries within a confidence range and to assign the boundaries so determined as the boundaries of the received digital document.

23. An apparatus as in claim 20 , wherein the processor identifies the largest connected component in the received digital document by:

finding the connected components in the image and creating an array of connected components from the found connected components;

determining which connected component is the largest;

creating a rectangle that encloses the largest connected component;

eliminating small connected components from the array; and

determining the boundaries of the largest connected component.

24. An apparatus as in claim 23 , wherein the processor further expands the rectangle to include connected components in the array that are not alone prior to determining the boundaries of the largest connected component.

25. An apparatus as in claim 20 wherein the row by row and column by column analysis performed by the processor includes using the horizontal and vertical bands to eliminate the bands in the digital image having the value of pixels of the background of the received digital document.

26. An apparatus as in claim 25 wherein the eliminated horizontal bands are less than about 60 pixels in height and the eliminated vertical bands are less than about 60 pixels in width.

27. An apparatus as in claim 25 wherein the processor further eliminates horizontal and vertical bands that are within a predetermined distance from a border of the received digital document.

28. An apparatus as in claim 20 , wherein the processor identifies the largest connected component and identifies the horizontal and vertical bands in parallel.