Method, apparatus, and computer-readable storage medium for recognizing characters in a digital document

1. A method of recognizing a character in a digital document, the method comprising:

classifying, by processing circuitry, a segment of the digital document as including text;

calculating, by the processing circuitry, at least one parameter value associated with the classified segment of the digital document;

determining, by the processing circuitry and based on the calculated at least one parameter value, a zonal parameter value;

classifying, by the processing circuitry, the segment of the digital document as a handwritten text zone or as a printed text zone based on the determined zonal parameter value and a threshold value, the threshold value being based on a selection of an intersection of a handwritten text distribution profile and a printed text distribution profile, each of the handwritten text distribution profile and the printed text distribution profile being associated with a zonal parameter corresponding to the determined zonal parameter value; and

generating, by the processing circuitry and based on the classifying, a modified version of the digital document.

2. The method of claim 1 , further comprising

performing, by the processing circuitry and when the segment is classified as a handwritten text zone, handwritten character recognition on the segment to recognize the handwritten text, and

performing, by the processing circuitry and when the segment is classified as a printed text zone, printed character recognition on the segment to recognize the printed text.

3. The method of claim 1 , wherein the determined zonal parameter value is an object density value calculated by

multiplying, by the processing circuitry, a segment ratio by a segment height, the segment ratio being a ratio of a number of objects in the segment to a segment width.

4. The method of claim 1 , wherein the generating the modified version of the digital document includes

assigning, by the processing circuitry and when the segment is classified as a handwritten text zone, a handwritten text identifier to the segment, and

assigning, by the processing circuitry and when the segment is classified as a printed text zone, a printed text identifier to the segment.

5. The method of claim 2 , further comprising

generating, by the processing circuitry and as the modified version of the digital document, a first selectable version of the digital document, wherein the first selectable version of the digital document includes the recognized handwritten text within the segment.

6. The method of claim 2 , further comprising

generating, by the processing circuitry and as the modified version of the digital document, a second selectable version of the digital document, wherein the second selectable version of the digital document includes the recognized printed text within the segment.

7. The method of claim 1 , further comprising

obtaining, by the processing circuitry, the threshold value from a reference table comprising threshold values based on a type of the zonal parameter value, each of the threshold values being based on a corresponding handwritten text distribution profile and corresponding printed text distribution profile from a database,

the corresponding handwritten text distribution profile being based on a histogram associated with text zones labeled as handwritten text, and

the corresponding printed text distribution profile being based on a histogram associated with text zones labeled as printed text.

8. The method of claim 7 , wherein each of the histograms are based on a comparison of a parameter value for an object within a labeled text zone and a corresponding ranking for the object, the corresponding ranking being based on the parameter value for the object and parameter values for each other object within the labeled text zone.

9. The method of claim 1 , wherein the selection of the intersection of the handwritten text distribution profile and the printed text distribution profile includes

maximizing, by the processing circuitry, an area under a curve for each of the handwritten text distribution profile and the printed text distribution profile, the threshold value being a value above which the segment is likely to be handwritten text.

10. The method of claim 1 , wherein the classifying includes

calculating, by the processing circuitry, a zonal ranking value based on the determined zonal parameter value and ranking values associated with each of the calculated at least one parameter value, and

comparing, by the processing circuitry, the zonal ranking value to the threshold value, the segment of the digital document being classified as a handwritten text zone when the zonal ranking value satisfies the threshold value.

11. A non-transitory computer-readable medium storing instructions which when executed by a computer, cause the computer to perform a method of recognizing a character in a digital document, the method comprising:

classifying a segment of the digital document as including text;

calculating at least one parameter value associated with the classified segment of the digital document;

determining, based on the calculated at least one parameter value, a zonal parameter value;

classifying the segment of the digital document as a handwritten text zone or as a printed text zone based on the determined zonal parameter value and a threshold value, the threshold value being based on a selection of an intersection of a handwritten text distribution profile and a printed text distribution profile, each of the handwritten text distribution profile and the printed text distribution profile being associated with a zonal parameter corresponding to the determined zonal parameter value; and

generating, based on the classifying, a modified version of the digital document.

12. The non-transitory computer-readable medium of claim 11 , further comprising

performing, when the segment is classified as a handwritten text zone, handwritten character recognition on the segment to recognize the handwritten text, and

performing, when the segment is classified as a printed text zone, printed character recognition on the segment to recognize the printed text.

13. The non-transitory computer-readable medium of claim 11 , wherein the determined zonal parameter value is an object density value calculated by

multiplying a segment ratio by a segment height, the segment ratio being a ratio of a number of objects in the segment to a segment width.

14. The non-transitory computer-readable medium of claim 11 , wherein the generating the modified version of the digital document includes

assigning, when the segment is classified as a handwritten text zone, a handwritten text identifier to the segment, and

assigning, when the segment is classified as a printed text zone, a printed text identifier to the segment.

15. The non-transitory computer-readable medium of claim 12 , further comprising

generating, as the modified version of the digital document, a first selectable version of the digital document, wherein the first selectable version of the digital document includes the recognized handwritten text within the segment and the recognized printed text within the segment.

16. The non-transitory computer-readable medium of claim 11 , further comprising

obtaining the threshold value from a reference table comprising threshold values based on a type of the zonal parameter value, each of the threshold values being based on a corresponding handwritten text distribution profile and corresponding printed text distribution profile from a database,

the corresponding handwritten text distribution profile being based on a histogram associated with text zones labeled as handwritten text, and

the corresponding printed text distribution profile being based on a histogram associated with text zones labeled as printed text.

17. The non-transitory computer-readable medium of claim 16 , wherein each of the histograms are based on a comparison of a parameter value for an object within a labeled text zone and a corresponding ranking for the object, the corresponding ranking being based on the parameter value for the object and parameter values for each other object within the labeled text zone.

18. The non-transitory computer-readable medium of claim 11 , wherein the selection of the intersection of the handwritten text distribution profile and the printed text distribution profile includes

maximizing an area under a curve for each of the handwritten text distribution profile and the printed text distribution profile, the threshold value being a value above which the segment is likely to be handwritten text.

19. The non-transitory computer-readable medium of claim 11 , wherein the classifying includes

calculating a zonal ranking value based on the determined zonal parameter value and ranking values associated with each of the calculated at least one parameter value, and

comparing the zonal ranking value to the threshold value, the segment of the digital document being classified as a handwritten text zone when the zonal ranking value satisfies the threshold value.

20. An apparatus for recognizing a character in a digital document, comprising:

processing circuitry configured to

classify a segment of the digital document as including text,

calculate at least one parameter value associated with the classified segment of the digital document,

determine, based on the calculated at least one parameter value, a zonal parameter value,

classify the segment of the digital document as a handwritten text zone or as a printed text zone based on the determined zonal parameter value and a threshold value, the threshold value being based on a selection of an intersection of a handwritten text distribution profile and a printed text distribution profile, each of the handwritten text distribution profile and the printed text distribution profile being associated with a zonal parameter corresponding to the determined zonal parameter value, and

generate a modified version of the digital document based on the segment classification.