Claims:WE CLAIM
1. A method for performing optical character recognition on an image including a plurality of printed characters, the method comprising:
defining, by an optical character recognition unit, one or more opcodes and direction pointers associated with the plurality of printed characters of a language and a font type, wherein each of the one or more opcodes has an associated unique opcode characterization value;
creating, by the optical character recognition unit, a binary tree comprising a plurality of nodes, wherein each node of the plurality of nodes is assigned the unique opcode characterization value, associated with each of the one or more opcodes, and the direction pointers comprising a first pointer value and a second pointer value;
retrieving, by the optical character recognition unit, a set of operations associated with the unique opcode characterization value assigned to each of the plurality of nodes; and
navigating, by the optical character recognition unit, the binary tree from a root node to a leaf node based on the set of operations, the first pointer value, and the second pointer value until the leaf node from the plurality of nodes is reached, wherein each of the leaf nodes represent one or more unique pre-defined features associated with a unique printed character from the plurality of printed characters.
2. The method of claim 1, further comprising receiving a user input that comprises the language and the font type associated with the plurality of printed characters.
3. The method of claim 1, further comprising performing one or more pre-processing operations on the image including the plurality of printed characters, wherein the one or more pre-processing operations comprise at least one of a skew correction, a line segmentation, a word segmentation, or a character segmentation.
4. The method of claim 1, further comprising grouping the plurality of printed characters into a plurality of buckets based on one or more common pre-defined features associated with each of the plurality of printed characters, wherein each of the plurality of buckets is associated with each of the plurality of nodes.
5. The method of claim 1, further comprising displaying each of the recognized unique printed character from the plurality of printed characters.
6. The method of claim 1, wherein the one or more opcodes are generated based on one or more pre-defined features associated with each of the plurality of printed characters.
7. The method of claim 6, wherein the one or more pre-defined features associated with each of the plurality of printed characters are based on one or more geometric features comprising slope, curvature, vertical/horizontal line, a square, or a circle.
8. The method of claim 1, wherein each of the plurality of printed characters are provided as input to the root node of the binary tree one at a time.
9. The method of claim 1, wherein the first pointer value and the second pointer value of each of the leaf nodes is NULL and the one or more opcodes associated with each of the leaf nodes is invalid.
10. The method of claim 1, wherein the navigation is performed for each of the plurality of printed characters.
11. An application server to perform optical character recognition on an image including a plurality of printed characters, the application server comprising:
a processor; and
a memory communicatively coupled to the processor, wherein the memory stores processor instructions, which, on execution, causes the processor to:
define one or more opcodes and direction pointers associated with the plurality of printed characters of a language and a font type, wherein each of the one or more opcodes has an associated unique opcode characterization value;
create a binary tree comprising a plurality of nodes, wherein each node of the plurality of nodes is assigned the unique opcode characterization value, associated with each of the one or more opcodes, and the direction pointers comprising a first pointer value and a second pointer value;
retrieve a set of operations associated with the unique opcode characterization value assigned to each of the plurality of nodes; and
navigate the binary tree from a root node to a leaf node based on the set of operations, the first pointer value, and the second pointer value until the leaf node from the plurality of nodes is reached, wherein each of the leaf nodes represent one or more unique pre-defined features associated with a unique printed character from the plurality of printed characters.
12. The application server of claim 11, wherein the processor is further configured to receive a user input that comprises the language and the font type associated with the plurality of printed characters
13. The application server of claim 11, wherein the processor is further configured to perform one or more pre-processing operations on the image including the plurality of printed characters, wherein the one or more pre-processing operations comprise at least one of a skew correction, a line segmentation, a word segmentation, or a character segmentation.
14. The application server of claim 11, wherein the processor is further configured to group the plurality of printed characters into a plurality of buckets based on one or more common pre-defined features associated with each of the plurality of printed characters, wherein each of the plurality of buckets is associated with each of the plurality of nodes.
15. The application server of claim 11, wherein the processor is further configured to display each of the recognized unique printed character from the plurality of printed characters.
16. The application server of claim 11, wherein the one or more opcodes are generated based on one or more pre-defined features associated with each of the plurality of printed characters.
17. The application server of claim 16, wherein the one or more pre-defined features associated with each of the plurality of printed characters are based on one or more geometric features comprising slope, curvature, vertical/horizontal line, a square, or a circle.
18. The application server of claim 11, wherein each of the plurality of printed characters are provided as input to the root node of the binary tree one at a time.
19. The application server of claim 11, wherein the first pointer value and the second pointer value of each of the leaf nodes is NULL and the one or more opcodes associated with each of the leaf nodes is invalid.

Dated this September 30, 2016

R Ramya Rao
Of K&S Partners
Agent for the Applicant
, Description:TECHNICAL FIELD
The present subject matter is related, in general to character recognition systems, and more particularly, but not exclusively to a method and a system for optical character recognition of a plurality of printed characters.