APPARATUS AND METHOD OF MATCHING SYMBOLS IN A TEXT IMAGE CODING AND DECODING SYSTEM

• US 20080175487A1
• Filed: 01/24/2007
• Published: 07/24/2008
• Est. Priority Date: 01/24/2007
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.), Purdue Research Foundation (The Trustees of Purdue University (d/b/a Purdue University))
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Yi, Jonghyon, Bouman, Charles A., Figuera, Maribel, OHK, Hyung-Soo
• Granted Patent: US 7,907,783 B2
• Time in Patent Office: Days
• US Class Current: 382/218
• CPC Class Codes: H04N 1/4115 involving the recognition of specific patterns, e.g. by symbol matching

Abstract

An apparatus of a text image coding and decoding system includes a matching unit to compute a first distance between a symbol of a text image with a reference symbol of a symbol dictionary, to determine whether the symbol matches with the reference symbol according to the first distance and a first reference, and to compute a second distance between the one of the symbols with the reference symbol if the symbol does not match matches with the reference symbol according to the first distance and the first reference, and to determine whether the symbol matches with the reference symbol according to the second distance and a second reference.

Claims

1. An apparatus usable in a text image coding and decoding system, comprising:

a matching unit to compute a first distance between a symbol of a text image with a reference symbol of a symbol dictionary, to determine whether the symbol matches with the reference symbol according to the first distance and a first reference, and to compute a second distance between the one of the symbols with the reference symbol if the symbol does not match matches with the reference symbol according to the first distance and the first reference, and to determine whether the symbol matches with the reference symbol according to the second distance and a second reference.

2. The apparatus of claim 1, wherein the matching unit comprises:

a first comparator to compare the first distance and the first reference to determine whether the symbol matches with the reference symbol; and

a second comparator to compare the second distance and the second reference to determine whether the symbol matches with the reference symbol.

3. The apparatus of claim 2, wherein a new reference symbol is created to correspond to the symbol and stored in the symbol dictionary when the symbol does not match with the reference symbol according to the comparison of the first controller

4. The apparatus of claim 3, wherein the matching unit determines that the symbol matches with the reference symbol according to the comparison of the second controller.

5. The apparatus of claim 4, wherein a new reference symbol is created to correspond to the symbol and stored in the symbol dictionary when the symbol does not match with the reference symbol according to the comparison of the second comparator.

6. The apparatus of claim 2, wherein:

the first reference comprises a first sub-reference and a second sub-reference;

the first comparator comprises a first sub-comparator to compare the first distance with the first sub-reference and a second sub-comparator to compare the first distance with the second sub-reference; and

the matching determines that the symbol matches with the reference symbol according to the comparisons of the first and second sub-comparators.

7. The apparatus of claim 5, wherein the second reference is different from the first and second sub-reference.

8. The apparatus of claim 5, wherein a new reference symbol is created to correspond to the symbol and stored in the symbol dictionary when the symbol does not match with the reference symbol according to the comparisons of the first and second sub-comparators.

9. The apparatus of claim 8, wherein the matching unit determines that the symbol matches with the reference symbol according to the comparison of the second controller.

10. The apparatus of claim 6, further comprising:

a coding unit to code the symbol according to information on the reference symbol and a location of the symbol of the text image when the symbol matches with the reference symbol according to the comparisons of the first and second sub-comparators and the second comparator.

11. The apparatus of claim 1, further comprising:

a decomposer to decompose image data to extract the text image having one or more symbols including the symbol; and

a coder to code the symbol with information on the reference symbol and a location of the symbol in the text image.

12. The apparatus of claim 11, further comprising:

a scanner to scan an object to generate a scanned image as the image data.

13. The apparatus of claim 1, further comprising:

a controller to control the symbol dictionary to create a new reference symbol when the symbol does not match with the reference symbol according to the first and second distances and the first and second references.

14. The apparatus of claim 1, wherein the first distance comprises an XOR distance.

15. The apparatus of claim 1, wherein the second distance comprises

a WXOR distance.

16. The apparatus of claim 1, wherein the second reference has a value greater that that of the first reference.

17. The apparatus of claim 1, wherein:

the first distance comprises an XOR distance;

the first distance comprises a WXOR distance; and

the matching unit compares the XOR distance with the first reference to determine whether to use the reference symbol to represent the symbol or to create the symbol as a new reference symbol.

28. The method of claim 1, further comprising:

decomposing image data to extract the text image having one or more symbols including the symbol; and

coding the symbol with information on the reference symbol and a location of the symbol in the text image.

29. The method of claim 28, further comprising:

scanning an object to generate a scanned image as the image data.

18. A method of a text image coding and decoding system, comprising:

computing a first distance between a symbol of a text image with a reference symbol of a symbol dictionary;

determining whether the symbol matches with the reference symbol according to the first distance and a first reference;

computing a second distance between the one of the symbols with the reference symbol if the symbol does not match matches with the reference symbol according to the first distance and the first reference; and

determining whether the symbol matches with the reference symbol according to the second distance and a second reference.

19. The method of claim 18, wherein the determining of whether the symbol matches with the symbol comprises:

comparing the first distance and the first reference in a first comparator to determine whether the symbol matches with the reference symbol; and

comparing the second distance and the second reference in a second comparator to determine whether the symbol matches with the reference symbol.

20. The method of claim 19, further comprising:

creating a new reference symbol to correspond to the symbol; and

storing the created reference symbol in the symbol dictionary when the symbol does not match with the reference symbol according to the comparison of the first controller

21. The method of claim 19, wherein the comparing of the first distance and the first reference comprises:

determining that the symbol matches with the reference symbol according to the comparison of the second controller.

22. The method of claim 21, further comprising:

creating a new reference symbol to correspond to the symbol; and

storing the created reference symbol in the symbol dictionary when the symbol does not match with the reference symbol according to the comparison of the second controller

23. The method of claim 19, wherein:

the first reference comprises a first sub-reference and a second sub-reference;

the first comparator comprises a first sub-comparator to compare the first distance with the first sub-reference and a second sub-comparator to compare the first distance with the second sub-reference; and

the determining of whether the symbol matches with the reference symbol comprises determining that the symbol matches with the reference symbol according to the comparisons of the first and second sub-comparators.

24. The method of claim 23, wherein the second reference is different from the first and second sub-reference.

25. The method of claim 23, further comprising:

creating a new reference symbol to correspond to the symbol; and

storing the created new reference symbol in the symbol dictionary when the symbol does not match with the reference symbol according to the comparisons of the first and second sub-comparators.

26. The method of claim 25, further comprising:

determining that the symbol matches with the reference symbol according to the comparison of the second controller.

27. The method of claim 26, further comprising:

coding the symbol according to information on the reference symbol and a location of the symbol of the text image when the symbol matches with the reference symbol according to the comparisons of the first and second sub-comparators and the second comparator.

30. The method of claim 18, further comprising:

controlling the symbol dictionary to create a new reference symbol when the symbol does not match with the reference symbol according to the first and second distances and the first and second references.

31. The method of claim 18, wherein the first distance comprises an XOR distance.

32. The method of claim 18, wherein the second distance comprises a

WXOR distance.

33. The method of claim 18, wherein the second reference has a value greater that that of the first reference.

34. The method of claim 18, wherein:

the first distance comprises an XOR distance;

the first distance comprises a WXOR distance; and

the determining of whether the symbol matches with the reference symbol comprises comparing the XOR distance with the first reference and comparing the WXOR distance with the second reference to determine whether to use the reference symbol to represent the symbol or to create the symbol as a new reference symbol.

35. A computer readable recording medium containing computer readable codes as a program to execute a method in a text image coding and decoding system, the method comprising:

computing a first distance between a symbol of a text image with a reference symbol of a symbol dictionary;

determining whether the symbol matches with the reference symbol according to the first distance and a first reference;

computing a second distance between the one of the symbols with the reference symbol if the symbol does not match matches with the reference symbol according to the first distance and the first reference; and

determining whether the symbol matches with the reference symbol according to the second distance and a second reference.

36. An apparatus usable in a text image coding and decoding system, comprising:

a matching unit to determine whether a symbol of input image data and a reference symbol of a dictionary match according to at least two different distances between the symbol and the reference symbol and at least two different reference values.

37. An apparatus usable in a text image coding and decoding system, comprising:

a matching unit to determine whether a symbol of input image data and a reference symbol of a dictionary match according to a coarse operation using a first distance and a first reference, and to determine whether the symbol of the input image data and the reference symbol of the dictionary match according to a fine operation using a second distance and a second reference when the symbol of the input image data and the reference symbol of the dictionary do not match match in the coarse operation.

38. A text image coding and decoding system, comprising:

an encoding apparatus to compute a first distance between a symbol of a text image with a reference symbol of a symbol dictionary, to determine whether the symbol matches with the reference symbol according to the first distance and a first reference, and to compute a second distance between the one of the symbols with the reference symbol if the symbol does not match matches with the reference symbol according to the first distance and the first reference, and to determine whether the symbol matches with the reference symbol according to the second distance and a second reference, so that an encoded signal is generated according to the determination using the first and second distances and the first and second references; and

a decoding apparatus to receive the encoded signal encoded according to the determination using the first and second distances and the first and second references, and to decode the received signal to reproduce the text image.

39. A method of a text image coding and decoding system, the method comprising:

computing a first distance between a symbol of a text image with a reference symbol of a symbol dictionary, to determine whether the symbol matches with the reference symbol according to the first distance and a first reference;

computing a second distance between the one of the symbols with the reference symbol if the symbol does not match matches with the reference symbol according to the first distance and the first reference;

determining whether the symbol matches with the reference symbol according to the second distance and a second reference, so that an encoded signal is generated according to the determination using the first and second distances and the first and second references;

decoding the encoded signal encoded according to the determination using the first and second distances and the first and second references to reproduce the text image.