Apparatus and method of matching symbols in a text image coding and decoding system

• US 8,300,963 B2
• Filed: 02/02/2011
• Issued: 10/30/2012
• Est. Priority Date: 01/24/2007
• Status: Active Grant

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Ohk, Hyung-Soo, Yi, Jonghyon, Bouman, Charles A., Figuera, Maribel
• Primary Examiner(s): Alavi, Amir
• Application Number:
  US13/019,400
• Publication Number:
  US 20110158545A1
• Time in Patent Office: 636 Days
• Field of Search: 382/170, 382/176, 382/186, 382/187, 382/204, 382218-220, 382/222, 382/224, 382/232, 382/233, 382/243, 382/257, 382/276, 341/50, 341/51, 341/63, 341/67, 341/87, 341/106, 341/107, 345/173, 707/101, 715/855
• US Class Current: 382/232
• 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 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. 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 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.

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

using a computer to perform operations of;

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 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; and

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.

3. An apparatus 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 symbol with the reference symbol if the symbol does not match 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; and

a coder to generate an encoded signal according to the determination according to the first distance and the first reference and the determination according to the second distance and the second reference.

4. The apparatus of claim 3, 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.

5. The apparatus of claim 4, 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 unit determines that the symbol matches with the reference symbol according to the comparisons of the first and second sub-comparators.

6. The apparatus of claim 3, further comprising:

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

7. The apparatus of claim 3, further comprising:

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

8. The apparatus of claim 3, 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.

9. The apparatus of claim 3, wherein:

the first distance comprises an exclusive-OR (XOR) distance computed by counting a total number of pixels in a first error map that is generated via an XOR operation between the symbol and the reference symbol;

the second distance comprises a weighted exclusive-OR (WXOR) distance computed by counting a total number of weights of pixels in a second error map that is generated via an XOR operation between the symbol and the reference symbol with the weights assigned to the pixels in the second error map based on surrounding pixels; 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.