Home | Links | Contact Us | More About Intellectual Property | Bookmark
Search patents:
Home Finance Image-recognition-through-localized-interpretation

 Image recognition through localized interpretation

Details
Inventors: Krtolica, Radovan V.; Melen, Roger D.;
Assignee: Canon Kabushiki Kaisha (Tokyo, JP)
Primary Examiner: Au; Amelia
Assistant Examiner: Miller; Martin
Attorney, Agent or Firm: Fenwick & West LLP

A printed or handwritten character image is recognized by training (301) a plurality of lookup tables with a set of known referent characters; obtaining (302) a bitmap of a character image to be recognized; mapping (303) the bitmap onto a standardized character matrix; partitioning (304) the matrix into a plurality of sub-matrices; (305) determining a set of candidates for each sub-matrix; and selecting (306) a preferred candidate from among the set of candidates responsive to at least one pre-defined selection criterion. The invention is implemented by means of a scanner (102), a character mapper (104), a matrix partitioner (106), a candidate set builder (108), and a character selector (110).

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Referring now to FIG.
1, there is shown a apparatus 100 for recognizing the pattern of a Character in accordance with the present invention.
Briefly, apparatus 100 comprises five major functional blocks.
Scanner 102 obtains a two-dimensional array of pixel values representing the character to be recognized.
Character mapper 104 maps the scanned image onto a character matrix according to pixel density or connectivity.
Matrix partitioner 106 partitions the character matrix into a plurality of sub-matrices.
Candidate set builder 108 uses a binary representation of each sub-matrix as an index into a lookup table in order to determine the set of possible candidate characters.
Character selector 110 selects a preferred candidate character based on at least one pre-defined selection criterion.
Referring now to FIG.
2, there is shown a physical block diagram of system 100 indicating components used to implement the functionality of blocks 102, 104, 106, 108, and 110 shown in FIG.
1.
In a preferred embodiment, scanner 102 is implemented by a scanning device 202, for example, an "HP ScanJet IIc" model digital scanner from Hewlett Packard Co.
, which provides a resolution of 400 dots (pixels) per inch, each pixel being quantized with an eight-bit gray scale resolution.
Character mapper 104, matrix partitioner 106, candidate set builder 108, and character selector 110 are each implemented by means of a microprocessor 204, in conjunction with memory 206, storage device 208, and output device 210, all of which are coupled to data bus 212.
In a preferred embodiment, a conventional IBM PC.
RTM.
or compatible is used.
Thus, microprocessor 204 could comprise a 200 MHz or faster Intel.
RTM.
Pentium.
RTM.
processor.
Memory 206 could be implemented by any combination of RAM, ROM, EPROM, or other memory circuitry.
Storage device 208 could include a hard disk, CD-ROM, magneto-optical drive, DVD, flash memory, or other mass storage device.
Output device 210 could comprise a CRT display, a printer, a network adapter, a modem, or the like



Related patents

0.024

Archive: All patents - Links

Copyright (c)2006 Eipa-patents.org - All rights reserved