METHOD AND SYSTEM FOR PREPROCESSING IMAGE FOR OPTICAL CHARACTER RECOGNITION

PROBLEM TO BE SOLVED: To provide a method and system for preprocessing an image including a plurality of columns, or regions, of text.SOLUTION: A plurality of components associated with text is determined. On determining the plurality of components, a line height and a column spacing are determined...

Full description

Saved in:
Bibliographic Details
Main Authors MOHAMED SULEIMAN KHORSHLD, HUSSEIN KHALID ALI O'MALLEY
Format Patent
LanguageEnglish
Published 21.11.2013
Subjects
CALCULATING
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Online AccessGet full text

Cover

More Information
Summary:PROBLEM TO BE SOLVED: To provide a method and system for preprocessing an image including a plurality of columns, or regions, of text.SOLUTION: A plurality of components associated with text is determined. On determining the plurality of components, a line height and a column spacing are determined for the components. The components are then associated with a column on the basis of the line height and the column spacing. A set of characteristic parameters are calculated for each column and the plurality of components of each column are merged based on the characteristic parameters to form sub-words and words. A first plurality of words and/or sub-words are merged and processed as a first region and a second plurality of words and/or sub-words are merged and processed as a second region. At least a portion of the second region vertically overlaps at least a portion of the first region.
Bibliography:Application Number: JP20130084694