Patent · US Expired

Method and apparatus for recognizing images of documents and storing different types of information in different files

US6163623A · kind A · utility

15Cited by
4References
29Claims
0Family size

Assignee

Inventor

Key dates

Filing dateJul 26, 1995
Grant dateDec 19, 2000
Priority date
Expiry dateJul 26, 2015

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V30/40
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method and apparatus for processing images of a document containing characters, tables and figures. After the documents are scanned, the various areas including the character images, table images, and figure images are grouped in accordance with the type of image. Different file names are assigned to each of the character section, table section, and figures. A portion of the file names for each of the character images, table images, and figures may be the same in order to indicate that the characters, tables, and images belong to the same document. Extensions may be assigned to the file names indicating whether the file contains characters, tables, or figures. Further, a number may be stored to indicate the table number, figure number or character image number. If newspaper or magazine articles are scanned, the various sections of the articles may be arranged automatically in order to make the information easier to utilize and to have an efficient use of the paper.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.