Automatic recognition of characters on structured background by combination of the models of the background and of the characters

Number of patents in Portfolio can not be more than 2000

United States of America Patent

PATENT NO 6690824
SERIAL NO

09596546

Stats

ATTORNEY / AGENT: (SPONSORED)

Importance

Loading Importance Indicators... loading....

Abstract

See full text

The invention relates to a process for obtaining by electronic means the automatic recognition of characters, even if printed in a variable position on a highly contrasted structured background drawing. The process consists in firstly producing a model of the background, obtained by capturing with an electronic camera the images of several samples, on which images there is only the background. Thereafter, the models of the symbols (for example alphanumeric characters) to be recognized are produced, either capturing the images of a set of characters printed on white background, or using the commercially available computer files of the characters of the chosen fonts. At the time of recognition, the position of each of the characters to be recognized is firstly measured with respect to the position of the printing of the drawing of the background. Each character to be recognized is thereafter compared with models obtained by combining the models of the symbols with the model of the background, with the same relative position of the unknown character. Recognition of the character together with background is therefore achieved by comparison with models of the characters combined with the same background in the same position, using any well-known recognition techniques.

Loading the Abstract Image... loading....

First Claim

See full text

Family

Loading Family data... loading....

Patent Owner(s)

Patent OwnerAddress
KBA-NOTASYS SA1000 LAUSANNE 22

International Classification(s)

  • [Classification Symbol]
  • [Patents Count]

Inventor(s)

Inventor Name Address # of filed Patents Total Citations
Stringa, Luigi Monaco, IT 6 223

Cited Art Landscape

Load Citation

Patent Citation Ranking

Forward Cite Landscape

Load Citation