Character recognition method using statistically weighted correlation
US5159644A · kind A · utility
Assignee
Inventors
Key dates
| Filing date | Aug 30, 1991 |
| Grant date | Oct 27, 1992 |
| Priority date | — |
| Expiry date | Aug 30, 2011 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F18/21
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A character recognition method comprising the following steps: (1) acquiring a two dimensional array of pixels, (2) locating an unknown character in the two dimensional array, (3) computing statistically weighted correlation coefficients between the unknown character and a trained set of characters (i.e. a font), (4) recognizing the unknown character as the trained character with the highest correlation coefficient above a threshold. The weights in the correlation calculations are adjusted to place more emphasis on those areas of a character that exhibit less noise and less emphasis on those areas of the character that exhibit more noise. A method for determining and using these weights is described herein.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.