作者: Gregory J. Martin , Robert Y. Chen , James A. Mason , John F. Cook
DOI:
关键词:
摘要: A character recognition method comprising the following steps: (1) acquiring a two dimensional array of pixels, (2) locating an unknown in array, (3) computing weighted correlation coefficients between and trained set characters (i.e. font), (4) recognizing as with highest coefficient above threshold. The weights calculations are adjusted to place more emphasis on those areas that distinguishes it from all other training set. for optimally adjusting these is described herein.