Premium
Character recognition via critical points
Author(s) -
Shchepin E. V.,
Nepomnyashchii G. M.
Publication year - 1991
Publication title -
international journal of imaging systems and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.359
H-Index - 47
eISSN - 1098-1098
pISSN - 0899-9457
DOI - 10.1002/ima.1850030306
Subject(s) - smoothing , computer science , character (mathematics) , character recognition , graph , coding (social sciences) , artificial intelligence , plane (geometry) , algorithm , pattern recognition (psychology) , theoretical computer science , computer vision , image (mathematics) , mathematics , geometry , statistics
A new approach to image coding, based on ordinate‐preserving plane homoeomorphism invariants, is presented. A critical‐points graph bearing full information on these invariants is outlined. Appropriate noise‐smoothing techniques are developed. The proposed method has been implemented and tested with a new optical character recognition program, CRIPT.