High-Speed Character Recognition Using a Dual Cellular Neural Network Architecture (CNND)

Tamás Szirányi, József Csicsvári

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

An effective new character recognition procedure implemented on a new type of hardware system is proposed. This procedure applied a new architecture, called CNND. This CNND contains one or more analog cellular neural Networks (CNN) and some digital logic, incorporating the advantages of the fast analog CNN signal processing and the fast and easy decision capability of digital logics. This paper shows that this CNND system can be used for recognition of multifont printed or handwritten characters. Implemented in hardware, the system could hit the 100 000 char/s recognition speed with a recognition rate of more than 95%. We show that the CNN results of pictures (maximum 40 * 40 pixels) of printed characters can be coded into about n * 20 bits (n = 2…6), so the coded results can be used to address memories of about 1 MB. The codes of CNN results of possible character pictures are used to address the memories while the memory contents are filled by the character categories. Prior to the hardware implementation the decision memories are filled by the results of recognition simulation for the possible pictures of each character-class in a filling procedure. In the memory filling procedure the simulated recognition uses a new random-type nearest neighbor (NN) method, which is ideal for the recent proposal of hardware applications. Recognition of handwritten characters is demonstrated in the same system with good recognition accuracy.

Original languageEnglish
Pages (from-to)223-231
Number of pages9
JournalIEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing
Volume40
Issue number3
DOIs
Publication statusPublished - Mar 1993

    Fingerprint

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this