Non-saturated binary image learning and recognition using the ratio-memory cellular neural network (RMCNN)

Chung-Yu Wu, Chieh Yu Hsieh, Sheng Hao Chen, Brian Che Yuan Hsieh, Cheng Ruei Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

In this paper, cellular neural network with ratio memory is proposed for non-saturated binary image processing. The Hebbien learning rule will be used to learn the weight of template A. The RMCNN system can recognize one non-saturated binary image and remove most ofthe noise added to the image pattern during the recognition period. The behavior of recognizing non-saturated binary images will be proved by mathematics equations. The effect will be simulated by Matlab software. With the method for non-saturated binary image processing, this theory can be easily implemented in hardware.

Original languageEnglish
Title of host publicationProceedings of the 7th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA 2002
EditorsRonald Tetzlaff
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages624-629
Number of pages6
ISBN (Electronic)981238121X
DOIs
StatePublished - 1 Jan 2002
Event7th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA 2002 - Frankfurt, Germany
Duration: 22 Jul 200224 Jul 2002

Publication series

NameProceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications
Volume2002-January

Conference

Conference7th IEEE International Workshop on Cellular Neural Networks and their Applications, CNNA 2002
CountryGermany
CityFrankfurt
Period22/07/0224/07/02

Keywords

  • Capacitors
  • Cellular neural networks
  • Equations
  • Image analysis
  • Image processing
  • Image recognition
  • Leakage current
  • Mathematics
  • Very large scale integration

Fingerprint Dive into the research topics of 'Non-saturated binary image learning and recognition using the ratio-memory cellular neural network (RMCNN)'. Together they form a unique fingerprint.

Cite this