A general purpose model for image operations based on multilayer perceptrons

Jenlong Moh, Frank Y. Shih

Research output: Contribution to journalArticlepeer-review

9 Scopus citations


In this paper, we investigate the use of multilayer perceptrons with recurrent connections as the general purpose modules for image processing in parallel architectures. The networks are trained to carry out classification rules in image transformation. The training patterns can be derived from user-defined transformations or from loading the pair of a sample image and its target image when the prior knowledge of transformations is unknown. Applications of our model include image smoothing, enhancement, edge detection, noise removal, morphological operations, image filtering, etc. With a number of stages stacked up together we are able to apply a series of operations on the image. That means, by providing various sets of training patterns the system can adapt itself to the concatenated transformation. Besides, recurrent connections from output of the last stage to input of the first stage allow a repeated sequence of operations to be used.

Original languageEnglish (US)
Pages (from-to)1083-1090
Number of pages8
JournalPattern Recognition
Issue number7
StatePublished - Jul 1995

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


  • Error back-propagation
  • Mathematical morphology
  • Multilayer perceptron
  • Parallel image processing
  • Recurrent neural networks


Dive into the research topics of 'A general purpose model for image operations based on multilayer perceptrons'. Together they form a unique fingerprint.

Cite this