Multi-module minimization neural network for motion-based scene segmentation

Yen Kuang Chen, Sun-Yuan Kung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

A competitive learning network, called Multi-Module Minimization (MMM) Neural Network, is proposed for unsupervised classification. The objective is to provide a general framework to divide a set of input patterns into a number of clusters such that the patterns of the same cluster exhibit any pre-specified similarity measure (i.e. not limited only to RBF). As an example of non-RBF measure, a motion-based segmentation problem is considered. Simulation results demonstrate that the MMM neural network does capture different motions and yield fairly accurate segmentation and motion-compensated frames.

Original languageEnglish (US)
Title of host publicationNeural Networks for Signal Processing
Pages371-380
Number of pages10
StatePublished - Jan 1 1996
EventProceedings of the 1996 IEEE Signal Processing Society Workshop - Kyota, Jpn
Duration: Sep 4 1996Sep 6 1996

Other

OtherProceedings of the 1996 IEEE Signal Processing Society Workshop
CityKyota, Jpn
Period9/4/969/6/96

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Signal Processing
  • Software

Fingerprint Dive into the research topics of 'Multi-module minimization neural network for motion-based scene segmentation'. Together they form a unique fingerprint.

  • Cite this

    Chen, Y. K., & Kung, S-Y. (1996). Multi-module minimization neural network for motion-based scene segmentation. In Neural Networks for Signal Processing (pp. 371-380)