Research Article Open Access

Classical Flexible Lip Model Based Relative Weight Finder for Better Lip Reading Utilizing Multi Aspect Lip Geometry

B. Sujatha and T. Santhanam

Abstract

Problem statement: Deaf and dumb needs assistance from a technical box that takes movements of lips to identify the words. This technical article provided appropriate model implementation of flexible lip model for better visual lip reading system. Approach: From the frame sequence of words, Active Shape Model (ASM) based lip model provided local tracking and extraction of geometric lip-feature. Two geometric criteria define required geometric features and its variations in the sequence. Results: The feature established machine classification using Analytic Hierarchy Process (AHP), a relative weight finder. AHP presents weight vector to fuzzy classifier to decide the video frame sequence belonging to a respective word. Conclusion: The suggested model tested on a total of 5 different sample databases results in 83.2% accuracy over the other combinational algorithms.

Journal of Computer Science
Volume 6 No. 10, 2010, 1065-1069

DOI: https://doi.org/10.3844/jcssp.2010.1065.1069

Submitted On: 30 June 2010 Published On: 30 July 2010

How to Cite: Sujatha, B. & Santhanam, T. (2010). Classical Flexible Lip Model Based Relative Weight Finder for Better Lip Reading Utilizing Multi Aspect Lip Geometry. Journal of Computer Science, 6(10), 1065-1069. https://doi.org/10.3844/jcssp.2010.1065.1069

  • 2,841 Views
  • 2,048 Downloads
  • 0 Citations

Download

Keywords

  • Active shape model
  • analytic hierarchy process
  • fuzzy classifier