Lipreading by locality discriminant graph

Yun Fu, Xi Zhou, Ming Liu, Mark Hasegawa-Johnson, Thomas S. Huang

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


The major problem in building a good lipreading system is to extract effective visual features from the enormous quantity of video sequences data. For appearance-based feature analysis in lipreading, classical methods, e.g. DCT, PCA and LDA, are usually applied to dimensionality reduction. We present a new pattern classification algorithm, called Locality Discriminant Graph (LDG), and develop a novel lipreading framework to successfully apply LDG to the problem. LDG takes the advantages of both manifold learning and Fisher criteria to seek the linear embedding which preserves the local neighborhood affinity within same class while discriminating the neighborhood among different classes. The LDG embedding is computed in closed-form and tuned by the only open parameter of k-NN number. Experiments on AVICAR corpus provide evidence that the graph-based pattern classification methods can outperform classical ones for lipreading.

Original languageEnglish (US)
Title of host publication2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings
StatePublished - 2006
Event14th IEEE International Conference on Image Processing, ICIP 2007 - San Antonio, TX, United States
Duration: Sep 16 2007Sep 19 2007

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880


Other14th IEEE International Conference on Image Processing, ICIP 2007
Country/TerritoryUnited States
CitySan Antonio, TX


  • Audio-visual speech
  • Discrete cosine transform
  • Discriminant analysis
  • Graph embedding
  • Lipreading

ASJC Scopus subject areas

  • General Engineering


Dive into the research topics of 'Lipreading by locality discriminant graph'. Together they form a unique fingerprint.

Cite this