Application of affine-invariant Fourier descriptors to lipreading for audio-visual speech recognition.
Sabri GurbuzZekeriya TufekciEric K. PattersonJohn N. GowdyPublished in: ICASSP (2001)
Keyphrases
- affine invariant
- fourier descriptors
- affine transformation
- contour matching
- zernike moments
- multiscale
- shape analysis
- feature vectors
- object matching
- shape representation
- shape descriptors
- shape features
- audio visual speech recognition
- machine learning
- fourier transform
- convex hull
- curvature scale space
- object recognition