A method for inductivelearningof primitive features is proposed. Primitive features are well investigated and they are extracted in bottom-up manner fiom training set of patterns ...
Multi-stream hidden Markov models (HMMs) have recently been very successful in audio-visual speech recognition, where the audio and visual streams are fused at the final decision...
In this paper, a novel face recognition method based on Gabor-wavelet and linear discriminant analysis (LDA) is proposed. Given training face images, discriminant vectors are compu...
Yanwei Pang, Lei Zhang, Mingjing Li, Zhengkai Liu,...
This paper presents a novel texture segmentation method using Bayesian estimation and neural networks. Multi-scale wavelet coefficients and the context information extracted from n...
Weighted graph matching is a good way to align a pair of shapes represented by a set of descriptive local features; the set of correspondences produced by the minimum cost matchin...