Speech and Vision Lab

  • Increase font size
  • Default font size
  • Decrease font size
Home Publications
Unsupervised texture classification using vector quantization and deterministic relaxation neural network
Research Area: Uncategorized Year: 1997
Type of Publication: Article Keywords: Hopfield neural nets, feature extraction, filtering theory, image classification, image coding, image texture, neural net architecture, probability, transform coding, two-dimensional digital filters, unsupervised learning, vector quantisation, wavelet tra
Authors: P.P. Raghu, R. Poongodi, B. Yegnanarayana  
This paper describes the use of a neural network architecture for classifying textured images in an unsupervised manner using image-specific constraints. The texture features are extracted by using two-dimensional (2-D) Gabor filters arranged as a set of wavelet bases. The classification model comprises feature quantization, partition, and competition processes. The feature quantization process uses a vector quantizer to quantize the features into codevectors, where the probability of grouping the vectors is modeled as Gibbs distribution. A set of label constraints for each pixel in the image are provided by the partition and competition processes. An energy function corresponding to the a posteriori probability is derived from these processes, and a neural network is used to represent this energy function. The state of the network and the codevectors of the vector quantizer are iteratively adjusted using a deterministic relaxation procedure until a stable state is reached. The final equilibrium state of the vector quantizer gives a classification of the textured image. A cluster validity measure based on modified Hubert index is used to determine the optimal number of texture classes in the image
Digital version