Scale space texture classification using combined classifiers with application to ultrasound tissue characterization

Texture is often considered as a repetitive pattern and the constructing: structure is known as texel. The granularity of a texture, i.e. the size of a texel, is different from one texture to another and hence inspiring us applying scale space techniques to texture classification. In this paper Gaussian kernels with different variances (sigma(2)) are convolved with the textures from Brodatz album to generate the textures in different scales. After some preprocessing and feature extraction using principal component analysis (PCA), the features are fed to a combined classifier for classification. The learning curves are used to evaluate the performance of the texture classifier system designed. The results of classification show that the scale space texture classification approach used can significantly improve the performance of the classification especially for small training set size. This is very important in applications where the training set data is limited. The application of this method to ultrasound liver tissue characterization for discrimination of normal liver from cirrhosis yields promising results.