Comparison of PCT and Fisher Discriminant Analysis for Texture Feature Selection

Feature selection methods are useful to obtain an optimal set from a larger set thereby eliminating redundancy in feature sets. In this paper, the popular methods of principal component transform and Fisher discriminant analysis are compared for texture feature selection. These features are constituted by wavelet features. The selection processes are judged on using the classification rate of a particular classifier as a criterion. The Euclidean distance measure is used as the criterion for efficiency. The results show that fisher method performs better than principal component transform. Results of computation time are also presented.