A Method of Supervised Discrimination of Textures Based on Serial Statistical Tests
It is presented a new type of learning textures recognition algorithms based on serial statistical tests. It is assumed that a texture can be formally represented by a multi-component random vector whose probabilistic characteristics are, in general, a priori unknown. Discrimination of textures is equivalent to a discrimination of random vectors of different but a priori unknown statistical properties. For this purpose non-parametric statistical tests based on serial statistics are used. Construction of serial statistics needs a linear ordering of multi-dimensional observation space. The method is illustrated by numerical examples.
Unable to display preview. Download preview PDF.
- 1.Bruno A., Collorec R., Bezy-Wendling J., et al. (1997). Texture Analysis in Medical Imaging. In: Roux C., Coatrieux J.-L. (eds) Contemporary Perspectives in Three-Dimensional Biomedical Imaging. IOS Press, Amsterdam: 133–164.Google Scholar
- 2.Kulikowski J.L., Wierzbicka D. (2004). Texture Analysis Based on Application of Non-Parametric Serial Statistical Tests. Biocybernetics and Biomedical Engineering vol. 24 No 2: 27–39.Google Scholar
- 3.Runyon R.P. (1977). Nonparametric Statistics. A Contemporary Approach. Addison-Wesley Publishing Company, Reading, Mass., USA.Google Scholar