Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: dyskryminacja tekstur

Sortuj według:

Ogranicz wyniki do:

Discrimination of biomedical textures based on logical similarity measure

Kulikowski J. L., Przytulska M., Wierzbicka D.

Journal of Medical Informatics & Technologies

2011

Vol. 17

89--95

The paper presents an approach to discrimination of textures in radiological images based on multi-aspect similarity measures composed of logical tests. There are formulated basis assumptions for similarity measures which can be composed by products of partial (single-aspect) similarity measures. On the basis of similarity measures -similarity classes are defined. Next, two types: strong and weak similarity measures are defined. It is shown that they make possible to define similarity measures based on quality objects properties as well as on their numerical parameters. As an example of application of the general concept discrimination of normal and ill (lesions affected) tissues is considered. It is illustrated by analysis of USG images of liver tissues for which morphological spectra and their statistical parameters have been calculated. It is shown that the differences between values of some pairs of corresponding parameters can be used to a construction of an effective algorithm of textures discrimination. This algorithm takes into consideration both, numerical features of the texture samples and some qualitative data concerning the patients. Conclusions are formulated at the end of the paper.

Choosing serial tests for discrimination of textures in biomedical images

Kulikowski J.K., Wierzbicka D.

Biocybernetics and Biomedical Engineering

2005

Vol. 25, no. 3

65-77

There are described several methods of the design of non-parametric serial statistical tests used for discrimination of textures. It is assumed that different textures are subjected to different but a priori unknown statistical distributions. The methods are based on linear ordering of multidimensional observation space. There are proposed several types of linear ordering based on the concepts of: reversible scanning, rosettes and permuted scale coding. The effectiveness of tests based on the proposed types of observation space ordering has been evaluated in a series of numerical experiments performed on real images of textures; the results of experiments are given in the paper with corresponding comments.