Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Texture analysis using directional local extrema

Mavromatis S., Boï J. M., Bulot R., Sequeira J.

Machine Graphics and Vision

2004

Vol. 13, No. 3

289-302

In this paper, we propose a new formalism that enables to take into account textural features of the image in a very robust and selective way. This approach also permits visualization of these features so experts can efficiently supervise an image segmentation process based on texture analysis. The texture concept has been studied through different approaches. One of them is based on the notion of ordered local extrema and is very promising. Unfortunately, this approach does not take into account texture directionality; and the mathematical morphology formalism, on which it is based, does not enable extensions to this feature. This has led us to design a new formalism for texture representation capable of including directionality features. It produces a representation of texture-relevant features in the form of a surface z = f(x, y). The visualization of this surface gives experts sufficient information for discriminating different textures. We illustrate this approach by a set of results showing its interest in the frame of supervised image segmentation.

3D medical imaging: from 2D images to 3D models

Mavromatis S., Sequeira J.

Journal of Medical Informatics & Technologies

2002

Vol. 3

IP7--14

Up to the end of the 70's, Medical Imaging was mainly related to the study of planar data sets resulting from direct physical acquisitions (e.g. X-Ray radiographs). Then, the development of inverse methods associated with the increasing power of computers enabled the visualization and the analysis of human being cross-section images (e.g. CT scans, MRI): these images are the result of mathematical processes and do not present direct physical acquisitions. The visualization of these data in three-dimensional space was made possible by the use of a set of parallel cross-sections: the result was spectacular but not sufficient for further development, especially in the case of clinical applications. Such applications need the characterization of a geometrical model, e.g. for the capture of sophisticated geometrical parameters or to provide a mathematical support to mechanical simulations.