Wyniki wyszukiwania - BazTech

1

Multi-scale morphological modeling of a class of structural texture

Zaremba M. B., Palenichka R. M., Missaoui R.

Machine Graphics and Vision

|

2005

|

Vol. 14, No. 2

171-199

EN

Consistent and time-efficient modeling of textures is important both for realistic texture mapping in computer graphics and correct texture segmentation in computer vision. A large class of natural and artificial images is represented by the so-called structural textures, which contain visibly repetitive patterns. The multi-scale morphological modeling approach proposed in this paper explicitly describes shape and intensity parameters of structural textures. It is based on a cellular growth of a texture region by a sequential morphological generation of structural texture cells starting from a seed cell. Its main advantage is a concise shape representation for structural texture cells in the form of piecewise linear skeletons. Another advantage is a robust and computationally efficient estimation of texture parameters. The cell parameter estimation is based on the cell localization and adaptive segmentation using a multi-scale matched filter. The experiments reported in the paper are related to texture parameter estimation from synthetic and real textures as well as structural texture synthesis based on the estimated parameters.

2

Robust extraction of diagnostic features of lesions from medical radiographic image

Palenichka R. M., Belikova T. P., Ivasenko I.

Machine Graphics and Vision

|

2000

|

Vol. 9, No. 1/2

473-496

EN

In this apper, a robust structural approach to detection, object segmentation and calculation of object features in medical images of different modalities is proposed. The goal of the presented approach is the detection and feature-based objective description of objects of interest in medical images for diagnosis of lesions in a natural way and in accordance with the physician diagnostic feature used in the clinical practice. A set of local structural features was divided in two classes: propetrties of planar object shape and intensity distribution prperties. Experimental results of the extraction of diagnostic properties of lessions on lung images confirmed the advantage of the proposed method over the conventional approach of histogram-based segmentation.

3

Structure-adaptive evaluation of additive noise level in images

Palenichka R. M., Ivasenko I. B.

Machine Graphics and Vision

|

1998

|

Vol. 7, No. 1/2

281-290

EN

In the presented paper the problem of noise estimation is considered. The distinctive feature of the presented structural image model is the separate modeling of the object's planar shape as well as the image intensity function which is defined within the support regions of objects and for the background itself. For the intensity function model of the original image a piecewise polynominal model is assumed.