Direct tensor filter method for synthetic turbulent field generation

A Direct Tensor Filter Method for synthetic turbulent field generation is proposed in this paper. The method is a generalization of the Direct Anisotropic Filter Method. The turbulent velocity fields built on the base of this method provides more properties corresponding to real physical turbulent fields in comparison to ones obtained with help of DAF method.

Employing the Perona - Malik anisotropic filter for the problem of landing site detection

The article deals with implementing a Perona - Malik anisotropic smoothing filter on a GPU . The filter features a built-in edge detector and because of this is able to preserve meaningful contours during smoothing, but its computational complexity prevents using it in real-time mode. We used the scheme suggested as an element of a landing guide detection algorithm operating on a discrete digital image. The modified filter demonstrated high performance and processing quality during simulating an optical landing system for a copter-type unmanned aerial vehicle

SEGMENTATION OF BRAIN MRIs BY SUPPORT VECTOR MACHINE: DETECTION AND CHARACTERIZATION OF STROKES

The aim of our work is the segmentation of healthy and pathological brains to obtain brain structures and extract strokes. We used real magnetic resonance (MR) images weighted on diffusion. The brain was isolated, and the images were filtered by an anisotropic filter, and then segmented by support vector machines (SVMs). We first applied the method on synthetic images to test the performance of the algorithm and adjust the parameters. Then, we compared our results with those obtained by a cooperative approach proposed in a previous paper.