Abstract

Abstract
This article presents an image processing application for hand detection and tracking using the 4-connected skeleton of the segmentation mask. The system has been designed to be used with techniques of virtual reality to develop an interactive application for phantom limb pain reduction in therapeutic treatments. One of the major contributions is the design of a fast and accurate skeleton extractor, that has proven to be faster than those available in the literature. The skeleton allows the system to precisely detect the position of all the interest points of the hand (namely the fingers and the hand center). The system, composed of both the hand detector and tracker, and the virtual reality application, can work in real-time, allowing the patient to watch the virtual image of his own hand on a screen.

Abstract
This work describes results comparing the influence of surface treatments (grinding, and immersion in 20% HNO3 solutions and distilled water) on (i) the corrosion resistance in 10% FeCl3 and 3.5% NaCl solutions, and (ii) the composition of passive films of AISI 304 stainless steel. Both immersion in HNO3 and in distilled water cause an increase in Cr concentration in the films. The acid treatment produces a more intense attack in 10% FeCl3 and increases the corrosion rate in 3.5% NaCl, whereas immersion in distilled water produces no changes in corrosion behaviour. It is argued that the improvement in pit initiation resistance often observed with stainless steel after a HNO3 treatment is essentially associated with removal of sulphide inclusions, and not with Cr enrichment in the film.

Abstract
This paper describes an approach for integrating motion estimation and region clustering techniques with the purpose of obtaining precise multiple motion segmentation. Motivated by the good results obtained in static segmentation we propose a hybrid approach where motion segmentation is achieved within a region-based clustering approach taken the initial result of a spatial pre-segmentation and extended to include motion information. Motion vectors are first estimated with a multiscale variational method applied directly over the input images and then refined by incorporating segmentation results into a region-based warping scheme. The complete algorithm facilitates obtaining spatially continuous segmentation maps which are closely related to actual object boundaries. A comparative study is made with some of the best known motion segmentation algorithms. © 2008 Springer-Verlag Berlin Heidelberg.

Abstract

Abstract