Grids enable the creation of virtual laboratories for the collaborative use of sophisticated instruments producing large amount of data that have to be processed in order to extract knowledge. In this context, a very important task is OF related with image processing, since most of the data are images that have to be adequately analyzed. We present a Grid-aware version of the Parallel IMAGE processing GEnoa library (PIMA(GE)(2) Lib). The major features of our approach are the preservation of the ease in the development of parallel image processing applications and the possibility to efficiently exploit the Grid resources for their executions. The resulting tool, called PIMA(GE)2 Grid, is based on the Grid Service technology; from the user point of view, it acts as an intermediate layer between Grid resources and parallel image processing applications. PIMA(GE)2 Grid represents a feasible solution to exploit multiple and computationally intensive image processing applications in a virtual laboratory.
THE USE OF PIMA(GE)(2) LIBRARY FOR EFFICIENT IMAGE PROCESSING IN A GRID ENVIRONMENT
Clematis A;D'Agostino D;Galizia A
2009
Abstract
Grids enable the creation of virtual laboratories for the collaborative use of sophisticated instruments producing large amount of data that have to be processed in order to extract knowledge. In this context, a very important task is OF related with image processing, since most of the data are images that have to be adequately analyzed. We present a Grid-aware version of the Parallel IMAGE processing GEnoa library (PIMA(GE)(2) Lib). The major features of our approach are the preservation of the ease in the development of parallel image processing applications and the possibility to efficiently exploit the Grid resources for their executions. The resulting tool, called PIMA(GE)2 Grid, is based on the Grid Service technology; from the user point of view, it acts as an intermediate layer between Grid resources and parallel image processing applications. PIMA(GE)2 Grid represents a feasible solution to exploit multiple and computationally intensive image processing applications in a virtual laboratory.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
