GPGPU Volume Classification using SimpleOpenCL
Dept. Matematica Aplicada i Analisi, Universitat de Barcelona, Spain
VI CVC Workshop on the progress of Research & Development (CVCR&D2011), pp. 136-141, 2011
@article{amoros2011gpgpu,
title={GPGPU Volume Classification using SimpleOpenCL},
author={Amoros, O. and Escalera, S. and Puig, A. and Salam{‘o}, M.},
year={2011}
}
In volume visualization, the definition of the regions of interest is inherently an iterative trialand-error process finding out the best parameters to classify and render the final image. In this work, we present a general framework for training multi-class classifiers using Error-Correcting Output Codes. Moreover, we propose a GPGPU parallelization system using SimpleOpenCL, an OpenSource library we created to make easier the use of OpenCL. Results show accurate classification results as well as good speed ups.
November 29, 2011 by hgpu
