Fuzzy Logic-Based Image Processing Using Graphics Processor Units

Abstract This paper introduces a parallelization of fuzzy logicbased image processing using Graphics Processor Units (GPUs). Using an NVIDIA 8800 Ultra, a 126 time speed improvement can be made to fuzzy edge extraction making its processing real-time. The GPU can process approximately 42 frames per second at 640x480 image resolution, thus 307,200 inference processes per frame. With a computational speed improvement of over two orders of magnitude, more time can be allocated to higher level computer vision algorithms. This GPU solution is described using NVIDIAs Compute Unified Device Architecture (CUDA). Keywords- Graphics Processor Units, Fuzzy Image Processing, Fuzzy Edge Extraction, Compute Unified Device Architecture

• Type: Journal
• Year: 2009
• Where: EUSFLAT
• Authors: Robert H. Luke III, Derek Anderson, James M. Keller, Simon Coupland
• Keywords: Edge Extraction, EUSFLAT 2009, Fuzzy Logic, Fuzzy Logicbased Image, Graphics Processor Units