GPU vs FPGA: Example Application on White Light Interferometry

High performance image processing applications area challenging field when targeting embedded processing. Field programmable gate arrays (FPGA) receive a growing interest as implementation platforms, but these solutions have to compete with the state of the art in image processing, which is codefined by graphics processing units (GPU). This paper provides a case study which analyzes the potential of embedded or hybrid implementation on FPGA and GPU for image stack processing in a white light interferometry (WLI) application.