University of Khartoum

Image Processing and Computer Vision: A Comparison between CPU and FPGA

Image Processing and Computer Vision: A Comparison between CPU and FPGA

Show full item record

Title: Image Processing and Computer Vision: A Comparison between CPU and FPGA
Author: Osman, Ahmed Mustafa Elsiddig
Abstract: Computer vision and image processing are used in many real world applications. Many of these applications require real time data processing. To improve the real time performance many researches were performed to improve either the algorithms used or the hardware that runs the algorithms. The main deal is to choose between the general purpose architectures flexibility (i.e. CPUs) or purpose built architectures efficiency (FPGAs). The aim of this thesis is to find a suitable tool to implement image processing and computer vision algorithms in an FPGA and compare between the CPU and the FPGA’s performance in terms of computational time, resources and accuracy. These Objectives were achieved and a comparison between the CPU and the FPGA was made. Also, a SIFT descriptor model was developed using MATLAB/Simulink and was implemented in a FPGA Xilinx Virtex 6 board. Multiple images were used as inputs for the algorithms under consideration and the results were obtained. The FPGA gave a far better performance compared to the CPU under specific configurations. A discussion was made to illustrate the reasons behind these results and improvements were suggested to increase FPGA’s performance in image processing and computer vision applications and future work was recommended.
URI: http://khartoumspace.uofk.edu/123456789/25778
Date: 2017


Files in this item

Files Size Format View

This item appears in the following Collection(s)

Show full item record

Share

Search DSpace


Browse

My Account