1
Optimizing the performance of an image processing algorithm using the PVM system | |
Author | Prapa Lertsirisathaporn |
Call Number | AIT Thesis no. CS-96-33 |
Subject(s) | Image processing Parallel processing (Electronic computers) |
Note | A thesis submitted in the partial fulfillment of the requirements for the degree of Master of Science. |
Publisher | Asian Institute of Technology |
Series Statement | Thesis ; no. CS-96-33 |
Abstract | Parallel processing is one of the most prom1smg solutions to the computing requirements of the future. A wide variety of applications demonstrate that solving problems with parallel algorithms is a significant approach for achieving faster processing. This is especially true in fields involved with intensive computation such as image processing. In this study, a two part method to enhance the speed of the image matching algorithm was developed and employed. First a parallel algorithm employing the divide-and-conquer technique was developed. Secondly, some forms of load balancing were considered in order to produce various task scheduling algorithms for distributing the tasks to processors. From implementation using the PVM (Parallel Virtual Machine) as an environment, it was found that faster processing depended on both the computational power of the machines forming the system and the policy for managing the system workload. |
Year | 1996 |
Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. CS-96-33 |
Type | Thesis |
School | School of Engineering and Technology (SET) |
Department | Department of Information and Communications Technologies (DICT) |
Academic Program/FoS | Computer Science (CS) |
Chairperson(s) | Yulu, Qi |
Examination Committee(s) | Stueart, Robert D.;Batanov, D. N. |
Scholarship Donor(s) | His Majesty King Bhumipol Adulyadej |
Degree | Thesis (M.Sc.) - Asian Institute of Technology, 1996 |