Karhunen-Loeve Transform: An Exercise in Simple Image-Processing Parallel Pipelines

Authors

  • M. Fleury
  • A. C. Downton
  • A. F. Clark

Abstract

Practical parallelizations of multi-phased low-level image-processing algorithms may require working in batch mode. The features of a new processing model, employing a pipeline of processor farms, are described. A simple exemplar, the Karhunen-Loeve transform, is prototyped on a network of processors running a real-time operating system. The design trade-offs for this and similar algorithms are indicated. In the manner of co-design, eventual implementation on large- and fine-grained hardware is considered.  The chosen exemplar is shown to have some features, such as strict sequencing and unbalanced processing phases, which militate against a comfortable implementation.

Downloads

Download data is not yet available.

Published

2012-03-01

How to Cite

Fleury, M., Downton, A. C., & Clark, A. F. (2012). Karhunen-Loeve Transform: An Exercise in Simple Image-Processing Parallel Pipelines. Computing and Informatics, 19(1), 19–36. Retrieved from http://147.213.75.17/ojs/index.php/cai/article/view/551