A Low-Cost Vector Processor for Speeding-Up Compute-Intensive Image Processing
Abstract
The advent of affordable add-on vector processing boards for standard workstations, complemented by mathematical/statistical libraries, is beginning to impact compute-intensive tasks such as image processing. A case in point is the restoration of distorted images from the Hubble Space Telescope. A low-cost vector processor implementation of the standard Tarasko-Richardson-Lucy (TRL) restoration algorithm is presented which is seamlessly interfaced to a commercial, memory-based image processing system.
- Publication:
-
Astronomical Data Analysis Software and Systems II
- Pub Date:
- January 1993
- Bibcode:
- 1993ASPC...52..570A