Share Email Print

Proceedings Paper

Image segmentation benchmark for evaluation of vision systems
Author(s): Edwige E. Pissaloux
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper proposes a benchmark for vision systems performance prediction, estimation and evaluation. The benchmark is based upon image cooperative edge-region segmentation task. It is composed by three algorithms: multi-thresholded image connected component labelling, image region segmentation and data reorganization. Formalized algorithms are given and their few implementation details on SIMD and MIMD computers are discussed. Benchmark result analysis and architectural implications for an efficient support of vision application are proposed as well.

Paper Details

Date Published: 21 March 2000
PDF: 12 pages
Proc. SPIE 3966, Machine Vision Applications in Industrial Inspection VIII, (21 March 2000); doi: 10.1117/12.380058
Show Author Affiliations
Edwige E. Pissaloux, Univ. de Rouen (France) and Laboratoire de Robotique de Paris, CNRS (France) (France)

Published in SPIE Proceedings Vol. 3966:
Machine Vision Applications in Industrial Inspection VIII
Kenneth W. Tobin Jr.; John C. Stover, Editor(s)

© SPIE. Terms of Use
Back to Top