Share Email Print
cover

Proceedings Paper

Designing observer trials for image fusion experiments with Latin Squares
Author(s): Eckart Michaelsen; Gabriele Schwan; Norbert Scherer-Negenborn
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Multisensor image fusion (e.g. IR with visual) is the process of combining relevant information from two or more images into a single image. The aim is to find an objective quality measure, which can be used in automatic applications, that correlates best with subjective observer trials. Not all combinations of image, algorithm, and test observer can be worked out. In this paper R. Fisher’s Design of Experiments approach based on Latin Squares is used for thinning out the number of experiments for each observer in such observer trials while preserving exactness and reliability of the result.

Paper Details

Date Published: 2 May 2017
PDF: 7 pages
Proc. SPIE 10200, Signal Processing, Sensor/Information Fusion, and Target Recognition XXVI, 1020015 (2 May 2017); doi: 10.1117/12.2262488
Show Author Affiliations
Eckart Michaelsen, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Gabriele Schwan, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)
Norbert Scherer-Negenborn, Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung (Germany)


Published in SPIE Proceedings Vol. 10200:
Signal Processing, Sensor/Information Fusion, and Target Recognition XXVI
Ivan Kadar, Editor(s)

© SPIE. Terms of Use
Back to Top