Title :
On the use of statistical tests on homomorphic filtered SAS images
Author :
Mandhouj, Imen ; Maussang, Frederic ; Solaiman, Basel ; Amiri, Hamid
Author_Institution :
CID Image & Inf. Process. Dept., Inst. Mines-Telecom, Brest, France
Abstract :
The principal objective of this paper is the statically study of pre-processed Synthetic Aperture Sonar (SAS) images. Different statistical tests are applied testing for distributional assumption in general and for normality in particular. Results of our statistical study are tested on a sample of SAS image filtered using a specific homomorphic filter depicted in our previous work [1]. Accordingly, hypothesis tests and graphical testing methods has been exploited to select the best representative of a filtered sample image SAS in order to perform a follow detection process.
Keywords :
filtering theory; sonar imaging; statistical testing; graphical testing methods; homomorphic filtered SAS images; hypothesis tests; preprocessed synthetic aperture sonar images; statistical tests; Distribution functions; Filtering theory; Gaussian distribution; Hafnium; Synthetic aperture sonar; Testing; Homomorphic filter; detection; hypothesis test; sonar image; statistical image study; testing for normality;
Conference_Titel :
OCEANS - Bergen, 2013 MTS/IEEE
Conference_Location :
Bergen
Print_ISBN :
978-1-4799-0000-8
DOI :
10.1109/OCEANS-Bergen.2013.6608112
