Adaptive Contrast Enhancement of Satellite Images Based on Histogram and Non-linear Transfer Function Methods

Citation

Saberi, Zamfirdaus and Hashim, Noramiza and Ali, Aziah and Boursier, Patrice and Abdullah, Junaidi and Che Embi, Zarina (2023) Adaptive Contrast Enhancement of Satellite Images Based on Histogram and Non-linear Transfer Function Methods. IAENG International Journal of Applied Mathematics, 53 (1). ISSN 1992-9978

[img] Text
IJAM_53_1_40.pdf
Restricted to Repository staff only

Download (2MB)

Abstract

Satellite images are widely used in various fields as they are important, especially in monitoring activities. Change detection is one such activity that assesses differences in satellite images over time. However, weather and environmental effects may degrade the quality of images. Therefore, the image quality needs to be enhanced before processing the image. This study examined a number of adaptive contrast enhancement approaches based on histogram & non-linear transfer functions, as well as the impact of adopting multiple colour spaces for enhancement. We proposed an enhancement method where the L channel in the CIE LAB colour space was enhanced through a combination of the adaptive gamma correction method with weighting distribution (AGCWD) and Contrast Limited Adaptive Histogram Equalisation (CLAHE). We also advocated using average ranking to select the best method by averaging the various metrics. Improving the performance of change detection, our technique produced the highest average rank of BRISQUE and RMSE contrast values compared to the other methods.

Item Type: Article
Uncontrolled Keywords: Contrast enhancement, satellite images, gamma correction, histogram equalisation, change detection
Subjects: Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions: Faculty of Computing and Informatics (FCI)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 07 Apr 2023 03:10
Last Modified: 07 Apr 2023 03:10
URII: http://shdl.mmu.edu.my/id/eprint/11303

Downloads

Downloads per month over past year

View ItemEdit (login required)