UPM Institutional Repository

Single image dehazing using second-generation wavelet transforms and the mean vector L2-norm


Citation

Khmag, Asem and Sy Mohamed, Sy Abd Rahman Al-haddad and Ramli, Abd Rahman and Kalantar, Bahareh (2018) Single image dehazing using second-generation wavelet transforms and the mean vector L2-norm. The Visual Computer volume, 34 (5). 675 - 688. ISSN 0178-2789; ESSN: 1432-2315

Abstract

Single image dehazing remains a seminal area of study in computer vision. Despite the huge number of studies that have addressed haze in a single image, the restoration images have not yet reached a satisfactory level in terms of visual appearance and time complexity burden. In this paper, a novel single image haze removal technique based on edge and fine texture preserving is introduced. To achieve better visual quality from the hazy image, the proposed technique uses mean vector L2-norm that is core of window sampling to estimate the transmission map. Then, second-generation wavelet transform filter is utilized in order to enhance the estimated transmission map of the resulted image. The usage of second-generation wavelet filter in this paper is due to its effectiveness while achieving fast speed. Experimental outcomes present that the proposed technique achieves competitive achievements in comparison with up-to-date state-of-the-art image dehazing methods in both quantitative and qualitative assessments, i.e., visual effects, universality, and computational processing speed.


Download File

Full text not available from this repository.

Additional Metadata

Item Type: Article
Divisions: Faculty of Engineering
DOI Number: https://doi.org/10.1007/s00371-017-1406-5
Publisher: Springer
Keywords: Scene segmentation; Mean vector L2-norm; Second-generation wavelet; Image recovery
Depositing User: Mohamad Jefri Mohamed Fauzi
Date Deposited: 23 Nov 2022 03:31
Last Modified: 23 Nov 2022 03:31
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1007/s00371-017-1406-5
URI: http://psasir.upm.edu.my/id/eprint/73899
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item