COMING SOON! PQDT Open is getting a new home!

ProQuest Open Access Dissertations & Theses will remain freely available as part of a new and enhanced search experience at www.proquest.com.

Questions? Please refer to this FAQ.

Dissertation/Thesis Abstract

Haze Removal by Scene Depth Estimation
by Kommera, Rahul, M.S., California State University, Long Beach, 2017, 27; 10262383
Abstract (Summary)

Haze is an atmospheric phenomenon that degrades the clarity of an image by scattering the light between the scene and the image acquisition system due to dust, smoke, and other particles. The current project presents a haze removal method, based on a linear model, which is used for estimating the scene depth. Results from real images under different haze conditions are presented. Images dehazed with the proposed method are compared to images dehazed with the Dark Channel Prior (DCP) method. Analysis of the Peak Signal to Noise Ratio (PSNR) values shows that while the DCP method tends to degrade rapidly as haze levels increase, the proposed method provides consistently superior PSNR characteristics even for high levels of haze.

Indexing (document details)
Advisor: Chassiakos, Anastasios
Commitee: Khoo, I-Hung, Yeh, Hen-Guel
School: California State University, Long Beach
Department: Electrical Engineering
School Location: United States -- California
Source: MAI 56/03M(E), Masters Abstracts International
Source Type: DISSERTATION
Subjects: Electrical engineering
Keywords:
Publication Number: 10262383
ISBN: 978-1-369-69852-7
Copyright © 2021 ProQuest LLC. All rights reserved. Terms and Conditions Privacy Policy Cookie Policy
ProQuest