Specifications
excluding Alkali and Alkaline Earth Metals - 801 Chemistry - 933.1 Crystalline Solids
DOI: 10.3724/SP.J.1010.2013.00118
Database: Compendex
Compilation and indexing terms, © 2013 Elsevier Inc.
© 2013 Elsevier Inc. All rights reserved.
20130601 新增 3 条
1.
Accession number: 20132116352554
Title: A two-stage method for haze removal with a single image
Authors: Shi, Zhenghao1 ; Yang, Huandi1 ; Zhao, Minghua1 ; Wang, Yinghui1 ; He, Lifeng2/石争
浩;;赵明华;王映辉;何立峰
Author affiliation: 1 School of Computer Science and Engineering, Xi'an University of
Technology, No. 5, South Jinhua Road, Xi'an 710048, China
2 School of Information Science and Technology, Aichi Prefectural University, 1522-3
Ibaragabasama, Nagakute, Aichi 480-1198, Japan
Corresponding author: Shi, Z. (ylshi@xaut.edu.cn)
Source title: ICIC Express Letters
Abbreviated source title: ICIC Express Lett.
Volume: 7
Issue: 8
Issue date: 2013
Publication year: 2013
Pages: 2429-2435
Language: English
ISSN: 1881803X
Document type: Journal article (JA)
Publisher: ICIC Express Letters Office, Tokai University, Kumamoto Campus, 9-1-1, Toroku,
Kumamoto, 862-8652, Japan
Abstract: Dark channel prior, proposed by He, is one of the most successful haze removal
methods with a single image in recent years. However, the method may suffer invalidity when the
scene object is inherently similar to the air light over a large local region. To address this issue, in
this paper, a two-stage method for haze removal with a single image by combining dark channel
prior with local histogram equalization is proposed. Firstly, a hazed image is dehazed based on
dark channel prior. Then, to overcome misestimate for regions similar to the atmospheric light,
the image is transformed from RGB to YCbCr color space, and then local histogram equalization is
done on the luminance component. The proposed method is tested with images under different
haze conditions. Experimental results show that the proposed method can effectively remove
haze from a hazed image. © 2013 ICIC International.
Number of references: 12
Main heading: Face recognition
Controlled terms: Graphic methods
Uncontrolled terms: Dark channel priors - Haze removal - Local histogram equalizations