A hypergraph-based algorithm for image restoration from salt and pepper noise

被引：17

作者：

Dharmarajan, R. ^{[1
]}

Kannan, K. ^{[1
]}

机构：

[1] SASTRA Univ, Dept Math, Thanjavur, India

来源：

AEU-INTERNATIONAL JOURNAL OF ELECTRONICS AND COMMUNICATIONS | 2010年 / 64卷 / 12期

关键词：

Hypergraph; Contra Harmonic Mean; Salt and Pepper Noise; Isolated hyperedges; MEDIAN FILTERS; REDUCTION;

D O I：

10.1016/j.aeue.2009.12.001

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

An algorithm is designed for the hypergraph (HG) representation of an image, subsequent detection of Salt and Pepper (SP) noise in the image and finally the restoration of the image from this noise. The image is first represented as the set union of hyperedges. As for the hyperedges themselves, these are determined by two Image Neighborhood Hypergraph (INHG) parameters, with the concepts of 8-bit neighborhood and INHG of a graph being central. The images taken up for experimental analyses are subjected to the Contra Harmonic Mean (CHM) filter for SP noise removal. The proposed algorithm exhibits superiority over traditional algorithms and recently proposed ones in terms of visual quality, Peak Signal to Noise Ratio (PSNR) and Mean Absolute Error (MAE). This superior performance of the CHM Filter is solely due to the HG representation of the test images. (C) 2010 Elsevier GmbH. All rights reserved.

引用

页码：1114 / 1122

页数：9

共 34 条

[1]

AMLAN K, 1984, IEEE T ACOUSTICS SPE, V32, P600

[2]

[Anonymous], HYPERGRAPH BASED IMA

[3] Suppression of "salt and pepper" noise based on Youden designs [J].