Blind image quality assessment method based on a particle swarm optimization support vector regression fusion scheme

被引：1

作者：

Eddine, Dakkar Borhen ^{[1
]}

Fella, Hachouf ^{[1
]}

Azeddine, Beghdadi ^{[2
]}

机构：

[1] Univ Freres Mentouri, Dept Elect, Fac Sci & Technol, Lab Automat & Robot, Campus A Hamani,Route Ain El Bey, Constantine 25000, Algeria

[2] Univ Paris 13, Sorbonne Paris Cite, Inst Galilee, Lab Traitement & Transport Informat, 99 Ave Jean Baptiste, F-93430 Villetaneuse, France

来源：

JOURNAL OF ELECTRONIC IMAGING | 2016年 / 25卷 / 06期

关键词：

fusion; image quality assessment; particle swarm optimization; support vector regression; NATURAL SCENE STATISTICS;

D O I：

10.1117/1.JEI.25.6.061623

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：

Quantifying image quality without reference is still a challenging problem, especially when different distortions affect the observed image. A no-reference image quality assessment (NR-IQA) metric is proposed. It is based on a fusion scheme of multiple distortion measures. This metric is built in two stages. First, a set of relevant IQA metrics is selected using a particle swarm optimization scheme. Then, a support vector regression (SVR)-based fusion strategy is adopted to derive the overall index of image quality. The obtained results demonstrate clearly that the proposed approach outperforms the state-of-the-art NR-IQA methods. Furthermore, the proposed approach is flexible and could be extended to other distortions. (C) 2016 SPIE and IS&T

引用

页数：13

共 35 条

[1]

[Anonymous], 2013, International Scholarly Research Notices., DOI [DOI 10.1155/2013/905685, 10.1155/2013/905685]

[2] LIBSVM: A Library for Support Vector Machines [J].

Chang, Chih-Chung ;

Lin, Chih-Jen .

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2011, 2 (03)

[3] A hybrid system for distortion classification and image quality evaluation [J].

Chetouani, Aladine ;

Beghdadi, Azeddine ;

Deriche, Mohamed .

SIGNAL PROCESSING-IMAGE COMMUNICATION, 2012, 27 (09) :948-960

[4] No-Reference Blur Assessment of Digital Pictures Based on Multifeature Classifiers [J].

Ciancio, Alexandre ;

Targino da Costa, Andre Luiz N. ;

da Silva, Eduardo A. B. ;

Said, Amir ;

Samadani, Ramin ;

Obrador, Pere .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2011, 20 (01) :64-75

[5]

Eberhart R., 2002, MHS95 P 6 INT S MICR, DOI [DOI 10.1109/MHS.1995.494215, 10.1109/MHS.1995.494215]

[6]

Eddine D. B., 2014, 5 EUR WORKSH VIS INF, P1

[7] No-reference quality assessment of JPEG images via a quality relevance map [J].

Golestaneh, S. Alireza ;

Chandler, Damon M. .

IEEE Signal Processing Letters, 2014, 21 (02) :155-158

[8] Fusion of hand based biometrics using particle swarm optimization [J].

Hanmandlu, M. ;

Kumar, Amioy ;

Madasu, Vamsi K. ;

Yarlagadda, Prasad .

PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY: NEW GENERATIONS, 2008, :783-+

[9]

Hassan R., 2005, 46 AIAA ASME ASCE AH, DOI [DOI 10.2514/6.2005-1897, 10.2514/6.2005-1897]

[10]

Hong Z., 2013, GREEN COMP COMM GREE, P1790

← 1 2 3 4 →