DocumentCode :
2263524
Title :
A Reduced Reference Image Quality Metric based on feature fusion and neural networks
Author :
Chetouani, Aladine ; Beghdadi, Azeddine ; Deriche, Mohamed ; Bouzerdoum, Abdesselam
Author_Institution :
Inst. Galilee, Univ. Paris 13, Villetaneuse, France
fYear :
2011
fDate :
Aug. 29 2011-Sept. 2 2011
Firstpage :
589
Lastpage :
593
Abstract :
A Global Reduced Reference Image Quality Metric (IQM) based on feature fusion using neural networks is proposed. The main idea is the introduction of a Reduced Reference degradation-dependent IQM (RRIQM/D) across a set of common distortions. The first stage consists of extracting a set of features from the wavelet-based edge map. Such features are then used to identify the type of degradation using Linear Discriminant Analysis (LDA). The second stage consists of fusing the extracted features into a single measure using Artificial Neural Networks (ANN). The result is a degradation-dependent IQM measure called the RRIQM/D. The performance of the proposed method is evaluated using the TID 2008 database and compared to some existing IQMs. The experimental results obtained using the proposed method demonstrate an improved performance even when compared to some Full Reference IQMs.
Keywords :
feature extraction; image fusion; neural nets; ANN; LDA; RRIQM/D; TID 2008 database; artificial neural network; feature extraction; feature fusion; linear discriminant analysis; reduced reference degradation-dependent IQM; reduced reference image quality metric; wavelet-based edge map; Artificial neural networks; Degradation; Feature extraction; Image edge detection; Image quality; Measurement; Transform coding;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing Conference, 2011 19th European
Conference_Location :
Barcelona
ISSN :
2076-1465
Type :
conf
Filename :
7073848
Link To Document :
بازگشت