Skip to main content
placeholder image

A reduced reference image quality metric based on feature fusion and neural networks

Conference Paper


Download full-text (Open Access)

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.

Authors


  •   Chetouani, Aladine (external author)
  •   Beghdadi, Azeddine (external author)
  •   Deriche, Mohamed (external author)
  •   Bouzerdoum, Salim

Publication Date


  • 2011

Citation


  • Chetouani, A., Beghdadi, A., Deriche, M. & Bouzerdoum, A. (2011). A reduced reference image quality metric based on feature fusion and neural networks. 19th European Signal Processing Conference, EUSIPCO 2011 (pp. 589-593).

Scopus Eid


  • 2-s2.0-84863746809

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=1867&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/861

Start Page


  • 589

End Page


  • 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.

Authors


  •   Chetouani, Aladine (external author)
  •   Beghdadi, Azeddine (external author)
  •   Deriche, Mohamed (external author)
  •   Bouzerdoum, Salim

Publication Date


  • 2011

Citation


  • Chetouani, A., Beghdadi, A., Deriche, M. & Bouzerdoum, A. (2011). A reduced reference image quality metric based on feature fusion and neural networks. 19th European Signal Processing Conference, EUSIPCO 2011 (pp. 589-593).

Scopus Eid


  • 2-s2.0-84863746809

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=1867&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/861

Start Page


  • 589

End Page


  • 593