Optimizing Multistage Discriminative Dictionaries for Blind Image Quality Assessment
- 16 October 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 20 (8), 2035-2048
- https://doi.org/10.1109/tmm.2017.2763321
Abstract
According to the types of the used features, state-ofthe-art methods for blind image quality assessment (BIQA) typically have two categories. The first category utilizes handcrafted natural scene statistics (NSS) features which are derived based on the statistical regularity of natural images. The second category utilizes codebook-based features which are obtained by feature encoding over a pre-constructed codebook. However, several problems need to be addressed in the existing codebook-based BIQA methods. First, dimension of the involved codebook-based features is too high. Second, codebooks are usually constructed by unsupervised learning algorithms. To address these problems, we propose a novel codebook-based BIQA method by optimizing multi-stage discriminative dictionaries (MSDDs). To be more specific, MSDDs are learned by performing the label consistent K-SVD (LC-KSVD) algorithm in a stage-by-stage manner. In each stage, a new quality consistency constraint called “qualitydiscriminative regularization” term is introduced and incorporated into the traditional reconstruction error term to form a unified objective function which can be effectively solved by LC-KSVD. Then, the latter stage takes the reconstruction residual data in the former stage as input based on which LC-KSVD is repeatedly performed until the final stage is reached. Once the MSDDs are learned, multi-stage feature encoding (MSFE) is performed to extract feature codes. Finally, the feature codes are concatenated across all stages and spatially aggregated over the entire image for quality prediction via a typical regression module. The proposed method has been extensively evaluated on five IQA databases and the experimental results has well confirmed its superiority over the existing relevant BIQA methods.Keywords
Funding Information
- National Natural Science Foundation of China (61622109)
- Natural Science Foundation of Zhejiang Province (R18F010008)
- China Scholarship Council (201708330302)
- Ningbo University
This publication has 60 references indexed in Scilit:
- Reduced reference image quality assessment using regularity of phase congruencySignal Processing: Image Communication, 2014
- VSI: A Visual Saliency-Induced Index for Perceptual Image Quality AssessmentIEEE Transactions on Image Processing, 2014
- Label Consistent K-SVD: Learning a Discriminative Dictionary for RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Pooling in image representation: The visual codeword point of viewComputer Vision and Image Understanding, 2013
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- Most apparent distortion: full-reference image quality assessment and the role of strategyJournal of Electronic Imaging, 2010
- Reduced-reference metric design for objective perceptual quality assessment in wireless imagingSignal Processing: Image Communication, 2009
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse RepresentationIEEE Transactions on Signal Processing, 2006
- Image Quality Assessment: From Error Visibility to Structural SimilarityIEEE Transactions on Image Processing, 2004
- Least squares quantization in PCMIEEE Transactions on Information Theory, 1982