No-reference blur image quality measure based on multiplicative multiresolution decomposition

• Published in: Journal of visual communication and image representation Vol. 24; no. 7; pp. 911 - 925
• Main Authors: Serir, A., Beghdadi, A., Kerouh, F.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.10.2013; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Blinds; Blur; Coding, codes; Computer science; control theory; systems; Computer systems performance. Reliability; Contrast; Data processing. List processing. Character string processing; Exact sciences and technology; Features extraction; Image quality; Information, signal and communications theory; Intrinsic information analysis; Memory organisation. Data processing; MMD; Multi-resolution analysis; Pattern recognition. Digital image processing. Computational geometry; Signal and communications theory; Software; Support Vector Machine; Telecommunications and information theory; Image quality; Multi-resolution analysis; MMD; Blur; Intrinsic information analysis; Support Vector Machine; Contrast; Features extraction; Performance evaluation; Image processing; Image content; Multiresolution analysis; Efficiency; Database; Vector support machine; Operator splitting; Selection criterion; Pattern extraction; Content analysis; Blind; Image compression; Blurred image; Subjective evaluation; Noisy image; Image analysis; Experimental result; Gaussian process; Quality control; Metric; Service quality
• ISSN: 1047-3203; 1095-9076
• DOI: 10.1016/j.jvcir.2013.06.002

•A multiplicative multi-resolution decomposition MMD is used for blur analysis.•Indexes are extracted by image-content analysis through MMD coefficients.•A quality blur measure is proposed by using a set of thresholds (direct MMD-BQ-1 and iterative MMD-BQ-2 ).•A quality blur measure is proposed by using a learning process MMD-BQSVM. A new approach for analyzing the blur effect on real images is proposed. This approach is based on the Multiplicative Multi-resolution Decomposition MMD. From MMD image-content analysis, a blind image quality measure dedicated to blur is then derived. The proposed measure has been applied on Gaussian-blurred and JPEG2000-compressed images from the LIVE, TID and IVC databases. The performance of the proposed measure is evaluated and compared with some referenced image quality metrics. The experimental results measured in terms of correlation with the subjective assessment of the images, demonstrate the efficiency of the proposed image quality measure in predicting the amount of blur.