ABSTRACT
This paper addresses the problem of estimating the quality of an image as it would be perceived by a human. A well accepted approach to assess perceptual quality of an image is to quantify its loss of structural information. We propose a blind image quality assessment method that aims at quantifying structural information loss in a given (possibly distorted) image by comparing its structures with those extracted from a database of clean images. We first construct a subspace from the clean natural images using (i) principal component analysis (PCA), and (ii) overcomplete dictionary learning with sparsity constraint. While PCA provides mathematical convenience, an overcomplete dictionary is known to capture the perceptually important structures resembling the simple cells in the primary visual cortex. The subspace learned from the clean images is called the source subspace. Similarly, a subspace, called the target subspace, is learned from the distorted image. In order to quantify the structural information loss, we use a subspace alignment technique which transforms the target subspace into the source by optimizing over a transformation matrix. This transformation matrix is subsequently used to measure the global and local (patch-based) quality score of the distorted image. The quality scores obtained by the proposed method are shown to correlate well with the subjective scores obtained from human annotators. Our method achieves competitive results when evaluated on three benchmark databases.
- live.ece.utexas.edu/research/quality/pristinedata.zip.Google Scholar
- M. Aharon, M. Elad, and A. Bruckstein. K-svd: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on signal processing, 54(11):4311--4322, 2006. Google ScholarDigital Library
- D. M. Chandler and S. S. Hemami. Vsnr: A wavelet-based visual signal-to-noise ratio for natural images. IEEE transactions on image processing, 16(9):2284--2298, 2007. Google ScholarDigital Library
- B. Fernando, A. Habrard, M. Sebban, and T. Tuytelaars. Unsupervised visual domain adaptation using subspace alignment. In Proceedings of the IEEE International Conference on Computer Vision, pages 2960--2967, 2013. Google ScholarDigital Library
- B. Girod. What's wrong with mean-squared error? In Digital images and human vision, pages 207--220. MIT press, 1993. Google ScholarDigital Library
- T. Guha, E. Nezhadarya, and R. K. Ward. Sparse representation-based image quality assessment. Signal Processing: Image Communication, 29(10):1138--1148, 2014. Google ScholarDigital Library
- Q. Jiang, F. Shao, G. Jiang, M. Yu, and Z. Peng. Supervised dictionary learning for blind image quality assessment using quality-constraint sparse coding. Journal of Visual Communication and Image Representation, 33:123--133, 2015. Google ScholarDigital Library
- L. Kang, P. Ye, Y. Li, and D. Doermann. Convolutional neural networks for no-reference image quality assessment. In IEEE Conference on Computer Vision and Pattern Recognition, pages 1733--1740, 2014. Google ScholarDigital Library
- E. Larson and D. Chandler. Categorical image quality assessment (csiq) database.Google Scholar
- J. Li, L. Zou, J. Yan, D. Deng, T. Qu, and G. Xie. No-reference image quality assessment using prewitt magnitude based on convolutional neural networks. Signal, Image and Video Processing, 10(4):609--616, 2016.Google ScholarCross Ref
- A. Mittal, A. K. Moorthy, and A. C. Bovik. No-reference image quality assessment in the spatial domain. IEEE Transactions on Image Processing, 21(12):4695--4708, 2012. Google ScholarDigital Library
- A. Mittal, R. Soundararajan, and A. C. Bovik. Making a completely blind image quality analyzer. IEEE Signal Processing Letters, 20(3):209--212, 2013.Google ScholarCross Ref
- B. A. Olshausen et al. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381(6583):607--609, 1996.Google ScholarCross Ref
- Y. C. Pati, R. Rezaiifar, and P. Krishnaprasad. Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition. In Signals, Systems and Computers, 1993. 1993 Conference Record of The Twenty-Seventh Asilomar Conference on, pages 40--44. IEEE, 1993.Google ScholarCross Ref
- N. Ponomarenko and K. Egiazarian. Tampere image database (tid2008).Google Scholar
- K. M. Priya and S. S. Channappayya. A novel sparsity-inspired blind image quality assessment algorithm. In Signal and Information Processing (GlobalSIP), 2014 IEEE Global Conference on, pages 984--988. IEEE, 2014.Google ScholarCross Ref
- M. A. Saad, A. C. Bovik, and C. Charrier. A dct statistics-based blind image quality index. IEEE Signal Processing Letters, 17(6):583--586, 2010.Google ScholarCross Ref
- H. Sheikh, Z. Wang, and A. Bovik. Live image quality assessment database release 2.Google Scholar
- Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4):600--612, 2004. Google ScholarDigital Library
- W. Xue, L. Zhang, and X. Mou. Learning without human scores for blind image quality assessment. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 995--1002, 2013. Google ScholarDigital Library
- L. Zhang, L. Zhang, X. Mou, and D. Zhang. Fsim: a feature similarity index for image quality assessment. IEEE Transactions on Image Processing, 20(8):2378--2386, 2011. Google ScholarDigital Library
Index Terms
- Blind image quality assessment using subspace alignment
Recommendations
Blind CT Image Quality Assessment Model Based on CT Image Statistics
ISICDM 2020: The Fourth International Symposium on Image Computing and Digital MedicineImage quality assessment is widely used in many image processing tasks, which can help researchers adjust image processing algorithms, design imaging systems, and evaluate image processing systems. Generally, CT image quality assessment can be ...
Blind assessment of image blur using the Haar wavelet
SAICSIT '10: Proceedings of the 2010 Annual Research Conference of the South African Institute of Computer Scientists and Information TechnologistsImages and video captured in real world situations generally have distorted digital pixel values. A variety of situations can cause these image degradations: sensor motion, environmental conditions and random noise. A crucial procedure in computer ...
The context effect for blind image quality assessment
AbstractImage quality assessment (IQA) is a process of visuo-cognitive, which is an essential stage in human interaction with the environment. The study of the context effect (Brown and Daniel, 1987) also shows that the evaluation results made ...
Comments