Multi-feature Fusion Based Image Quality Assessment Method
JIA Huizhen1, WANG Tonghan1, FU Peng2
1.Jiangxi Engineering Laboratory on Radioactive Geoscience and Big Data Technology, East China University of Technology, Nanchang 330013
2.School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094
To avoid the difficulties in choosing and explaining the visual features and pooling strategies in image quality assessment, a reference images quality assessment method based on multi-feature fusion is proposed. Various underlying features of reference and distorted images are extracted,and a machine learning method is applied to predict the quality of real images. Firstly, phase congruency, gradient, visual saliency and contrast of reference and distorted images are extracted. Then similarity maps of four features are calculated, respectively. The mean and variance characteristics of these similarity maps are extracted. Finally, the assessment model is learned by support vector regression. The experimental results on four benchmark databases demonstrate a high coherence between subjective and objective assessment by the proposed method.
[1] WANG Z, BOVIK A C. Modern Image Quality Assessment. San Rafael, USA: Morgan & Claypool, 2006.
[2] WANG Z, BOVIK A C, LU L G. Why Is Image Quality Assessment so Difficult // Proc of the IEEE International Conference on Acoustics, Speech, and Signal Processing. Washington, USA: IEEE, 2002, IV: 3313-3316.
[3] WANG Z, BOVIK A C, SHEIKH H R, et al. Image Quality Assessment: From Error Visibility to Structural Similarity. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.
[4] WANG Z, SIMONCELLI E P, BOVIK A C. Multiscale Structural Similarity for Image Quality Assessment // Proc of the IEEE Confe-rence Record of the 37th Asilomar Conference on Signals, Systems and Computers. Washington, USA: IEEE, 2003, II: 9-12.
[5] CHEN G H, YANG C L, XIE S L, et al. Gradient-Based Structural Similarity for Image Quality Assessment // Proc of the International Conference on Image Processing. Washington, USA: IEEE, 2006: 2929-2932.
[6] WANG Z, SIMONCELLI E P. Translation Insensitive Image Similarity in Complex Wavelet Domain // Proc of the IEEE International Conference on Acoustics, Speech, and Signal Processing. Washington, USA: IEEE, 2005, II: 573-576.
[7] LI C F, BOVIK A C. Three-Component Weighted Structural Similarity Index. Proc of SPIE, 2009, 7242. DOI: 10.1117/12.811821.
[8] WANG Z, LI Q. Information Content Weighting for Perceptual Image Quality Assessment. IEEE Transactions on Image Process, 2011, 20(5): 1185-1198.
[9] DAMERA-VENKATA N, KITE T D, GEISLER W S, et al. Image Quality Assessment Based on a Degradation Model. IEEE Transactions on Image Processing, 2000, 9(4): 636-650.
[10] CHANDLER D M, HEMAMI S S. VSNR: A Wavelet-Based Vi-sual Signal-to-Noise Ratio for Natural Images. IEEE Transactions on
Image Processing, 2007, 16(9): 2284-2298.
[11] SHEIKH H R, BOVIK A C, VECIANA D. An Information Fidelity Criterion for Image Quality Assessment Using Natural Scene Statistics. IEEE Transactions on Image Process, 2005, 14(12): 2117-2128.
[12] SHEIKH H R, BOVIK A C. Image Information and Visual Quality. IEEE Transactions on Image Process, 2006, 15(2): 430-444.
[13] LARSON E C, CHANDLER D M. Most Apparent Distortion: Full-Reference Image Quality Assessment and the Role of Strategy. Journal of Electronic Imaging, 2010, 19(1). DOI: 10.1117/1.3267105.
[14] ZHANG L, ZHANG L, MOU X Q, et al. FSIM: A Feature Similarity Index for Image Quality Assessment. IEEE Transactions on Image Processing, 2011, 20(8): 2378-2386.
[15] ZHANG L, SHEN Y, LI H Y. VSI: A Visual Saliency-Induced Index for Perceptual Image Quality Assessment. IEEE Transactions on Image Processing, 2014, 23(10): 4270-4281.
[16] LIU A M, LIN W S, NARWARIA M. Image Quality Assessment Based on Gradient Similarity. IEEE Transactions on Image Proce-ssing, 2012, 21(4): 1500-1512.
[17] XUE W F, ZHANG L, MOU X Q, et al. Gradient Magnitude Si-milarity Deviation: A Highly Efficient Perceptual Image Quality Index. IEEE Transactions on Image Processing, 2014, 23(2): 684-695.
[18] WANG T H, ZHANG L, JIA H Z, et al. Multiscale Contrast Similarity Deviation: An Effective and Efficient Index for Perceptual Image Quality Assessment. Signal Processing: Image Communication, 2016, 45: 1-9.
[19] PONOMARENKO N, IEREMEIEV O, LUKIN V, et al. Color Image Database TID2013: Peculiarities and Preliminary Results // Proc of the European Workshop on Visual Information Processing. Washington, USA: IEEE, 2013: 106-111.
[20] JEFFREY L. A Visual Discrimination Model for Imaging System Design and Evaluation // PELI E, ed. Visual Models for Target Detection and Recognition. Singapore, Singapore: World Scientific, 1995: 207-220.
[21] SAFRANEK R J, JOHNSTON J D. A Perceptually Tuned Sub-band Image Coder with Imaging Dependent Quantization and Post-Quantization Data Compression // Proc of the IEEE Conference on Acoustics, Speech, and Signal Processing. Washington, USA: IEEE, 1989: 1945-1948.
[22] HOU X D, ZHANG L Q. Saliency Detection: A Spectral Residual Approach // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2007. DOI: 10.1109/CVPR.2007.383267.
[23] KOVESI P. Image Features from Phase Congruency. Journal of Computer Vision, 1999, 1(3): 1-26.
[24] 贾惠珍,孙权森,王同罕.结合感知特征和自然场景统计的无参考图像质量评价.中国图象图形学报, 2014, 19(6): 859-867.
(JIA H Z, SUN Q S, WANG T H. Blind Image Quality Assessment Based on Perceptual Features and Natural Scene Statistics. Journal of Image and Graphics, 2014, 19(6): 859-867.)
[25] 吴 帅,徐 勇,赵东宁.基于深度卷积网络的目标检测综述.模式识别与人工智能, 2018, 31(4): 335-346.
(WU S, XU Y, ZHAO D N. Survey of Object Detection Based on Deep Convolutional Network. Pattern Recognition and Artificial Intelligence, 2018, 31(4): 335-346.)
[26] NGUYEN A, KIM J, OH H, et al. Deep Visual Saliency on Stere-oscopic Images. IEEE Transactions on Image Processing, 2019, 28(4): 1939-1953.
[27] BASAK D, PAL S, PATRANABIS D C. Support Vector Regression. Neural Information Processing, 2007, 11(10): 203-224.
[28] WANG T H, ZHANG L, JIA H Z. An Effective General-Purpose NR-IQA Model Using Natural Scene Statistics(NSS) of the Luminance Relative Order. Signal Processing(Image Communication), 2019, 71: 100-109.
[29] BREIMAN L. Random Forests. Machine Learning, 2001, 45(1): 5-32.
[30] TOMANDL D, SCHOBER A. A Modified General Regression Neural Network(MGRNN) with New, Efficient Training Algorithms as a Robust ′Black Box′-Tool for Data Analysis. Neural Networks, 2001, 14(8): 1023-1034.
2019, Vol. 32 
