New Objective Stereo Image Quality Metric Using Human Visual Characteristics and Phase Congruency

Abstract:

Objective quality metric evaluates image quality automatically. In this paper, a new objective stereo image quality metric is proposed with left-right image quality (LRIQ) model and stereo perception quality (SPQ) model. In LRIQ model, wavelet transform is used to simulate multi-channel effect. Meanwhile, phase congruency (PC) map of sub-image is extracted as main feature to measure quality of each sub-image. Then all the sub-images qualities are weighted according to contrast sensitivity function curve. The SPQ model, quality score is obtained by comparing the PC maps of original and distorted absolute disparity images. Finally, these two models are combined to evaluate stereo image quality. Experimental results demonstrate that the correlation coefficients between proposed evaluation method and DMOS are above 0.93, and the root mean square errors are all less than 5.6, under JPEG, JPEG2000 compression, Gaussian blurring, Gaussian white noise and H.264 coding distortion. It indicates that the subjective results perform highly accordance with objective qualities.

• Periodical: Advanced Materials Research (Volumes 816-817)
• Pages: 506-511
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.816-817.506
• Online since: September 2013
• Authors: Yang Song, Mei Yu, Kai Hui Zheng, Sheng Ding
• Keywords: Human Visual System, Phases Congruency, Stereo Image Quality, Stereo Perception

References

[1] R. Bensalma. A Perceptual Metric for Stereoscopic Image Quality Assessment Based on the Binocular Energy. Multidimensional Systems and Signal Processing, 2012, 24(2): 1-36.

DOI: 10.1007/s11045-012-0178-3

[2] F. Shao, G. Y. Jiang, M. Yu, et al. Asymmetric Coding of Multi-View Video Plus Depth Based 3-D Video for View Rendering. IEEE Transactions on Multimedia, 2012, 14(1): 157-167.

DOI: 10.1109/tmm.2011.2169045

[3] G. Y. Jiang, D. J. Huang, X. Wang et al. Progress in Image Quality Evaluation Method. Electronics and Information Technology, 2010, 32 (1): 219-226.

[4] Z. Y. Zhang, P. An, Q. W. Zhang. Stereo Image Quality Assessment Based on Visual Attention. Journal of Image and Graphics. 2012, 17(6): 722-725.

[5] M. J. Chen, C. C. Su. Full-reference Quality Assessment of Stereoscopic Images by Modeling Binocular Rivalry. 2012 Conference Record of the Forty Sixth Conference on Signals, Systems and Computers. 2012: 721-725.

DOI: 10.1109/acssc.2012.6489106

[6] A. Benoit, P. L. Callet, P. Campisi, et al. Quality Assessment of Stereoscopic Image. EURASIP Journal on Image and Video Processing, 2008, (2008): 1-13.

DOI: 10.1155/2008/659024

[7] L. Zhang, L . Zhang, X. Q. Mou, D. Zhang. FSIM: A Feature Similarity Index for Image Quality Assessment. IEEE Transaction on Image Processing, 2011, 20(8): 2378 – 2386.

DOI: 10.1109/tip.2011.2109730

[8] P. Dostal, L. K. rasula, M. Klima. HLFSIM: Objective Image Quality Metric Based on ROI Analysis. IEEE International Conference on Security Technology, 2012: 367-375.

DOI: 10.1109/ccst.2012.6393587

[9] M. C. Morrone, R. A. Owens. Feature Detection from Local Energy. Pattern Recognition Letters, 1987, 6(5): 303-313.

DOI: 10.1016/0167-8655(87)90013-4

[10] P. Kovesi. Image Features from Phase Congruency. Journal of Computer Vision and Pattern Recognition, 1999, 1(3): 1-26.

[11] Z. Wang, C. Bovik. Image Quality Assessment: from Error Visibility to Structural Similarity, IEEE Transactions on Image Processing, 2004, 13(4): 600-612.

DOI: 10.1109/tip.2003.819861

[12] J. M. Zhou, G. Y. Jiang, X. Y. Mao, et al. Subjective Quality Analysis of Stereoscopic Images in 3DTV System. Visual Communications and Image Processing Conference, Taiwan, (2011).

DOI: 10.1109/vcip.2011.6115913

[13] A. Boev, M. Poikela, et al., Technical Report D5. 3, 2010. Available: http: /sp. cs. tut. fi/mobile3dtv/impaired-videos.

[14] http: /mpeg. chiariglione. org.