Abstract
Compared to ordinary images, omnidirectional image (OI) usually has a broader view and a higher resolution, and image quality assessment (IQA) can help people to understand and improve their visual experience. However, the current IQA works cannot achieve good performance. To address this, we proposed a novel visual perception-based no-reference/blind omnidirectional image quality assessment (NR/B-OIQA) model. The gradient-based global structural features and gray-level co-occurrence matrix-based local structural features are combined together to highlight the rich quality-aware structural information. And a novel steganalysis real model-based color descriptor is extracted to reflect the color information that ignored in most IQA models. With a multi-scale visual perception, we take image entropy and the natural scene statistics features to convey the high-level semantics and quantify the unnaturalness of omnidirectional images. Finally, we apply support vector regression to predict the objective quality value based on the subjective scores and extracted all features. Experiments are conducted on OIQA and CVIQD2018 Databases, and the results illustrate that our model has more reliable performance and stronger competitiveness and receives better conformity with the subjective values.
- [1] . 2021. Full-reference screen content image quality assessment by fusing multilevel structure similarity. ACM Trans. Multimedia Comput. Commun. Appl. 17, 3, Article
94 (July 2021), 21 pages.DOI: Google ScholarDigital Library
- [2] . 2018. Perceptual quality assessment of omnidirectional images. In Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS’18). 1–5.
DOI: Google ScholarCross Ref
- [3] J. Fridrich and J. Kodovsky. 2012. Rich models for steganalysis of digital images. In IEEE Transactions on Information Forensics and Security. 868–882.
DOI: Google ScholarDigital Library
- [4] . 1999. Color-based object recognition. Pattern Recogn. 32, 3 (1999), 453–464.Google Scholar
Cross Ref
- [5] . 2020. Deep virtual reality image quality assessment with human perception guider for omnidirectional image. IEEE Trans. Circ. Syst. Video Technol. 30 (
Apr. 2020), 917–928.Google ScholarCross Ref
- [6] . 1973. Textural features for image classification. Studies Media Commun. 3, 6 (1973), 610–621.Google Scholar
- [7] . 1998. Independent component filters of natural images compared with simple cells in primary visual cortex. Proc. Roy. Soc. B: Biol. Sci. 265, 1394 (1998), 359–366.Google Scholar
Cross Ref
- [8] . 2011. Image quality assessment based on S-CIELAB model. Signal Image Video Process. 5, 3 (2011), 283–290.Google Scholar
Cross Ref
- [9] . 2020. Identification of deep network generated images using disparities in color components. Signal Process. 174 (2020).Google Scholar
- [10] Huawei iLab. 2019. VR Data Report. Huawei iLab, Shenzhen, China.Google Scholar
- [11] . 2021. Blind omnidirectional image quality assessment with viewport oriented graph convolutional networks. IEEE Trans. Circ. Syst. Video Technol. 31 (
May 2021), 1724–1737.Google ScholarDigital Library
- [12] . 2021. Cubemap-based perception-driven blind quality assessment for 360-degree images. IEEE Trans. Image Process. (2021), 2364–2377.
DOI: Google ScholarDigital Library
- [13] . 1987. An evaluation of the two-dimensional gabor filter model of simple receptive fields in cat striate cortex. J. Neurophysiol. 58, 6 (1987), 1233–1258.Google Scholar
Cross Ref
- [14] . 2016. Blind image quality assessment using subspace alignment. InProceedings of the 10th Indian Conference on Computer Vision, Graphics and Image Processing (
ICVGIP’16 ). ACM, New York, NY, Article91 , 6 pages.DOI: Google ScholarDigital Library
- [15] . 2019. A method localizing an omnidirectional image in pre-constructed 3D wireframe map. In Proceedings of the IEEE/SICE International Symposium on System Integration.Google Scholar
Cross Ref
- [16] 2006. Orientation-selective adaptation to first- and second-order patterns in human visual cortex. J. Neurophysiol. 95, 2 (2006), 862–881.Google Scholar
Cross Ref
- [17] . 2010. Multiscale skewed heavy tailed model for texture analysis. In Proceedings of the IEEE International Conference on Image Processing.Google Scholar
- [18] . 2017. Blind image quality assessment using center-surround mechanism. InProceedings of the International Conference on Video and Image Processing (ICVIP’17). ACM, New York, NY, 113–118.
DOI: Google ScholarDigital Library
- [19] . 2016. BSD: Blind image quality assessment based on structural degradation. Neurocomputing 236 (May 2016), 93–103.Google Scholar
Digital Library
- [20] . 2019. No-reference stereoscopic image quality assessment based on visual attention and perception. IEEE Access 7 (2019), 46706–46716.Google Scholar
Cross Ref
- [21] . 2014. No-reference image quality assessment based on spatial and spectral entropies. Signal Process.: Image Commun. 29, 8 (2014), 856–863.
DOI: Google ScholarCross Ref
- [22] . 2020. Blind image quality assessment by natural scene statistics and perceptual characteristics. ACM Trans. Multimedia Comput. Commun. Appl. 16, 3, Article
91 (Aug. 2020), 91 pages.DOI: Google ScholarDigital Library
- [23] . 2021. Image Quality Assessment in the Modern Age. ACM, New York, NY, 5664–5666. Google Scholar
Digital Library
- [24] . 2012. No-reference image quality assessment in the spatial domain. IEEE Trans. Image Process. 21, 12 (2012), 4695–4708.
DOI: Google ScholarDigital Library
- [25] . 2013. Making a “completely blind” image quality analyzer. IEEE Signal Process. Lett. 20, 3 (2013), 209–212.
DOI: Google ScholarCross Ref
- [26] . 2013. Making a “completely blind” image quality analyzer. IEEE Signal Process. Lett. 20, 3 (2013), 209–212.
DOI: Google ScholarCross Ref
- [27] . 2009. The statistics of natural images. Netw. Comput. Neural Syst. (2009), 517–548.
DOI: Google ScholarCross Ref
- [28] . 2006. Image information and visual quality. IEEE Trans. Image Process. 15, 2 (2006), 430–444.Google Scholar
Digital Library
- [29] . 2006. A statistical evaluation of recent full reference image quality assessment algorithms. IEEE Trans. Image Process. 15, 11 (2006), 3440–3451.Google Scholar
Digital Library
- [30] . 2019. Gradient-based camera exposure control for outdoor mobile platforms. IEEE Trans. Circ. Syst. Video Technol. 29, 6 (2019), 1569–1583.
DOI: Google ScholarCross Ref
- [31] . 1996. The entropy of scale-space. In Proceedings of the International Conference on Pattern Recognition.Google Scholar
Cross Ref
- [32] . 2021. Perceptual quality assessment of omnidirectional images as moving camera videos. IEEE Trans. Visual. Comput. Graph.99 (2021), 1.Google Scholar
- [33] . 2018. A large-scale compressed 360-degree spherical image database: From subjective quality evaluation to objective model comparison. In Proceedings of the IEEE 20th International Workshop on Multimedia Signal Processing (MMSP’18).Google Scholar
Cross Ref
- [34] . 2019. MC360IQA: The multi-channel CNN for blind 360-degree image quality assessment. In Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS’19).Google Scholar
Cross Ref
- [35] . 2017. Weighted-to-spherically-uniform quality evaluation for omnidirectional video. IEEE Signal Process. Lett. (2017), 1408–1412.Google Scholar
- [36] . 2000. Sparse coding and decorrelation in primary visual cortex during natural vision. Science 287, 5456 (2000), 1273–1276.Google Scholar
Cross Ref
- [37] VR Photography. 2020. Retrieved from https://en.wikipedia.org/wiki/VRphotography.Google Scholar
- [38] . 2019. Blind panoramic image quality assessment via the asymmetric mechanism of human brain. In Proceedings of the IEEE Visual Communications and Image Processing (VCIP’19). 1–4.
DOI: Google ScholarCross Ref
- [39] . 2020. Blind omnidirectional image quality assessment with viewport oriented graph convolutional networks. IEEE Trans. Circ. Syst. Video Technol.99 (2020), 1.Google Scholar
- [40] . 2014. Gradient magnitude similarity deviation: A highly efficient perceptual image quality index. IEEE Trans. Image Process. 23, 2 (2014), 684–695.
DOI: Google ScholarDigital Library
- [41] . 2020. Secure binary image steganography with distortion measurement based on prediction. IEEE Trans. Circ. Syst. Video Technol. 30, 5 (2020), 1423–1434.
DOI: Google ScholarCross Ref
- [42] . 2015. A framework to evaluate omnidirectional video coding schemes. In Proceedings of the IEEE International Symposium on Mixed & Augmented Reality.Google Scholar
Digital Library
- [43] . 2018. Blind stereoscopic video quality assessment: From depth perception to overall experience. IEEE Trans. Image Process. 27, 2 (2018), 721–734.Google Scholar
Cross Ref
- [44] . 2016. Quality metric for spherical panoramic video. In Proceedings of the SPIE Optical Engineering + Applications Conference.Google Scholar
- [45] . 2014. VSI: A visual saliency-induced index for perceptual image quality assessment. IEEE Trans. Image Process. 23, 10 (2014), 4270–4281.Google Scholar
Cross Ref
- [46] . 2011. FSIM: A feature similarity index for image quality assessment. IEEE Trans. Image Process. 20, 8 (2011), 2378–2386.Google Scholar
Digital Library
- [47] . 2020. Segmented spherical projection based blind omnidirectional image quality assessment. IEEE Access 8 (2020), 1–1.Google Scholar
- [48] . 2004. Image quality assessment: From error visibility to structural similarity. IEEE Trans. Image Process. 13, 4 (2004).Google Scholar
- [49] . 2020. Blind quality assessment for image superresolution using deep two-stream convolutional networks. Info. Sci. 528 (2020).Google Scholar
Cross Ref
- [50] . 2020. Tensor oriented no-reference light field image quality assessment. IEEE Trans. Image Process. 29 (2020), 4070–4084.Google Scholar
Digital Library
- [51] . 2021. No-reference quality assessment for 360-degree images by analysis of multi-frequency information and local-global naturalness. IEEE Transactions on Circuits and Systems for Video Technology.
DOI: Google ScholarCross Ref
- [52] . 2018. Weighted-to-spherically-uniform SSIM objective quality evaluation for panoramic video. In Proceedings of the 14th IEEE International Conference on Signal Processing (ICSP’18).Google Scholar
Cross Ref
- [53] . 2020. High-definition video compression system based on perception guidance of salient information of a convolutional neural network and HEVC compression domain. IEEE Trans. Circ. Syst. Video Technol. 30, 7 (2020), 1946–1959.
DOI: Google ScholarDigital Library
Index Terms
Toward A No-reference Omnidirectional Image Quality Evaluation by Using Multi-perceptual Features
Recommendations
No-reference Omnidirectional Image Quality Assessment Based on Joint Network
MM '22: Proceedings of the 30th ACM International Conference on MultimediaIn panoramic multimedia applications, the perception quality of the omnidirectional content often comes from the observer's perception of the viewports and the overall impression after browsing. Starting from this hypothesis, this paper proposes a deep-...
No-reference image quality assessment using statistical wavelet-packet features
We present a no-reference image quality assessment method in the wavelet-packet domain.The proposed method achieves a high accuracy as compared to existing methods.The method is able to assess image quality across various distortion types.The method is ...
Reduced-reference Perceptual Discrepancy Learning for Image Restoration Quality Assessment
Artificial IntelligenceAbstractImage restoration has been receiving extensive attention owing to its widespread applications, and numerous restoration algorithms have been proposed. However, how to accurately evaluate the performances of image restoration algorithms remains ...






Comments