No-reference stereoscopic image quality assessment guided by visual hierarchical structure and binocular effects

Yong Ding; Yang Zhao

doi:10.1364/AO.57.002610

Applied Optics
Vol. 57,
Issue 10,
pp. 2610-2621
(2018)
•https://doi.org/10.1364/AO.57.002610

No-reference stereoscopic image quality assessment guided by visual hierarchical structure and binocular effects

Yong Ding and Yang Zhao

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
Yong Ding and Yang Zhao, "No-reference stereoscopic image quality assessment guided by visual hierarchical structure and binocular effects," Appl. Opt. 57, 2610-2621 (2018)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Citation alert
Save article

Check for updates

Abstract

Stereoscopic image quality assessment (SIQA) is an essential technique for modern 3D image and video processing systems serving as performance evaluators and monitors. However, the study on SIQA remains immature due to the complexity of the human visual system (HVS) and binocular effects that binocular vision brings about. To overcome the difficulties, a novel method is proposed that extracts and quantifies image quality-aware features related to cortex areas in charge of visual quality perception, rather than attempting to rigorously simulate the biological processing in HVS, so that the predicting accuracy is preserved while the computational complexity remains moderate. Meanwhile, binocular effects including binocular rivalry and visual discomfort are taken into consideration. Moreover, the proposed method can be operated completely without the assistance of reference images, indicating its wide practical usages. Compared to state-of-the-art works, our method shows evident superiority in terms of effectiveness and robustness.

Full Article | PDF Article

More Like This

Full-reference quality assessment of stereoscopic images by learning binocular visual properties

Jian Ma, Ping An, Liquan Shen, and Kai Li
Appl. Opt. 56(29) 8291-8302 (2017)

No-reference stereoscopic image quality assessment based on hue summation–difference mapping image and binocular joint mutual filtering

Jiachen Yang, Kyohoon Sim, Bin Jiang, and Wen Lu
Appl. Opt. 57(14) 3915-3926 (2018)

Multiple just-noticeable-difference-based no-reference stereoscopic image quality assessment

Zijin Gu, Yong Ding, Ruizhe Deng, Xiaodong Chen, and Andrey S. Krylov
Appl. Opt. 58(2) 340-352 (2019)

Previous Article Next Article

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (7)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (6)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Equations (28)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

	LIVE I	LIVE II
JPEG 2000 compression	80	72
JPEG compression	80	72
White noise	80	72
Gaussian blur	45	72
Rayleigh fast fading	80	72
Symmetrically distorted	365	120
Asymmetrically distorted	0	240
Total	365	360

		A	B	C	D
LIVE I	PLCC	0.926	0.936	0.944	0.951
LIVE I	SRCC	0.900	0.922	0.931	0.942
	RMSE	6.172	5.714	5.420	5.021
LIVE II	PLCC	0.891	0.902	0.931	0.945
LIVE II	SRCC	0.876	0.892	0.925	0.940
	RMSE	5.115	5.001	4.124	3.645

Training Dataset	Testing Dataset	PLCC	SRCC
LIVE I	LIVE II	0.841	0.835
LIVE II	LIVE I	0.882	0.875

		BRISQUE	QAC	NIQE	GM_LoG	IL_NIQE	Akhter	Chen	Shao	Zhou¹	Appina	Zhou²	Xu	Our
LIVE I	PLCC	0.910	0.835	0.811	0.928	0.861	0.626	0.895	0.878	0.928	0.917	0.941	0.949	0.951
	SRCC	0.901	0.839	0.797	0.911	0.860	0.383	0.891	0.866	0.887	0.911	0.921	0.934	0.942
	RMSE	6.793	8.320	8.853	6.006	7.700	14.827	7.247	NA	6.025	6.598	5.540	5.088	5.021
LIVE II	PLCC	0.771	0.804	0.740	0.881	0.728	0.568	0.895	0.820	0.861	0.845	0.923	0.926	0.945
	SRCC	0.770	0.785	0.707	0.874	0.673	0.543	0.880	0.789	0.823	0.888	0.919	0.910	0.940
	RMSE	7.038	6.706	7.594	5.262	7.734	9.294	5.102	NA	5.779	7.279	4.262	4.182	3.645
LIVE I & II	PLCC	0.841	0.820	0.776	0.905	0.795	0.597	0.895	0.849	0.895	0.881	0.932	0.938	0.948
	SRCC	0.836	0.812	0.752	0.893	0.767	0.462	0.886	0.828	0.855	0.900	0.920	0.922	0.941
	RMSE	6.915	7.519	8.228	5.637	7.717	12.080	6.182	NA	5.903	6.936	4.905	4.638	4.338

		BRISQUE	QAC	NIQE	GM_LoG	IL_NIQE	Akhter	Chen	Shao	Zhou¹	Appina	Zhou²	Xu
LIVE I	PLCC	1	1	1	1	1	1	1	1	1	1	0	0
	SRCC	1	1	1	1	1	1	1	1	1	1	1	0
	RMSE	1	1	1	1	1	1	1	NA	1	1	1	0
LIVE II	PLCC	1	1	1	1	1	1	1	1	1	1	1	1
	SRCC	1	1	1	1	1	1	1	1	1	1	1	1
	RMSE	1	1	1	1	1	1	1	NA	1	1	0	0

		BRISQUE	QAC	NIQE	GM_LoG	IL_NIQE	Akhter	Chen	Shao	Zhou¹	Appina	Zhou²	Xu	Our
LIVE I	JP2K	0.812	0.886	0.632	0.906	0.861	0.866	0.863	0.870	0.824	0.917	0.871	0.903	0.908
	JPEG	0.569	0.682	0.599	0.642	0.544	0.675	0.617	0.429	0.614	0.782	0.687	0.678	0.744
	WN	0.940	0.938	0.907	0.935	0.920	0.914	0.919	0.930	0.915	0.910	0.941	0.905	0.925
	GB	0.860	0.871	0.861	0.857	0.873	0.555	0.878	0.914	0.916	0.865	0.905	0.907	0.920
	FF	0.784	0.558	0.519	0.506	0.536	0.640	0.652	NA	0.867	0.666	0.785	0.800	0.801
	w.a.	0.787	0.779	0.689	0.761	0.735	0.747	0.777	NA	0.819	0.824	0.831	0.832	0.854
LIVE II	JP2K	0.593	0.781	0.599	0.839	0.593	0.724	0.867	0.790	0.717	0.864	0.897	0.861	0.918
	JPEG	0.769	0.821	0.637	0.878	0.491	0.649	0.867	0.730	0.593	0.839	0.802	0.771	0.865
	WN	0.846	0.621	0.600	0.920	0.617	0.714	0.950	0.882	0.891	0.932	0.942	0.936	0.944
	GB	0.862	0.843	0.851	0.884	0.880	0.682	0.900	0.942	0.903	0.846	0.907	0.922	0.947
	FF	0.935	0.891	0.775	0.949	0.758	0.559	0.933	NA	0.891	0.860	0.920	0.858	0.943
	w. a.	0.801	0.791	0.692	0.894	0.668	0.666	0.903	NA	0.799	0.868	0.894	0.870	0.923
LIVE I & II	JP2K	0.708	0.836	0.616	0.874	0.734	0.799	0.865	0.832	0.773	0.892	0.883	0.883	0.913
	JPEG	0.664	0.748	0.617	0.754	0.519	0.663	0.735	0.572	0.604	0.809	0.741	0.722	0.801
	WN	0.895	0.788	0.762	0.928	0.776	0.819	0.934	0.907	0.904	0.920	0.941	0.920	0.934
	GB	0.861	0.854	0.855	0.874	0.877	0.633	0.892	0.931	0.908	0.853	0.906	0.916	0.937
	FF	0.856	0.716	0.640	0.716	0.641	0.602	0.785	NA	0.878	0.758	0.849	0.827	0.868
	w.a.	0.794	0.785	0.690	0.827	0.701	0.706	0.840	NA	0.809	0.846	0.862	0.851	0.888

		BRISQUE	QAC	NIQE	GM_LoG	IL_NIQE	Akhter	Chen	Shao	Zhou¹	Appina	Zhou²	Xu	Our
LIVE I	JP2K	0.812	0.886	0.632	0.906	0.861	0.866	0.863	0.870	0.824	0.917	0.871	0.903	0.908
	JPEG	0.569	0.682	0.599	0.642	0.544	0.675	0.617	0.429	0.614	0.782	0.687	0.678	0.744
	WN	0.940	0.938	0.907	0.935	0.920	0.914	0.919	0.930	0.915	0.910	0.941	0.905	0.925
	GB	0.860	0.871	0.861	0.857	0.873	0.555	0.878	0.914	0.916	0.865	0.905	0.907	0.920
	FF	0.784	0.558	0.519	0.506	0.536	0.640	0.652	NA	0.867	0.666	0.785	0.800	0.801
	w.a.	0.787	0.779	0.689	0.761	0.735	0.747	0.777	NA	0.819	0.824	0.831	0.832	0.854
LIVE II	JP2K	0.593	0.781	0.599	0.839	0.593	0.724	0.867	0.790	0.717	0.864	0.897	0.861	0.918
	JPEG	0.769	0.821	0.637	0.878	0.491	0.649	0.867	0.730	0.593	0.839	0.802	0.771	0.865
	WN	0.846	0.621	0.600	0.920	0.617	0.714	0.950	0.882	0.891	0.932	0.942	0.936	0.944
	GB	0.862	0.843	0.851	0.884	0.880	0.682	0.900	0.942	0.903	0.846	0.907	0.922	0.947
	FF	0.935	0.891	0.775	0.949	0.758	0.559	0.933	NA	0.891	0.860	0.920	0.858	0.943
	w. a.	0.801	0.791	0.692	0.894	0.668	0.666	0.903	NA	0.799	0.868	0.894	0.870	0.923
LIVE I & II	JP2K	0.708	0.836	0.616	0.874	0.734	0.799	0.865	0.832	0.773	0.892	0.883	0.883	0.913
	JPEG	0.664	0.748	0.617	0.754	0.519	0.663	0.735	0.572	0.604	0.809	0.741	0.722	0.801
	WN	0.895	0.788	0.762	0.928	0.776	0.819	0.934	0.907	0.904	0.920	0.941	0.920	0.934
	GB	0.861	0.854	0.855	0.874	0.877	0.633	0.892	0.931	0.908	0.853	0.906	0.916	0.937
	FF	0.856	0.716	0.640	0.716	0.641	0.602	0.785	NA	0.878	0.758	0.849	0.827	0.868
	w.a.	0.794	0.785	0.690	0.827	0.701	0.706	0.840	NA	0.809	0.846	0.862	0.851	0.888

Abstract

Cited By

Figures (7)

Tables (6)

Equations (28)

Applied Optics