Adaptively Truncating Gradient for Image Quality Assessment

Minjuan Gao; Hongshe Dang; Xuande Zhang

Uneingeschränkter Zugang

Adaptively Truncating Gradient for Image Quality Assessment

Minjuan Gao

Hongshe Dang

und

Xuande Zhang

| 11. Jan. 2021

International Journal of Advanced Network, Monitoring and Controls

Band 5 (2020): Heft 4 (January 2020)

Über diesen Artikel

Vorheriger Artikel

Nächster Artikel

Zitieren

Online veröffentlicht: 11. Jan. 2021

Seitenbereich: 27 - 33

DOI: https://doi.org/10.21307/ijanmc-2020-034

Schlüsselwörter
Image Quality Assessment, Human Visual System, Upper Threshold, Truncating Gradient

© 2020 Xuande Zhang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

The gradient map and the adaptively truncating gradient map corresponding to the reference image and the distorted image. (a) the reference image. (b) the distorted image. (c) and (d) are the gradient map of (a) and (b), respectively. (e) and (f) are the adaptively truncating gradient map of (a) and (b), respectively.

SROCC performance with different T0 values on six databases

COMPARISON SROCC FOR INDIVIDUAL DISTORTION OF TEN IQA METRICS ON TID2013 DATABASE. THE FIRS TTWO ARE MARKED IN BOLD

Database	Distortion type	PSNR	SSIM (2004)	MS-SSIM (2003)	IFC (2005)	VIF (2006)	FSIM (2011)	GMSD (2014)	DASM (2017)	SSRM (2018)	Proposed
TID2013		PSNR	SSIM (2004)	MS-SSIM (2003)	IFC (2005)	VIF (2006)	FSIM (2011)	GMSD (2014)	DASM (2017)	SSRM (2018)
	Awgn	0.9291	0.8671	0.8646	0.6612	0.8994	0.8973	0.9461	0.9299	0.8545	0.9293
	Awgn-color	0.8986	0.7726	0.7730	0.5352	0.8299	0.8208	0.8689	08612	0.7757	0.8463
	Spatial-correlated	0.9197	0.8515	0.8544	0.6601	0.8835	0.8750	0.9348	0.9301	0.8392	0.9178
	Mask-noise	0.8321	0.7767	0.8073	0.6932	0.8450	0.7944	0.7085	0.8019	0.8184	0.8068
	HF-noise	0.9140	0.8634	0.8604	0.7406	0.8972	0.8984	0.9164	0.9179	0.8754	0.9069
	Impulse-noise	0.8969	0.7503	0.7629	0.6408	0.8537	0.8072	0.7633	0.8550	0.7872	0.8336
	Quantization-noise	0.8801	0.8657	0.8706	0.6282	0.7854	0.8719	0.9057	0.9032	0.8496	0.8629
	GB	0.9155	0.9668	0.9673	0.8907	0.9650	0.9551	0.9114	0.9546	0.9674	0.9686
	Denoising	0.9481	0.9254	0.9268	0.7779	0.8911	0.9302	0.9525	0.9496	0.9288	0.9361
	JPEG	0.9189	0.9200	0.9265	0.8357	0.9192	0.9324	0.9500	0.9473	0.9287	0.9515
	JP2K	0.8840	0.9468	0.9504	0.9078	0.9516	0.9577	0.9656	0.9620	0.9562	0.9635
	JPEG-trans-error	0.7682	0.8493	0.8475	0.7425	0.8409	0.8464	0.8401	0.8534	0.8369	0.8802
	JP2K-trans-error	0.8886	0.8828	0.8889	0.7769	0.8761	0.8913	0.9135	0.8966	0.8765	0.9141
	Pattern-noise	0.6864	0.7821	0.7968	0.5737	0.7720	0.7917	0.8143	0.8138	0.7745	0.7632
	Block-distortion	0.1552	0.5720	0.4801	0.2414	0.5306	0.5489	0.6630	0.6338	0.3186	0.6635
	Mean-shift	0.7671	0.7752	0.7906	0.5522	0.6276	0.7531	0.7356	0.6127	0.6919	0.6143
	Contrast change	0.4416	0.3775	0.4634	-0.1798	0.8386	0.4686	0.3253	0.3498	0.4519	0.4889
	Saturation change	0.0944	-0.4141	-0.4099	-0.4029	-0.3099	-0.2748	-0.1907	0.0382	-0.2513	-0.2602
	Multiple-noise	0.8911	0.7803	0.7786	0.61423	0.8468	0.8469	0.8880	0.8814	0.8067	0.8698
	Comfort-noise	0.8410	0.8566	0.8528	0.81620	0.8946	0.9121	0.9298	0.9203	0.8921	0.9112
	Noisy-compression	0.9144	0.9057	0.9068	0.8180	0.9204	0.9466	0.9631	0.9402	0.9164	0.9367
	Color quantization	0.9269	0.8542	0.8555	0.6006	0.8414	0.8760	0.9098	0.9177	0.8546	0.8952
	Chromatic abbr.	0.8871	0.8775	0.8784	0.8210	0.8848	0.8715	0.8517	0.8693	0.8844	0.8849
	Sparse sample	0.9044	0.9461	0.9483	0.8885	0.9353	0.9565	0.9684	0.9669	0.9541	0.9601

COMPARISON THE PERFORMANCE RESULTS OF TEN IQA METRICS ON SIX PUBLIC DATABASES. THE FIRST TWO ARE MARKED IN BOLD

Database	criteria	PSNR	SSIM (2004)	MS-SSIM (2003)	IFC (2005)	VIF (2006)	FSIM (2011)	GMSD (2014)	DASM (2017)	SSRM (2018)	Proposed
	SROCC	PSNR	SSIM (2004)	MS-SSIM (2003)	IFC (2005)	VIF (2006)	FSIM (2011)	GMSD (2014)	DASM (2017)	SSRM (2018)	0.6396	0.7417	0.7859	0.5389	0.6769	0.8015	0.8038	0.8025	0.7500	0.8105
TID2013	KROCC	0.4698	0.5588	0.6047	0.3939	0.5147	0.6289	0.6334	0.6321	0.5718	0.6387
TID2013	PLCC	0.7017	0.7895	0.8329	0.5538	0.7720	0.8589	0.8542	0.8574	0.8078	0.8601
	RMSE	0.8832	0.7608	0.6861	1.0322	0.7880	0.6349	0.6444	0.6547	0.7307	0.6324
	SROCC	0.5531	0.7749	0.8542	0.5675	0.7491	0.8805	0.8906	-	0.8332	0.8913
TID2008	KROCC	0.4027	0.5768	0.6568	0.4236	0.5860	0.6946	0.7090	-	0.6535	0.7042
TID2008	PLCC	0.5734	0.7732	0.8451	0.7340	0.8090	0.8738	0.8786	-	0.8379	0.8745
	RMSE	1.0994	0.8511	0.7173	0.9113	0.7888	0.6525	0.6408	-	0.7324	0.6458
	SROCC	0.8756	0.9479	0.9513	0.9259	0.9636	0.9634	0.9546	0.9601	0.9608	0.9531
LIVE	KROCC	0.6865	0.7963	0.8045	0.7579	0.8282	0.8337	0.8237	0.8218	0.8312	0.8211
LIVE	PLCC	0.8721	0.9449	0.9430	0.9248	0.9598	0.9597	0.9515	0.9571	0.9695	0.9379
	RMSE	13.368	8.9455	9.0956	10.392	7.6734	7.6780	7.1131	7.7716	5.6639	8.0188
	SROCC	0.8058	0.8756	0.9133	0.7671	0.9195	0.9242	0.9571	0.9523	0.9369	0.9251
CSIQ	KROCC	0.6084	0.6907	0.7393	0.5897	0.7537	0.7567	0.8122	0.8041	0.7791	0.7575
CSIQ	PLCC	0.8001	0.8613	0.8998	0.8381	0.9277	0.9120	0.9543	0.9531	0.9097	0.9055
	RMSE	0.1575	0.1334	0.1145	0.1432	0.0980	0.1077	0.0791	0.0799	0.1138	0.1114
	SROCC	0.6884	0.9018	0.8980	0.8993	0.8964	0.9262	0.8789	0.8966	0.9047	0.9103
IVC	KROCC	0.5218	0.7223	0.7203	0.7202	0.7158	0.7564	0.6882	0.7179	0.7310	0.7352
IVC	PLCC	0.7199	0.9119	0.8934	0.9080	0.9028	0.9376	0.8549	0.9190	0.9132	0.9206
	RMSE	0.8456	0.4999	0.5474	0.5105	0.5239	0.4236	0.6320	0.5220	0.4965	0.4758
	SROCC	0.6189	0.8066	0.8394	0.3185	0.6223	0.9181	0.9103	0.9215	0.8527	0.9062
A57	KROCC	0.4309	0.6058	0.6478	0.2378	0.4589	0.7639	0.7513	0.7782	0.6604	0.7289
A57	PLCC	0.6587	0.8017	0.8504	0.4548	0.6158	0.9252	0.9085	0.9429	0.8528	0.8530
	RMSE	0.1849	0.1469	0.1293	0.2189	0.1936	0.0933	01027	0.0813	0.0707	0.1283

eISSN:: 2470-8038
Sprache:: Englisch

Zeitrahmen der Veröffentlichung:: 4 Hefte pro Jahr
Fachgebiete der Zeitschrift:: Informatik, andere

Zeitschrift RSS Feed

Adaptively Truncating Gradient for Image Quality Assessment

Online veröffentlicht: 11. Jan. 2021

Seitenbereich: 27 - 33

DOI: https://doi.org/10.21307/ijanmc-2020-034

Schlüsselwörter
Image Quality Assessment, Human Visual System, Upper Threshold, Truncating Gradient

© 2020 Xuande Zhang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

COMPARISON SROCC FOR INDIVIDUAL DISTORTION OF TEN IQA METRICS ON TID2013 DATABASE. THE FIRS TTWO ARE MARKED IN BOLD

COMPARISON THE PERFORMANCE RESULTS OF TEN IQA METRICS ON SIX PUBLIC DATABASES. THE FIRST TWO ARE MARKED IN BOLD

Adaptively Truncating Gradient for Image Quality Assessment

Online veröffentlicht: 11. Jan. 2021

Seitenbereich: 27 - 33

DOI: https://doi.org/10.21307/ijanmc-2020-034

SchlüsselwörterImage Quality Assessment, Human Visual System, Upper Threshold, Truncating Gradient

© 2020 Xuande Zhang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

COMPARISON SROCC FOR INDIVIDUAL DISTORTION OF TEN IQA METRICS ON TID2013 DATABASE. THE FIRS TTWO ARE MARKED IN BOLD

COMPARISON THE PERFORMANCE RESULTS OF TEN IQA METRICS ON SIX PUBLIC DATABASES. THE FIRST TWO ARE MARKED IN BOLD

Schlüsselwörter
Image Quality Assessment, Human Visual System, Upper Threshold, Truncating Gradient