Coarse-to-fine underwater image enhancement based on multi-level wavelet transform

Table 1. Comparison of quantitative results by variant models with different number of building modules on Test 1.
View table
View in Article
Table 1. Comparison of quantitative results by variant models with different number of building modules on Test 1.
Level ResIN_3 ResIN_4 ResIN_5
PSNR 24.38 24.47 24.50
SSIM 0.884 1 0.885 6 0.886 7
Model Res_3 Res_4 Res_6
PSNR 24.23 24.44 24.51
SSIM 0.882 5 0.884 9 0.886 8
Model RK2_3 RK2_4 RK2_6
PSNR 24.01 24.18 24.53
SSIM 0.874 3 0.879 2 0.886 8

Table 2. Comparison of quantitative results by different variant models on Test1.

View table

View in Article

Table 2. Comparison of quantitative results by different variant models on Test1.

Level	n=1	n=2	n=3	n=4	n=5
PSNR	21.08	23.33	24.51	24.48	24.43
SSIM	0.830 4	0.866 7	0.886 7	0.881 7	0.876 4
Model	n=6	Net-w/o-lb	Net-w/o-hb	Net-w/o-R	Net-Residual
PSNR	23.89	22.47	22.15	21.76	23.87
SSIM	0.871 1	0.841 2	0.839 7	0.838 9	0.869 5

Table 3. Quantitative comparison of enhanced results by different algorithms on Test1.

View table

View in Article

Table 3. Quantitative comparison of enhanced results by different algorithms on Test1.

Models	EWT	ERH	HUIE	UWCNN	UWGAN	WDN	MWN	FGAN	Ours
PSNR	21.04	15.25	11.48	15.87	12.19	18.98	23.67	14.84	24.51
SSIM	0.836	0.715	0.635	0.705	0.648	0.776	0.864	0.732	0.886
PCQI	0.991	0.983	0.968	0.974	0.971	0.987	1.012	0.892	1.057
EI	78.45	74.18	66.52	71.57	68.29	76.44	80.57	64.08	82.54
UIQM	2.951	2.616	2.395	2.553	2.490	2.821	3.052	2.795	3.123
UCIQE	0.610	0.594	0.566	0.581	0.573	0.605	0.614	0.608	0.625
Entropy	7.528	7.246	7.029	7.126	7.097	7.482	7.714	7.303	7.854

Table 4. Quantitative comparison of enhanced results by different algorithms on Test2.

View table

View in Article

Table 4. Quantitative comparison of enhanced results by different algorithms on Test2.

Models	EWT	ERH	HUIE	UWCNN	UWGAN	WDN	MWN	FGAN	Ours
PSNR	17.64	17.84	18.51	14.23	17.32	17.96	18.22	17.81	20.18
SSIM	0.823	0.847	0.803	0.657	0.822	0.780	0.809	0.730	0.862
PCQI	0.989	1.018	0.986	0.969	0.977	0.980	0.981	0.983	1.035
EI	76.20	77.65	74.89	68.47	70.89	73.49	75.12	75.89	80.44
UIQM	2.871	2.921	2.827	2.456	2.710	2.733	2.802	2.814	2.987
UCIQE	0.607	0.613	0.605	0.587	0.598	0.601	0.609	0.603	0.618
Entropy	7.389	7.457	7.338	7.020	7.117	7.248	7.308	7.325	7.528

Tools

Get Citation

Copy Citation Text

Guoming YUAN, Guang YANG, Jinfeng WANG, Haijun LIU, Wei WANG. Coarse-to-fine underwater image enhancement based on multi-level wavelet transform[J]. Optics and Precision Engineering, 2022, 30(22): 2939

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Information Sciences

Received: May. 19, 2022

Accepted: --

Published Online: Nov. 28, 2022

The Author Email: YANG Guang (yangg202205@163.com)

DOI:10.37188/OPE.20223022.2939

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Comparison of quantitative results by variant models with different number of building modules on Test 1.

Table 1. Comparison of quantitative results by variant models with different number of building modules on Test 1.

Table 2. Comparison of quantitative results by different variant models on Test1.

Table 2. Comparison of quantitative results by different variant models on Test1.

Table 3. Quantitative comparison of enhanced results by different algorithms on Test1.

Table 3. Quantitative comparison of enhanced results by different algorithms on Test1.

Table 4. Quantitative comparison of enhanced results by different algorithms on Test2.

Table 4. Quantitative comparison of enhanced results by different algorithms on Test2.