Blind Restoration for Underwater Image Based on Sparse Prior of Red Channel

Jun Xie; Guojia Hou; Guodong Wang; Zhenkuan Pan

doi:10.3788/LOP202158.1610014

Journals >Laser & Optoelectronics Progress >Volume 58 >Issue 16 >Page 1610014 > Article

Laser & Optoelectronics Progress
Vol. 58, Issue 16, 1610014 (2021)

Blind Restoration for Underwater Image Based on Sparse Prior of Red Channel

Jun Xie, Guojia Hou^*, Guodong Wang, and Zhenkuan Pan

Author Affiliations

College of Computer Science and Technology, Qingdao University, Qingdao, Shandong 266071, China

show less

DOI: 10.3788/LOP202158.1610014 Cite this Article Set citation alerts

Jun Xie, Guojia Hou, Guodong Wang, Zhenkuan Pan. Blind Restoration for Underwater Image Based on Sparse Prior of Red Channel[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1610014 Copy Citation Text

show less

Fig. 1. Comparison of red channel of underwater images. (a1)(a2) Clear images; (b1)(b2) blurred images

Download full size

Fig. 2. Flowchart of proposed algorithm

Download full size

Fig. 3. Subjective comparison of different underwater image restored algorithms. (a) Original images; (b) UDCP algorithm; (c) MSCW algorithm; (d) WCID algorithm; (e) IBLA algorithm; (f) fusion algorithm; (g) UIDE algorithm; (h) proposed algorithm

Download full size

Fig. 4. Detailed comparison of different underwater image restored algorithms. (a1)(a2) Original images; (b1)(b2) UDCP algorithm; (c1)(c2) MSCW algorithm; (d1)(d2) WCID algorithm; (e1)(e2) IBLA algorithm; (f1)(f2) fusion algorithm; (g1)(g2) UIDE algorithm; (h1)(h2) proposed algorithm

Download full size

Fig. 5. SURF feature point matching

Download full size

Fig. 6. Edge detection and statistics of edge pixels

Download full size

Image	Original	UDCP	MSCW	WCID	IBLA	Fusion	UIDE	Proposed
①	0.32	0.32	0.40	0.45	0.48	0.59	0.58	0.61
②	0.41	0.50	0.54	0.49	0.48	0.54	0.59	0.64
③	0.46	0.51	0.55	0.53	0.54	0.57	0.61	0.62
④	0.50	0.49	0.59	0.56	0.56	0.58	0.54	0.61
⑤	0.46	0.58	0.56	0.51	0.52	0.63	0.62	0.68
⑥	0.55	0.58	0.60	0.64	0.48	0.58	0.63	0.64
⑦	0.54	0.56	0.59	0.61	0.59	0.58	0.59	0.63
Dataset average	0.48	0.56	0.57	0.55	0.57	0.59	0.60	0.63

Table 1. Quantitative comparison of UCIQE under different underwater image restored algorithms

Image	Original	UDCP	MSCW	WCID	IBLA	Fusion	UIDE	Proposed
①	0.39	0.41	0.46	0.31	0.38	0.39	0.45	0.73
②	0.48	0.57	0.59	0.50	0.57	0.58	0.59	0.59
③	0.47	0.48	0.54	0.57	0.39	0.54	0.54	0.66
④	0.50	0.62	0.65	0.64	0.56	0.55	0.48	0.58
⑤	0.38	0.61	0.52	0.50	0.40	0.53	0.45	0.62
⑥	0.62	0.69	0.58	0.60	0.54	0.59	0.56	0.63
⑦	0.62	0.63	0.61	0.61	0.56	0.61	0.55	0.67
Dataset average	0.55	0.60	0.58	0.59	0.55	0.58	0.55	0.63

Table 2. Quantitative comparison of BIQI under different underwater image restored algorithms

Image	Original	UDCP	MSCW	WCID	IBLA	Fusion	UIDE	Proposed
①	7.73	7.07	5.45	6.45	5.57	5.02	4.37	12.57
②	5.33	4.60	4.56	6.14	4.66	4.52	4.43	13.17
③	2.13	2.07	1.99	2.00	2.08	2.17	1.97	2.44
④	3.84	4.10	3.36	3.56	3.35	3.29	3.55	9.00
⑤	4.83	4.36	4.06	4.57	4.33	3.98	3.76	5.42
⑥	2.90	2.88	2.62	2.99	2.83	2.87	2.89	3.77
⑦	4.94	5.25	4.61	5.59	4.75	4.67	4.44	7.05
Dataset average	4.65	4.38	4.00	4.49	4.07	4.12	3.63	4.82

Table 3. Quantitative comparison of JNB under different underwater image restored algorithms

Jun Xie, Guojia Hou, Guodong Wang, Zhenkuan Pan. Blind Restoration for Underwater Image Based on Sparse Prior of Red Channel[J]. Laser & Optoelectronics Progress, 2021, 58(16): 1610014

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information