Single Image Super-Resolution Based on Convolutional Neural Network

Ziteng Shi; Zhiren Wang; Rui Wang; Fuquan Ren

doi:10.3788/LOP55.121001

Journals >Laser & Optoelectronics Progress >Volume 55 >Issue 12 >Page 121001 > Article

Laser & Optoelectronics Progress
Vol. 55, Issue 12, 121001 (2018)

Single Image Super-Resolution Based on Convolutional Neural Network

Ziteng Shi, Zhiren Wang, Rui Wang, and Fuquan Ren^*

Author Affiliations

College of Science, Yanshan University, Qinhuangdao, Hebei 066004, China

show less

DOI: 10.3788/LOP55.121001 Cite this Article Set citation alerts

Ziteng Shi, Zhiren Wang, Rui Wang, Fuquan Ren. Single Image Super-Resolution Based on Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2018, 55(12): 121001 Copy Citation Text

show less

Fig. 1. SRCNN algorithm framework

Download full size

Fig. 2. Proposed algorithm framework

Download full size

Fig. 3. Function schematic. (a) ReLU; (b) e-ReLU

Download full size

Fig. 4. Graph of train loss in the proposed method with the increase of iterations in the training process

Download full size

Fig. 5. Comparison of the reconstruction of the baby_GT in Set 5. (a) Original image; (b) BI/33.91 dB; (c) ScSR/34.29 dB; (d) SRCNN/34.83 dB; (e) SRCNN-Ex/34.91dB; (f) proposed method/35.04 dB

Download full size

Fig. 6. Comparison of the reconstruction of the butterfly_GT in Set 5. (a) Original image; (b) BI/24.04 dB; (c) ScSR/25.58 dB; (d) SRCNN/25.00 dB; (e) SRCNN-Ex/25.58 dB; (f) proposed method/27.91 dB

Download full size

Fig. 7. Comparison of the reconstruction of the lenna in Set 14. (a) Original image; (b) BI/31.68 dB; (c) ScSR/32.64 dB; (d) SRCNN/32.53 dB; (e) SRCNN-Ex/32.78 dB; (f) proposed method/33.57 dB

Download full size

Fig. 8. Comparison of the reconstruction of the pepper in Set 14. (a) Original image; (b) BI/32.38 dB; (c) ScSR/33.32 dB; (d) SRCNN/32.08 dB; (e) SRCNN-Ex/33.30 dB; (f) proposed method/34.57 dB

Download full size

Fig. 9. Change graph of the average PSNR value for proposed algorithm in the Set 5 test set, with the number of iterations

Download full size

Name	Size	Number	Stride	Padding
Conv1	5×5	64	1	0
Conv2	3×3	32	1	0
Deconv	9×9	1	3	4

Table 1. Parameter settings for each layer

Image	BI		ScSR		SRCNN		SRCNN-Ex		Proposed method
Image	PSNR /dB	SSIM	PSNR /dB	SSIM	PSNR /dB	SSIM	PSNR /dB	SSIM	PSNR /dB	SSIM
Baby	33.91	0.90	34.29	0.92	34.83	0.92	34.91	0.92	35.04	0.92
Bird	32.57	0.93	34.11	0.92	33.77	0.94	34.03	0.94	35.46	0.95
Butterfly	24.04	0.82	25.58	0.82	25.00	0.83	25.58	0.84	27.91	0.91
Head	32.88	0.80	33.17	0.80	33.42	0.82	33.42	0.82	33.67	0.83
Women	28.56	0.89	29.94	0.91	29.60	0.91	29.91	0.91	31.22	0.93
Average	30.39	0.87	31.42	0.87	31.32	0.88	31.57	0.89	32.66	0.91

Table 2. PSNR and SSIM values on Set 5 test set

Image	BI		ScSR		SRCNN		SRCNN-Ex		Proposed method
Image	PSNR /dB	SSIM	PSNR /dB	SSIM	PSNR /dB	SSIM	PSNR /dB	SSIM	PSNR /dB	SSIM
Baboon	23.21	0.54	23.50	0.59	23.52	0.60	23.54	0.60	23.62	0.61
Barbara	26.25	0.75	26.39	0.75	26.76	0.78	26.84	0.78	26.57	0.78
Bridge	24.40	0.65	24.80	0.70	24.89	0.70	24.95	0.70	25.14	0.71
Coastguard	26.55	0.61	27.00	0.65	27.00	0.66	27.08	0.66	27.12	0.66
Comic	23.12	0.70	23.90	0.76	23.77	0.75	23.87	0.75	24.53	0.79
Face	32.82	0.80	33.10	0.81	33.38	0.82	33.40	0.82	33.71	0.83
Flowers	27.23	0.80	28.25	0.83	28.06	0.83	28.27	0.83	29.22	0.85
Foreman	31.16	0.91	32.04	0.91	32.09	0.91	32.01	0.91	33.65	0.94
Lenna	31.68	0.86	32.64	0.87	32.53	0.87	32.78	0.88	33.57	0.88
Man	27.01	0.75	27.76	0.78	27.56	0.78	27.72	0.78	28.33	0.80
Monarch	29.43	0.92	30.71	0.93	30.40	0.93	30.87	0.93	32.78	0.95
Pepper	32.38	0.87	33.32	0.87	32.08	0.88	33.30	0.88	34.57	0.89
Ppt3	23.71	0.87	24.98	0.87	24.34	0.88	25.02	0.89	26.24	0.92
Zebra	26.63	0.80	27.95	0.82	27.74	0.84	28.37	0.84	29.11	0.85

Table 3. PSNR and SSIM values on Set 14 test set

Method	1000 times iteration	10⁵ times iteration	2×10⁵ times iteration	8×10⁸ times iteration
SRCNN	477			381600000
SRCNN-Ex	1392			1113600000
Proposed method	141	14100	28200

Table 4. Comparison of training times

Ziteng Shi, Zhiren Wang, Rui Wang, Fuquan Ren. Single Image Super-Resolution Based on Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2018, 55(12): 121001

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information