Single color image super-resolution using sparse representation and color constraint

doi:10.23919/JSEE.2020.000004

Journal of Systems Engineering and Electronics ›› 2020, Vol. 31 ›› Issue (2): 266-271.doi: 10.23919/JSEE.2020.000004

• Electronics Technology • Previous Articles Next Articles

Single color image super-resolution using sparse representation and color constraint

Zhigang XU*(), Qiang MA(), Feixiang YUAN()

School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China

Received:2019-05-13 Online:2020-04-30 Published:2020-04-30
Contact: Zhigang XU E-mail:yangzij@lut.edu.cn;2639421095@qq.com;1528924388@qq.com
About author:XU Zhigang was born in 1977. He is a Ph.D. and an associate professor in the School of Computer and Communication, Lanzhou University of Technology. His research interests include image super-resolution, sparse coding and machine learning. E-mail: yangzij@lut.edu.cn|MA Qiang was born in 1994. He is currently pursuing his master degree with the School of Computer and Communication, Lanzhou University of Technology. His research interests are color image super-resolution and sparse coding. E-mail: 2639421095@qq.com|YUAN Feixiang was born in 1991. He received his master degree from the School of Computer and Communication, Lanzhou University of Techno-logy in 2018. He is currently an engineer. His research interests are color image super-resolution and sparse coding. E-mail: 1528924388@qq.com
Supported by:
the National Natural Science Foundation of China(61761028);This work was supported by the National Natural Science Foundation of China (61761028)

Abstract

Abstract:

Color image super-resolution reconstruction based on the sparse representation model usually adopts the regularization norm (e.g., $L_{1}$ or $L_{2})$. These methods have limited ability to keep image texture detail to some extent and are easy to cause the problem of blurring details and color artifacts in color reconstructed images. This paper presents a color super-resolution reconstruction method combining the $L_{2 / 3}$ sparse regularization model with color channel constraints. The method converts the low-resolution color image from RGB to YCbCr. The $L_{2 / 3}$ sparse regularization model is designed to reconstruct the brightness channel of the input low-resolution color image. Then the color channel-constraint method is adopted to remove artifacts of the reconstructed high-resolution image. The method not only ensures the reconstruction quality of the color image details, but also improves the removal ability of color artifacts. The experimental results on natural images validate that our method has improved both subjective and objective evaluation.

Key words: color image, sparse representation, super-resolution, $L_{2 / 3}$ regularization norm, color channel constraint

Zhigang XU, Qiang MA, Feixiang YUAN. Single color image super-resolution using sparse representation and color constraint[J]. Journal of Systems Engineering and Electronics, 2020, 31(2): 266-271.

Figures/Tables 5

Fig 1

Fig 2

Fig 3

Table 1

Fig 4

References 21

1	CRUZ C, MEHTA R, KATKOVNIK V, et al. Single image super-resolution based on wiener filter in similarity domain. IEEE Trans. on Image Processing, 2018, 27 (3): 1376- 1389. doi: 10.1109/TIP.2017.2779265
2	ZHAO W, BIAN X F, HUANG F, et al. Fast image super-resolution algorithm based on multi-resolution dictionary learning and sparse representation. Journal of Systems Engineering and Electronics, 2018, 29 (3): 471- 482. doi: 10.21629/JSEE.2018.03.04
3	SONG Q, XIONG R Q, LIU D, et al. Fast image super-resolution via local adaptive gradient field sharpening transform. IEEE Trans. on Image Processing, 2018, 21 (4): 1966- 1980.
4	PIACENZA P, SHERMAN S, CIOCARLIE M. Data-driven super-resolution on a tactile dome. IEEE Robotics and Automation Letters, 2018, 3 (3): 1434- 1441. doi: 10.1109/LRA.2018.2800081
5	LIU D, WANG Z W, WEN B H, et al. Robust single image super-resolution via deep networks with sparse prior. IEEE Trans. on Image Processing, 2016, 25 (7): 3194- 3207. doi: 10.1109/TIP.2016.2564643
6	DONG C, LOY C C, HE K, et al. Image super-resolution using deep convolutional networks. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2016, 38 (2): 295- 307. doi: 10.1109/TPAMI.2015.2439281
7	YANG J C, WRIGHT J, HUANG T S, et al. Image super-resolution via sparse representation. IEEE Trans. on Image Processing, 2010, 19 (11): 2861- 2873. doi: 10.1109/TIP.2010.2050625
8	XU Z G, LI W W, YUAN F X, et al. Super-resolution reconstruction based on l1/2 sparse regularization and multicomponent dictionaries. Systems Engineering and Electronics, 2018, 40 (3): 699- 703.
9	LIU J Y, YANG W H, ZHANG X F, et al. Retrieval compensated group structured sparsity for image super-resolution. IEEE Trans. on Multimedia, 2017, 19 (2): 302- 316. doi: 10.1109/TMM.2016.2614427
10	ZHANG Y L, GU K Y, ZHANG Y B, et al. Image super-resolution based on dictionary learning and anchored neighborhood regression with mutual incoherence. Proc. of the IEEE International Conference on Image Processing, 2015, 591- 595.
11	TIMOFTE R, SMET V D, GOOL L V. A+: adjusted anchored neighborhood regression for fast super-resolution. Proc. of the Asian Conference on Computer Vision, 2014, 111- 126.
12	XU Y, YU L C, XU H T, et al. Vector sparse representation of color image using quaternion matrix analysis. IEEE Trans. on Image Processing, 2015, 24 (4): 1315- 1329. doi: 10.1109/TIP.2015.2397314
13	YANG L, LIU Y G, HUANG R G, et al. New approach for super-resolution from a single color image based on sparse coding. Journal of Computer Applications, 2013, 33 (2): 472- 475. doi: 10.3724/SP.J.1087.2013.00472
14	CHENG M, WANG C, LI J. Single-image super-resolution in rgb space via group sparse representation. IET Image Processing, 2015, 9 (6): 461- 467. doi: 10.1049/iet-ipr.2014.0313
15	YANG M C, WANG Y C. A self-learning approach to single image super-resolution. IEEE Trans. on Multimedia, 2013, 15 (3): 498- 508. doi: 10.1109/TMM.2012.2232646
16	XU J, CHANG Z G, FAN J L, et al. Super-resolution via adaptive combination of color channels. Multimedia Tools & Applications, 2017, 76 (1): 1553- 1584.
17	CAO W F, DUN J, XU Z B. Fast image deconvolution using closed-form thresholding formulas of $lq\ (q=12, 23)$ regularization. Journal of Visual Communication & Image Representation, 2013, 24 (1): 31- 41.
18	AHARON M, ELAD M, BRUCKSTEIN A. K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. on Signal Processing, 2006, 54 (11): 4311- 4322. doi: 10.1109/TSP.2006.881199
19	MOUSAVI H S, MONGA V. Sparsity-based color image super resolution via exploiting cross channel constraints. IEEE Trans. on Image Processing, 2017, 26 (11): 5094- 5106. doi: 10.1109/TIP.2017.2704443
20	BECK A, TEBOULLE M. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM Journal on Imaging Sciences, 2009, 2 (1): 183- 202. doi: 10.1137/080716542
21	DONG W S, ZHANG L, SHI G M, et al. Nonlocally centralized sparse representation for image restoration. IEEE Trans. on Image Processing, 2013, 22 (4): 1620- 1630.

Image	Evaluation parameter	BI	ScSR	NCSR	MCcSR	Ours
Flowers	PSNR	30.38	32.52	31.96	32.53	33.40
Flowers	SSIM	0.898	0.929	0.913	0.930	0.938
Comic	PSNR	26.06	27.28	27.22	26.52	27.92
Comic	SSIM	0.851	0.899	0.896	0.892	0.908
Butterfly	PSNR	27.42	30.51	30.63	30.23	31.19
Butterfly	SSIM	0.915	0.951	0.952	0.950	0.958
Skiing	PSNR	32.00	33.57	33.61	33.54	34.33
Skiing	SSIM	0.931	0.945	0.947	0.944	0.953
Bike	PSNR	25.66	27.33	27.03	26.94	27.92
Bike	SSIM	0.850	0.896	0.863	0.864	0.913

[1]	Guisheng WANG, Yequn WANG, Shufu DONG, Guoce HUANG. Multiple transformation analysis for interference separation in TDCS [J]. Journal of Systems Engineering and Electronics, 2022, 33(5): 1064-1078.
[2]	Yuanrong TIAN, Xing WANG. Learning a discriminative high-fidelity dictionary for single channel source separation [J]. Journal of Systems Engineering and Electronics, 2021, 32(5): 1097-1110.
[3]	Jian WANG, Chunxia QIN, Xiufei ZHANG, Ke YANG, Ping REN. A multi-source image fusion algorithm based on gradient regularized convolution sparse representation [J]. Journal of Systems Engineering and Electronics, 2020, 31(3): 447-459.
[4]	Wei ZHAO, Xiaofeng BIAN, Fang HUANG, Jun WANG, Mongi A ABIDI. Fast image super-resolution algorithm based on multi-resolution dictionary learning and sparse representation [J]. Journal of Systems Engineering and Electronics, 2018, 29(3): 471-482.
[5]	Jian ZHAO, Chao ZHANG, Shunli ZHANG, Tingting LU, Weiwen SU, Jian JIA. Pre-detection and dual-dictionary sparse representation based face recognition algorithm in non-sufficient training samples [J]. Journal of Systems Engineering and Electronics, 2018, 29(1): 196-202.
[6]	Jiaqi Zhen and Zhifang Wang. DOA estimation method for wideband signals by sparse recovery in frequency domain [J]. Systems Engineering and Electronics, 2017, 28(5): 871-878.
[7]	Zhizhong Fu, Yawei Li, Yuan Li, Lan Ding, and Keyu Long. Frequency domain based super-resolution method for mixed-resolution multi-view images [J]. Journal of Systems Engineering and Electronics, 2016, 27(6): 1303-1314.
[8]	Jingjing Cai, Dan Bao, and Peng Li. DOA estimation via sparse recovering from the smoothed covariance vector [J]. Systems Engineering and Electronics, 2016, 27(3): 555-561.
[9]	Xiang Wang, Zhitao Huang, and Yiyu Zhou. Underdetermined DOA estimation and blind separation of non-disjoint sources in time-frequency domain based on sparse representation method [J]. Journal of Systems Engineering and Electronics, 2014, 25(1): 17-25.
[10]	Jiajia Zhao, Zhengyuan Tang, Jie Yang, and Erqi Liu. Infrared small target detection using sparse representation [J]. Journal of Systems Engineering and Electronics, 2011, 22(6): 897-904.
[11]	Liangkui Lin, Hui Xu, Dan Xu, Wei An, and Kai Xie. QPSO-based algorithm of CSO joint infrared super-resolution and trajectory estimation [J]. Journal of Systems Engineering and Electronics, 2011, 22(3): 405-411.
[12]	Fuzhen Zhu, Jinzong Li, Bing Zhu, and Dongdong Ma. Super-resolution image reconstruction based on three-step-training neural networks [J]. Journal of Systems Engineering and Electronics, 2010, 21(6): 934-940.
[13]	Chunhui Zhu*, Yi Shen, and Qiang Wang. New fast algorithm for hypercomplex decomposition and hypercomplex cross-correlation [J]. Journal of Systems Engineering and Electronics, 2010, 21(3): 514-519.
[14]	Yang Miao, & Wei Zhiqiang. Fuzzy color morphological sieves? [J]. Journal of Systems Engineering and Electronics, 2009, 20(6): 1366-1372.
[15]	Li Liangchao, Yang Jianyu, Cui Guolong, Wu Junjie, Jiang Zhengmao & Zheng Xin. Super-resolution processing of passive millimeter-wave images based on conjugate-gradient algorithm [J]. Journal of Systems Engineering and Electronics, 2009, 20(4): 762-767.

Single color image super-resolution using sparse representation and color constraint

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 5

References 21

Related Articles 15

Recommended Articles

Metrics

Comments