Abstract
Sparse coding based face image Super-Resolution (SR) approaches have received increasing amount of interest recently. However, most of the existing sparse coding based approaches fail to consider the geometrical structure of the face space, as a result, artificial effects on reconstructed High Resolution (HR) face images come into being. In this paper, a novel sparse coding based face image SR method is proposed to reconstruct a HR face image from a Low Resolution (LR) observation. In training stage, it aims to get a more expressive HR-LR dictionary pair for certain input LR patch. The intrinsic geometric structure of training samples is incorporated into the sparse coding procedure for dictionary learning. Unlike the existing SR methods which use the graph constructed in LR Manifold (LRM) as regularization term, the proposed method uses graph constructed in HR Manifold (HRM) as regularization term. In reconstruction stage, K selection mean constrains is used in l 1 convex optimization, aiming at finding an optimal weight for HR face image patch reconstruction. Experimental results on both simulation and real world images suggest that our proposed one achieves better quality when compared with other state-of-the-art methods.
Similar content being viewed by others
References
An L, Bhanu B (2014) Face image super-resolution using 2D CCA. Signal Process 103:184–194
Baker S, Kanade T (2002) Limits on super-resolution and how to break them. IEEE Trans Pattern Analysis Machine Intell 24(9):1167–1183
Belkin M, Niyogi P (2002) Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput 15(6):1373–1396
Capel D, Zisserman A (2001) Super- resolution from multiple views using learnt image models, IEEE Int Conf Comput Vision Pattern Recognition, pp.627–634
Chang H, Yeung D, Xiong Y (2004) Super-resolution through neighbor embedding. IEEE Int Conf Comput Vision Pattern Recognition, pp. 275–282
Chang L, Zhou M (2010) Face sketch synthesis via sparse representation, Int Conf Pattern Recognization, pp.2146–2149
Cheng B, Yang J, Yan S, Yun F, Huang TS (2010) Learning with L1-graph for image analysis. IEEE Trans Image Process 19(4):858–866
CMU+ MIT Face Database. [Online]. Available: http://vasc.ri.cmu.edu/idb/images/face/frontal images/images.html
Gao W, Cao B (2008) The CAS-PEAL large-scale Chinese face database and baseline evaluations. IEEE TSMC-A 38(1):149–161
He H, Siu W-C (2011) Single image super-resolution using Gaussian process regression, in CVPR, pp. 449–456
Huang H, He H, Fan X, Zhang J (2010) Super-resolution of human face image using canonical correlation analysis. Pattern Recogn 43(7):2532–2543
Huang H, Wu N (2011) Fast facial image super-resolution via local linear transformations for resource-limited applications. IEEE Trans Image Process 21(10):1363–1377
Jiang J, Hu R, Han Z, Lu T (2014) Efficient single image super-resolution via graph-constrained least squares regression. Multimedia Tools Appl 72(3):2573–2596
Jiang J, Hu R, Wang Z, Han Z, Jiayi M (2015) Facial Image Hallucination through Coupled-Layer Neighbor Embedding. IEEE Trans Circ Syst Video Technol. doi:10.1109/TCSVT.2015.2433538
Jiang J, Hu R, Wang Z, Han Z (2014) Noise robust face hallucination via locality-constrained representation, IEEE Trans Multimedia, vol. PP, no. 99, pp. 1–1
Jiang J, Hu R, Wang Z, Han Z (2014) Face super-resolution via multilayer locality-constrained iterative neighbor embedding and intermediate dictionary learning. IEEE Trans Image Process 23(10):4220–4231
Jiang J, Ma X, Hu R, Cai Z (2015) Sparse support regression for image super-resolution. IEEE Photonics J 7(5):1–11
Jung C, Jiao L, Liu B, Gong M (2011) Position-patch based face hallucination using convex optimization. IEEE Signal Proc Letters 18(6):367–370
Kim KI, Kwon Y (2010) Single-image super-resolution using sparse regression and natural image prior. IEEE Trans Pattern Anal Mach Intell 32(6):1127–1133
Li X, He H, Wang R, Cheng J (2015) Superpixel-guided nonlocal means for image denoising and super-resolution, Signal Processing
Li X, He H, Wang R, Tao D (2015) Single image superresolution via directional group sparsity and directional Features. IEEE Trans Image Process 24(9):2874–2888
Li X, He H, Yin Z, Chen F, Cheng J (2015) KPLS-based image super-resolution using clustering and weighted boosting. Neurocomputing 149:940–948
Liu C, Shum HY, Zhang CS (2001) A two-step approach to hallucinating faces: global parametric model and local nonparametric model. IEEE Int Conf Comput Vision Pattern Recognition, pp. 192–198
Lu X, Yan P, Yuan Y (2014) Alternatively constrained dictionary learning for image superresolution. IEEE Trans Cybernetics 44(3):366–377
Ma X, Luong HQ, Philips W, Song H, Cui H (2012) Sparse representation and position prior based face hallucination upon classified over-complete dictionaries. Signal Process 92(9):2066–2074
Ma J, Qiu W, Zhao J, Ma Y, Yuille AL, Zhuowen T (2015) Robust L2E estimation of transformation for non-rigid registration. IEEE Trans Signal Process 63(5):1115–1129
Ma X, Zhang J, Qi C (2010) Hallucinating face by position-patch. Pattern Recogn 43(1):2224–2236
Ma J, Zhao J, Tian J, Yuille A, Zhuowen T (2014) Robust point matching via vector field consensus. IEEE Trans Image Process 23(4):1706–1721
Ma J, Zhao J, Yuille AL (2016) Non-rigid point set registration by preserving global and local structures. IEEE Trans Image Process 25(1):53–64
Ma J, Zhou H, Zhao J, Gao Y, Jiang J, Tian J (2015) Robust feature matching for remote sensing image registration via locally linear transforming. IEEE Trans Geosci Remote Sens 53(12):6469–6481
Roweis S, Saul L (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326
Su C, Zhuang Y, Huang L et al (2005) Steerable pyramid based face hallucination. Pattern Recogn 38(6):813–824
Sung Won Park, Savvides M (2007) Breaking the limitation of manifold analysis for super-resolution of facial images, IEEE Int Conf Acoustics, Speech Signal Proc, Page(s): 573–576
Timofte R, De V, Van Gool L (2013) Anchored neighborhood regression for fast example-based super-resolution, in ICCV, pp. 1920–1927
Wang Z, Hu R, Liang C, Yu Y, Jiang J, Ye M, Chen J, Leng Q. Zero-shot person re-identification via cross-view consistency, IEEE Trans Multimedia, vol. PP, no.99, pp.1–1, doi: 10.1109/TMM.2015.2505083
Wang Z, Bovik AC (2004) Image quality assessment: from error measurement to structural similarity. IEEE Trans Image Process 13(4):600–612
Wang Z, Hu R, Jiang J, Han Z, Shao Z (2015) Heteroskedasticity tuned mixed-norm sparse regularization for face hallucination, Multimedia Tools Appl, doi: 10.1007/s11042-015-2996-4
Wang Z, Hu R, Wang S, Jiang J (2014) Face hallucination via weighted adaptive sparse regularization. IEEE Trans Circuits Syst Video Technol 24(5):802–813
Wang X, Tang X (2005) Hallucinating face by eigentransform. IEEE TSMC-C 34(3):425–434
Xiang M, Huansheng S, Xueming Q (2015) Robust framework of single-frame face super-resolution across head pose, facial expression, and illumination variations. IEEE Trans Human-Machine Syst 45(2):238–250
Yang J, Wright J, Huang T, Ma Y (2008) Image super resolution as sparse representation of raw image patches. IEEE Conf Comput Vision Pattern Recognition, pp. 1–8
Zhang W, Cham W-K (2009) Learning-based face hallucination in DCT domain, in Proc. IEEE Int Conf Comput Vision Pattern Recognition (CVPR), pp. 1–8
Zhang W, Cham W-K (2011) Hallucinating face in the DCT domain. IEEE Trans Image Process 20(10):2769–2779
Zhang X, Silong P, Jing J (2008) An adaptive learning method for face hallucination using locality preserving projections, 8th IEEE Int Conf Auto Face Gesture Recognition, pp.1–8
Zhu Z, Guo F, Yu H, Chen C (2014) Fast single image super-resolution via self-example learning and sparse representation. IEEE Trans Multimedia 16(8):2178–2190
Acknowledgments
The research was supported by the National High Technology Research and Development Program of China (863 Program) (2015AA016306, 2013AA014602), the National Natural Science Foundation of China (61231015, 61172173, 61303114, 61501413), the EU FP7 QUICK project under Grant Agreement No. PIRSES-GA-2013-612652, the Internet of Things Development Funding Project of Ministry of industry in 2013 (No.25), the Technology Research Program of Ministry of Public Security (2014JSYJA016), the China Postdoctoral Science Foundation funded project (2013M530350, 2014M562058), and the Specialized Research Fund for the Doctoral Program of Higher Education (20130141120024), the Fundamental Research Funds for the Central Universities (2042014kf0025), Major Science and Technology Innovation Plan of Hubei Province (No. 2013AAA020).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Huang, K., Hu, R., Jiang, J. et al. HRM graph constrained dictionary learning for face image super-resolution. Multimed Tools Appl 76, 3139–3162 (2017). https://doi.org/10.1007/s11042-015-3215-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-015-3215-z