Abstract
Face hallucination is a special super-resolution (SR) algorithm that enhances the resolution and quality of low-resolution (LR) facial image. For reconstructing finer high frequency information which are missing in image degradation, learning-based face SR methods rely on accurate prior information from training samples. In this paper, we propose a contextual-field supported iterative representation algorithm for face hallucination to discovery accurate prior. Different from traditional local-patch based methods, we use contextual-field supported sampling to replace local receptive field patch sampling for enriching prior information. Then, two weighted matrices are introduced to constrain reconstruction-errors term and representation-coefficients term simultaneously, one matrix ameliorates the heteroscedasticity of real data and the other one improves the stability of solution. Finally, we use iterative representation learning to iteratively update the supported dictionary pairs and their representation-coefficients to refine accurate high-frequency information. The experimental results show that the proposed approach outperforms some state-of-the-art face hallucination methods over FERET and CMU-MIT face databases using both subjective and objective evaluation indexes.
This work is supported by the National Natural Science Foundation of China (61502354, 61501413, 61671332, 41501505, U1404618), the Natural Science Foundation of Hubei Province of China (2018ZYYD059, 2015CFB451, 2014CFA130, 2012FFA099, 2012FFA134, 2013CF125), the Science and Technique Development Program of He’nan (172102210186), Scientific Research Foundation of Wuhan Institute of Technology (K201713), Graduate Education Innovation Foundation of Wuhan Institute of Technology (CX2017069, CX2017070).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baker, S., Kanade, T.: Hallucinating faces. In: Proceedings of IEEE International Conference on Automatic Face and Gesture Recognition 2000, p. 83 (2002)
Chang, H., Yeung, D., Xiong, Y.: Super-resolution through neighbor embedding. Proc. Comput. Vis. Pattern Recogn. 1, I-275–I-282 (2004)
Cui, Z., Chang, H., Shan, S., Zhong, B., Chen, X.: Deep network cascade for image super-resolution. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 49–64. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_4
Dong, C., Chen, C.L., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295–307 (2016)
Jiang, J., Hu, R., Han, Z., Lu, T., Huang, K.: Position-patch based face hallucination via locality-constrained representation. In: IEEE International Conference on Multimedia and Expo, pp. 212–217 (2012)
Jiang, J., Hu, R., Wang, Z., Han, Z., Ma, J.: Facial image hallucination through coupled-layer neighbor embedding. IEEE Trans. Circuits Syst. Video Technol. 26(9), 1674–1684 (2016)
Jiang, J., Yu, Y., Tang, S., Ma, J., Qi, G.J., Aizawa, A.: Context-patch based face hallucination via thresholding locality-constrained representation and reproducing learning. In: IEEE International Conference on Multimedia and Expo, pp. 469–474 (2017)
Kim, J., Lee, J.K., Lee, K.M.: Accurate image super-resolution using very deep convolutional networks, pp. 1646–1654 (2015)
Liu, C., Shum, H.Y., Freeman, W.T.: Face Hallucination: Theory and Practice. Kluwer Academic Publishers, Dordrecht (2007)
Lu, T., Guan, Y., Chen, D., Xiong, Z., He, W.: Low-rank constrained collaborative representation for robust face recognition. In: IEEE International Workshop on Multimedia Signal Processing, pp. 1–7 (2017)
Lu, T., Xiong, Z., Zhang, Y., Wang, B., Lu, T.: Robust face super-resolution via locality-constrained low-rank representation. IEEE Access 5(99), 13103–13117 (2017)
Ma, X., Huang, H., Wang, S., Qi, C.: A simple approach to multiview face hallucination. IEEE Signal Process. Lett. 17(6), 579–582 (2010)
Ma, X., Zhang, J., Qi, C.: Hallucinating face by position-patch. Pattern Recogn. 43(6), 2224–2236 (2010)
Phillips, P., Moon, H., Rizvi, S., Rauss, P.: The feret evaluation methodology for face-recognition algorithms. IEEE Trans. Pattern Anal. Mach. Intell. 22(10), 1090–1104 (2000)
Romano, Y., Elad, M.: Con-patch: when a patch meets its context. IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. 25(9), 3967–3978 (2016)
Romano, Y., Isidoro, J., Milanfar, P.: RAISR: rapid and accurate image super resolution. IEEE Trans. Comput. Imaging 3(1), 110–125 (2017). https://doi.org/10.1109/TCI.2016.2629284
Rowleys, H.: Neural network-based face detection. IEEE Trans. Pattern Anal. Mach. Intell. 20(1), 23–38 (1998)
Shi, J., Liu, X., Zong, Y., Qi, C., Zhao, G.: Hallucinating face image by regularization models in high-resolution feature space. IEEE Trans. Image Process. PP(99), 1 (2018)
Timofte, R., De, V., Gool, L.V.: Anchored neighborhood regression for fast example-based super-resolution. In: IEEE International Conference on Computer Vision, pp. 1920–1927 (2013)
Timofte, R., De Smet, V., Van Gool, L.: A+: adjusted anchored neighborhood regression for fast super-resolution. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9006, pp. 111–126. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-16817-3_8
Wang, Z., Hu, R., Wang, S., Jiang, J.: Face hallucination via weighted adaptive sparse regularization. IEEE Trans. Circuits Syst. Video Technol. 24(5), 802–813 (2014)
Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process 13(4), 600–612 (2004)
Yang, J., Wright, J., Huang, T.S., Ma, Y.: Image super-resolution via sparse representation. IEEE Trans. Image Process. 19(11), 2861–2873 (2010)
Yang, Z., He, P.: Non-local diffusion weighted image super-resolution using collaborative joint information. Exp. Ther. Med. 15(1), 217–225 (2018)
Zhang, Y., et al.: Collaborative representation cascade for single-image super-resolution. IEEE Trans. Syst. Man Cybern. Syst. PP(99), 1–16 (2017)
Zhang, Y., Zhang, Y., Zhang, J., Wang, H., Dai, Q.: Single image super-resolution via iterative collaborative representation. In: Ho, Y.-S., Sang, J., Ro, Y.M., Kim, J., Wu, F. (eds.) PCM 2015. LNCS, vol. 9315, pp. 63–73. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24078-7_7
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Zeng, K., Lu, T., Li, X., Zhang, Y., Peng, L., Qu, S. (2018). Contextual-Field Supported Iterative Representation for Face Hallucination. In: Vaidya, J., Li, J. (eds) Algorithms and Architectures for Parallel Processing. ICA3PP 2018. Lecture Notes in Computer Science(), vol 11336. Springer, Cham. https://doi.org/10.1007/978-3-030-05057-3_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-05057-3_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-05056-6
Online ISBN: 978-3-030-05057-3
eBook Packages: Computer ScienceComputer Science (R0)