Abstract
In real-world surveillance scenario, the face recognition (FR) systems pose a lot of challenges due to the captured low-resolution (LR) and noisy probe images. A new face super-resolution (SR) algorithm is proposed to design a recognition model overcoming the challenges of existing FR systems. The proposed SR algorithm inherits the merits of functional-interpolation and dictionary-based SR techniques. The functional interpolation assists in generating more discriminable output, whereas the dictionary-based approach assists in eliminating noise effects from the reconstruction process. Consequently, it produces more discriminable and noise-free high-resolution (HR) images from captured noisy LR probe images, suitable for real-world problems like low-resolution face recognition. The results obtained from the experiments performed on several popular face image datasets including FEI, FERET, and CAS-PEAL-R1 show that the proposed algorithm performs better than all the comparative SR methods.
Similar content being viewed by others
Notes
Note: the pixels of output HR face which are reconstructed using the proposed SR algorithm are named as interpolated (or missing) HR pixels. We are also used the same terminology to represent the corresponding pixels in HR training faces for simplicity.
The method in [12] generates two types of output for each noisy input image i.e., outlier vector (detected noisy pixels) and filtered image. The proposed method utilizes only outlier vector in the reconstruction while it is entirely away from filtered images.
Θ is the binary vector in which value 0 and 1 assigned to noisy and clean pixel respectively.
Note that source code of this paper is available on email to ershyamrajput@gmail.com
References
Abdi H., Williams L. J. (2010) Principal component analysis. Wiley Interdiscip Rev Comput Stat 2(4):433–459
Biswas S., Bowyer K. W., Flynn P. J. (2012) Multidimensional scaling for matching low-resolution face images. IEEE Transactions on Pattern Analysis and Machine Intelligence 34(10):2019–2030
Chakrabarti A., Rajagopalan A. N., Chellappa R. (2007) Super-resolution of face images using kernel pca-based prior. IEEE Transactions on Multimedia 9(4):888–892
Chang H., Yeung D. Y., Xiong Y. (2004) Super-resolution through neighbor embedding. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1, pp. 1–8
Chen C. L. P., Liu L., Chen L., Tang Y. Y., Zhou Y. (2015) Weighted couple sparse representation with classified regularization for impulse noise removal. IEEE Trans Image Process 24(11):4014–4026
Chu Y., Ahmad T., Bebis G., Zhao L. (2017) Low-resolution face recognition with single sample per person. Signal Process 141:144–157
Dong C., Loy C. C., He K., Tang X. (2016) Image super-resolution using deep convolutional networks. IEEE T Pattern Anal 38(2):295–307
Gao W., Cao B., Shan S., Chen X., Zhou D., Zhang X., Zhao D. (2008) The cas-peal large-scale chinese face database and baseline evaluations. IEEE T Syst Man Cy A 38(1):149–161
Hennings-Yeomans P. H., Baker S., Kumar B. V. K. V. (2008) Simultaneous super-resolution and feature extraction for recognition of low-resolution faces. In: IEEE Conference on computer vision and pattern recognition, pp. 1–8
Hoerl A. E., Kennard R. W. (1970) Ridge regression: Biased estimation for nonorthogonal problems. Technometrics 12(1):55–67
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
Hwang H., Haddad R. A. (1995) Adaptive median filters: new algorithms and results. IEEE T Image Process 4(4):499–502
Jafar I. F., AlNa’mneh R. A., Darabkh K. A. (2013) Efficient improvements on the bdnd filtering algorithm for the removal of high-density impulse noise. IEEE T Image Process 22(3):1223–1232
Jiang J., Chen C., Huang K., Cai Z., Hu R. (2016) Noise robust position-patch based face super-resolution via tikhonov regularized neighbor representation. Information Sciences 367–368:354 –372
Jiang J., Chen C., Ma J., Wang Z., Wang Z., Hu R. (2017) Srlsp: a face image super-resolution algorithm using smooth regression with local structure prior. IEEE T Multimedia 19(1):27–40
Jiang J., Hu R., Liang C., Han Z., Zhang C. (2014) Face image super-resolution through locality-induced support regression. Signal Process 103:168–183
Jiang J., Hu R., Wang Z., Cai Z. (2016) Cdmma: Coupled discriminant multi-manifold analysis for matching low-resolution face images. Signal Process 124:162–172
Jiang J., Hu R., Wang Z., Han Z. (2014) Face super-resolution via multilayer locality-constrained iterative neighbor embedding and intermediate dictionary learning. IEEE T Image Process 23(10):4220–4231
Jiang J., Hu R., Wang Z., Han Z. (2014) Noise robust face hallucination via locality-constrained representation. IEEE T Multimedia 16(5):1268–1281
Jiang J., Ma J., Chen C., Jiang X., Wang Z. (2016) Noise robust face image super-resolution through smooth sparse representation. IEEE T Cybernetics 47 (11):3991–4002
Jiang J., Wang Z., Chen C., Lu T. (2016) L1-l1 norms for face super-resolution with mixed gaussian-impulse noise. In: 2016 IEEE International conference on acoustics, speech and signal processing ICASSP, pp. 2089–2093
Jiang J., Yu Y., Tang S., Ma J., Qi G. J., Aizawa A. (2017) Context-patch based face hallucination via thresholding locality-constrained representation and reproducing learning. In: 2017 IEEE International conference on multimedia and expo ICME, pp. 469–474
Jiang J, Hu R, Han Z, Wang Z, Chen J (2013) Two-step superresolution approach for surveillance face image through radial basis function-partial least squares regression and locality-induced sparse representation. Journal of Electron Imaging 22 (4):11–20
Li B., Chang H., Shan S., Chen X. (2010) Low-resolution face recognition via coupled locality preserving mappings. IEEE Signal Processing Letters 17(1):20–23
Li X., Orchard M. T. (2001) New edge-directed interpolation. IEEE T Image Process 10(10):1521–1527
Liu L., Chen C. L. P., Li S., Tang Y. Y., Chen L. (2017) Robust face hallucination via locality-constrained bi-layer representation. IEEE T Cybernetics 18 (4):1189–1201
Liu L., Chen C. P., Zhou Y., You X. (2015) A new weighted mean filter with a two-phase detector for removing impulse noise. Inf Sci 315:1–16
Liu L., Chen L., Chen C. L. P., Tang Y. Y., pun C. M. (2017) Weighted joint sparse representation for removing mixed noise in image. IEEE T Cybernetics 47 (3):600–611
Lu T., Xiong Z., Zhang Y., Wang B., Lu T. (2017) Robust face super-resolution via locality-constrained low-rank representation. IEEE Access 5:13103–13117
Ma J., Qiu W., Zhao J., Ma Y., Yuille A. L., Tu Z. (2015) Robust l2 e estimation of transformation for non-rigid registration. IEEE T Signal Processing 63 (5):1115–1129
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
Ma X., Zhang J., Qi C. (2010) Hallucinating face by position-patch. Pattern Recogn 43(6):2224–2236
Neves J., Narducci F., Barra S., Proenċa H. (2016) Biometric recognition in surveillance scenarios: a survey. Artif Intell Rev 46(4):515–541
Nguyen K., Fookes C., Sridharan S., Tistarelli M., Nixon M. (2018) Super-resolution for biometrics: a comprehensive survey. Pattern Recogn 78:23–42
Park J. S., Lee S. W. (2008) An example-based face hallucination method for single-frame, low-resolution facial images. IEEE T Image Process 17(10):1806–1816
Phillips P. J., Moon H., Rauss P., Rizvi S. A. (1997) The feret evaluation methodology for face-recognition algorithms. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 137–143
Rajput S. S., Arya K. V. (2019) Noise robust face hallucination via outlier regularized least square and neighbor representation. IEEE Transactions on Biometrics Behavior, and Identity Science 1(4):252–263
Rajput S. S., Arya K. V., Bohat V. K. (2019) Face image super-resolution using differential evolutionary algorithm. In: Verma N.K., Ghosh A.K. (eds) Computational Intelligence: Theories, Applications and Future Directions - Volume II, pp. 635–644. Springer Singapore
Rajput S. S., Bohat V. K., Arya K. V. (2018) Grey wolf optimization algorithm for facial image super-resolution Applied Intelligence
Rajput S. S., Singh A., Arya K.V., Jiang J. (2018) Noise robust face hallucination algorithm using local content prior based error shrunk nearest neighbors representation. Signal Processing 147:233–246
Roweis S. T., Saul L. K. (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326
Thomaz C. E., Giraldi G. A. (2010) A new ranking method for principal components analysis and its application to face image analysis. Image Vis Comput 28 (6):902–913
Wang X., Tang X. (2005) Hallucinating face by eigentransformation. IEEE T Syst Man Cy C 35(3):425–434
Wang Z., Liu D., Yang J., Han W., Huang T. (2015) Deep networks for image super-resolution with sparse prior. In: 2015 IEEE International conference on computer vision ICCV, pp. 370–378
Wright J., Yang A. Y., Ganesh A., Sastry S. S., Ma Y. (2009) Robust face recognition via sparse representation. IEEE T Pattern Anal 31(2):210–227
Xiao Y., Zeng T., Yu J., Ng M. K. (2011) Restoration of images corrupted by mixed gaussian-impulse noise via l1 l0 minimization. Pattern Recogn 44(8):1708–1720
Xing R., Fu J., Shao Y., You J. (2014) Rigid regression for facial image interpolation with local structure prior. In: 2014 Sixth international conference on intelligent human-machine systems and cybernetics, vol. 2, pp. 67–70
Xing X., Wang K. (2016) Couple manifold discriminant analysis with bipartite graph embedding for low-resolution face recognition. Signal Process 125:329–335
Zhang L., Wu X. (2006) An edge-guided image interpolation algorithm via directional filtering and data fusion. IEEE T Image Process 15(8):2226–2238
Zhang X., Peng S., Jiang J. (2008) An adaptive learning method for face hallucination using locality preserving projections. In: 2008 8Th IEEE international conference on automatic face gesture recognition, pp. 1–8
Zhang X., Wu X. (2008) Image interpolation by adaptive 2-d autoregressive modeling and soft-decision estimation. IEEE T Image Process 17(6):887–896
Zou W. W. W., Yuen P. C. (2012) Very low resolution face recognition problem. IEEE T Image Process 21(1):327–340
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix A
The matrix form of Eq. (1) is given below:
where GL (a,b) is the matrix in which each column correspond to one LR dictionary patch. After multiply Θ(a, b) with each element we obtain,
where \( \ddot {P^{L}}(a,b) = {\varTheta }(a,b) \odot P^{L}(a,b)\) and \( \ddot {G^{L}}(a,b) = {\varTheta }(a,b) \odot G^{L}(a,b)\).
Following [4, 32, 40], (13) can be simplified as:
where term ones(N, 1) denotes column vector of value one (or 1), operator “∖” is the left matrix devision, and C(a, b) denotes covariance matrix for PL(a, b) which is calculated as:
where J = PL(a, b)ones(N, 1)T −GL(a, b). Finally, obtained weights are rescaled to satisfy \(\sum \limits _{n = 1}^{N} {{w_n}(a,b)} = 1\).
Appendix B
Since the objective function given in (9) is convex w.r.t.Λ, the optimal Λ∗ is obtain by taking its derivative w.r.t. Λ as follows:
To make term GLΓGLT invertible (non-singular), by following [10], we add a small constant value λ to the diagonal elements of the matrix GLΓGLT before taking its inverse. Thus we have,
For our experiments, the λ is set to small constant value 10− 6.
Rights and permissions
About this article
Cite this article
Rajput, S.S., Arya, K.V. A robust face super-resolution algorithm and its application in low-resolution face recognition system. Multimed Tools Appl 79, 23909–23934 (2020). https://doi.org/10.1007/s11042-020-09072-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09072-5