Abstract In this paper, the novel multiple-view face hallucination method was proposed. This method is reconstructed the high-resolution face images in various poses (normal, up, down, left, and right) from a single low-resolution face image within theseposes. There are two steps in our proposed method. In the first step, a high-resolution face image in the same view of the observation is reconstructed by the position-patch face hallucination framework with the improved Locally Linear Embedding (LLE), which the number of neighbours is adaptive. In the second step, the reconstructed image is used to generate the high- resolution of the other views by the novel tensor regression technique. The experimental results on the well-known dataset show that the proposed method can achieve the better quality image than the baseline methods.

References

[1]ChakrabartiA.,Rajagopalan N., andChellappa R., Super-Resolution of Face Images Using Kernel PCA-Based Prior, IEEE Transactions on Multimedia,vol. 9,no. 4,pp. 888-892, 2007.

[2]BelhumeurP., HespanhaJ., and KriegmanD., Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection, IEEE Transactions on Pattern Analysis and Machine Intelligence,vol. 19,no. 7,pp. 711-720, 1997.

[3]LiuC.,ShumH.,andZhangC., ATwo-step ApproachtoHallucinating Faces:Global Parametric ModelandLocalNonparametric Model, inProceedings of IEEE Computer Society Conference onComputer Vision and Pattern Recognition, pp. 192-198,2001.

[4]Elad M. and Feuer A., Restoration of aSingle Superresolution ImagefromSeveral Blurred, Noisy, andUndersampled Measured Images, IEEE Transactions onImage Processing,vol. 6, no .12,pp. 1646-1658, 1997.

[5]Farsiu S., Elad M., and Milanfar P., Multiframe DemosaicingandSuper-ResolutionofColor Images, IEEE Transactions onImage Processing,vol. 15,no. 1,pp.141-159, 2006.

[6]Farsiu S., Robinson D., Elad M., and Milanfar P., Fast andRobust Multiframe Super Resolution, IEEE Transactions onImage Processing,vol. 13, no. 10,pp. 1327-1344, 2004.

[7]Freeman T. and Pasztor C., LearningLow-Level Vision, inProceedings of the 7thIEEE International Conference onComputer Vision, Cambridge,pp. 1182-1189,1999.

[8]Shen H. and Li S., Hallucinating Faces by Interpolation and Principal Component Analysis, inProceedings of the2ndInternational Symposium onComputational Intelligence and Design,Changsha,pp. 295-298, 2009.

[9]Irani M. and Peleg S., ImprovingResolutionby Image Registration, CVGIP: Graph. Models Image Processing,vol. 53,no. 3,pp. 231-239, 1991.

[10]LiuJ.,QiaoJ.,Wang X.,andYujunL., Face Hallucinationbased onIndependent Component Analysis, inProceedings ofIEEE International Symposium onCircuits and Systems,Seattle,pp. 3242-3245, 2008.

[11]WuJ. and Trivedi M., A Regression Model in TensorPCA Subspacefor Face Image Super- resolution Reconstruction, inProceedings ofthe 18thInternational Conference onPattern Recognition,Hong Kong, pp. 627-630, 2006.

[12]JiaK. andGong S., Generalized Face Super- Resolution, IEEE Transactions onImage Processing,vol. 17,no. 6,pp. 873-886, 2008.

[13]LiuC., Shum Y., and Freeman T., Face Hallucination:TheoryandPractice, International Journal of Computer Vision,vol. 75,no. 1,pp. 115-134, 2007.

[14]Penev S. and Sirovich L., TheGlobal DimensionalityofFace Space, inProceedings of the 4thIEEE International Conference on Automatic Face and Gesture Recognition, Grenoble,pp. 264-270, 2000.

[15]Roweis S. and Saul L., Nonlinear Dimensionality ReductionbyLocally Linear Embedding, Science,vol. 290,no. 5500,pp. 2323-2326, 2000.

[16]Sanguansat P., Face Hallucination Using Bilateral-Projection-Based Two-Dimensional Principal Component Analysis, inProceedings ofInternational Conference onComputer and Electrical Engineering,pp. 876-880, 2008.

[17]Shah H., Sharif M., Raza M., and AzeemA., A Survey: Linear and Nonlinear PCA Based Face Recognition Techniques, TheInternational Arab Journal of Information Technology,vol. 10, no. 6,pp. 536-545, 2015.

[18]Trussell J. and Hartwig E., Mathematics for Demosaicking, IEEE Transactions onImage Processing,vol. 11,no. 4,pp. 485-492, 2002.

[19]Turk A. and Pentland P., FaceRecognition usingEigenfaces, inProceedings of theIEEE Computer Society Conference onComputer Vision and Pattern Recognition, pp. 586-591, 1991.

[20]Liu W., Lin D., and Tang X., Hallucinating Faces: TensorPatchSuper-Resolutionand Coupled Residue Compensation, available at: http://mmlab.ie.cuhk.edu.hk/archive/2005/01467 480.pdf, last visited 2005.

[21]Gao W., CaoB.,ShanS.,ChenX.,ZhouD., ZhangX.,and ZhaoD., The CAS-PEAL Large- Scale Chinese Face Database and Baseline Evaluations, IEEE Transactions onSystems, Man and Cybernetics, Part A: Systems and Humans,vol. 38,no. 1,pp. 149-161, 2008.

[22]Ma X.,HuangH.,WangS., andQi C., A Simple Approach to Multiview Face Hallucination, IEEESignal Processing Letters, vol. 17,no. 6,pp. 579-582, 2010.

[23]MaX.,ZhangJ.,and QiC., Position-basedFace Hallucination Method, inProceedings ofIEEE International Conference onMultimedia and Expo,New York,pp. 290-293, 2009,

[24]WangX. andTangX., HallucinatingFaceby Eigentransformation, IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews,vol. 35,no. 3,pp. 425- 434, 2005. 666The International Arab Journal of Information Technology, Vol. 13, No. 6, November 2016

[25]Yan H., Liu J., Sun J., and Sun X., ICA Based Super-Resolution Face Hallucination and Recognition, inProceedings of the4th International Symposium on Neural Networks, Nanjing,pp. 1065-1071.

[26]LiY. andLinX., AnImproved Two-Step ApproachtoHallucinating Faces, in Proceedings of the 3rdInternational Conference onImage and Graphics,Hong Kong,pp. 298- 301, 2004.

[27]LinZ. andShumH., Fundamental limits of Reconstruction-basedSuperresolution Algorithms Under Local Translation, IEEE Transactions onPattern Analysis and Machine Intelligence,vol. 26,no. 1,pp. 83-97, 2004. ParinyaSanguansatreceivedhis BEng, MEng and PhD degrees in Electrical Engineering from the Chulalongkorn University, Thailand, in 2001, 2004 and2007respectively. He is an assistant professor in the Faculty of Engineering and Technology, Panyapiwat Institute ofManagement, Thailand. His research areas are machine learning, image processing, digital signalprocessing in pattern recognition includingonlinehandwritten recognition, face and automatic targetrecognition.