CROSS STYLE IMAGE SYNTHESIS THROUGH SEMI COUPLED DICTIONARY LEARNING AND GENERALIZED CROSS VALIDATION ALGORITHM
DOI:
https://doi.org/10.55766/sujst-2023-06-e0850Keywords:
Compressed sensing, Cross style image processing, Dictionary learning, Semi Coupled Dictionary Learning, Generalized Cross ValidationAbstract
In various Computer vision applications for better visualization, interpretation and better recognition, we frequently want to change an image in one style into another one which is a large research area of compressive sensing. Algorithms on compressed sensing are in demand to create better reconstruction of the images while taking less computational time and requiring less storage capacity. In the present work attempts are put in the same direction and brought an algorithm which includes semi coupled dictionary learning (SCDL) model of compressed sensing with Singular Value Decomposition (SVD) based Generalized Cross Validation (GCV) algorithm. Using this algorithm one can find the different value of regularization parameters for different sizes of images and that helps to get better reconstruction of the images with ease while doing experiments on cross style image synthesis problems.
References
Hou H.S., and Andrews H.C. (1978). Cubic spline for image interpolation and digital filtering. IEEE Transaction on Signal Pressing, 26(6):508-517.
Stark H., and Oskoui P. (1989). High resolution image recovery from image-plane arrays, using convex projections. Opt. Soc. Am A., 6(11):1,715-1,726.
Irani M., and Peleg S. (1991). Improving resolution by image registration. CVGIP: Graphical Models and Image Processing, 53(3):231-239.
Nhat N., Milanfar P., and Golub G. (2001). A Computationally efficient super resolution image reconstruction algorithm. IEEE Transactions on Image Processing, 10(4):573-583.
Li X. and M. Orchard. (2001). New edge directed interpolation. IEEE Trans on IP, 10(10):1,521-1,527.
Zhang X., and ad X. Wu. (2008). Image interpolation by adaptive 2-d autoregressive modeling and soft-decision estimation. IEEE Trans on IP, 17(6):887-896.
Mallat S. and G. Yu. (2010). Super resolution with sparse mixing estimators. IEEE Trans on IP, 19(11):2,889-2,900.
Hertzmann, C. Jacobs, N. Oliver, B. Curless, and D. Salensin Image analogies. In SIGGRAPH, 327-340.
Efros and W. T. Freeman. (2011). Image quilting for texture synthesis and transfer. In SIGGRAPH, 1(2).
Lin D. and X. Tang. (2005). Coupled space learning of image style transformation. In ICCV. IEEE, 1-4.
Wang X. and X. Tang. (2008). Face photo-sketch synthesis and recognition. IEEE Trand on PAMI, 1,955-1,967.
Lei Z. and S. Li. (2009). Coupled spectral regression for matching heterogeneous faces. In CVPR. IEEE, 1-2.
Sharma and D. Jacobs. (2011). By passing synthesis: PIS fir face recognition with pose, low-resolution and sketch. IN CVPR. IEEE, 1-2.
Yang J., J. Wright, T. Huang, and Y. Ma. (2010). Image super resolution via sparse representation. IEEE Trans on IP, 19(11):2,861-1,873.
Belgaonkar Sanjay M, Vipula Singh, ‘Image compression and reconstruction in compressive sensing paradigm‘, Global Transitions Proceedings 3 (2022) 220–224.
Yang J., Wright J., and Huang T. (2008). Image super resolution as sparse representation of raw image patches. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Anchorage, USA.
Wang S., Zhang L., and Liang Y. (2012). Semi coupled dictionary learning with applications to image super resolution and photo-sketch synthesis. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Providence, USA.
Shravya S., Goklani, Hemant S., and Jignesh N. Sarvaiya. (2016). Image Super-Resolution using Single Image Semi Coupled Dictionary Learning. International Journal of Image Processing (IJIP), 10.3(2016):135.
Kowsalya G., A., Hepzibah Christinal, D., Abraham Chandy, S. Jebasingh, and Chandrajit L. Bajaj (2021). Analysis of the Measurement Matrix in Directional Predictive Coding for Compressive Sensing of Medical Images. Electronic Letters on Computer Vision and Image Analysis. 20(2):102-113.
Hastie T., and Efron B., Johnstona I. (2004). Least angle regression. The Annals of Statistics, 32(2):407-499.
Yang M., Zhang L., Yang J., and Zhang D. (2010). Metaface learning for sparse representation base face recognition. In ICIP, 2010:1,601-1,604.
Jiehua Zhu, and Xiezhang L. (2019). A Smoothed 𝑙0-Norm and 𝑙1-Norm Regularization Algorithm for Computed Tomography. Hindawi Journal of Applied Mathematics, 8398035.
Golub, G.H., and Luk, F.T. (1979a). Singular Value decomposition: application and computations Transactions of the Twenty-Second Conference of Army Mathematicians, 577-605.
Hemmerle, W.J. (1975). An explicit solution for generalized ridge regression. Technometrics, 17:309-313.
Gene H. Golub, Michael Heath and Grace (1979b). Wahba, Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter. Technometrics, 21(2):215-223.
Horel, A.E. and Kennard, R.W. (1976). Ridge Regression: iterative estimation of the biasing parameter. Comm. In Statist, 4:105-123.
Marquardt, D.W. (1970). Generalized Inverses, ridge regression, biased linear estimation and nonlinear estimastion. Technometrics, 12:591-64.
Swindel, B.F. (1976). Good Ridge Estimators based on prior information. Comm. In S Statist., A5:985-997.
Wahaba, G. (1976). A-survey of some smoothing problems and the method of generalized cross-validation for solving them. Proceedings of the Conference on the Applications of Statistics. Dayton, Ohio. Edited by: Krishnaiah, P.R., June 14-17.
