Abstract

The single image super-resolution refers to the process of recovering missing high-resolution details so as to reconstruct a high resolution image(HR) from a single low resolution image (LR). Correspondences between low and high resolution image patches are learned from a database of low and high resolution image pairs, and then applied to a new low-resolution image to recover its most likely high-resolution version. In this paper color image super resolution method is implemented using critically sampled directionlet transform. In this method color image in RGB format is converted to YCbCr format. The luminance component Y alone is super resolved and other two components are interpolated using standard methods. At the end the YCbCr format is converted back to RGB format.

References

• Velisavljevic.V, Beferull-Lozano.B, Vetterly.M., and Dragotti P.L. ”Directionlets: anisotropic multi directional representation with separable filtering”. IEEE Transactions Image Processing, page 19161933, 2006
• http://www.the-digital-picture.com/pictures.
• Ayan.Chakrabarti, Rajagopalan.A.N., and Rama.Chellappa. ”Super-resolution of face images using kernel pca-based prior”. IEEE Transactions on Multimedia, 9(4):888–892, 2007.
• Lin Z.C. Wilburn B Ben-Ezra, M. Penrose pixels: superresolution in the detector layout domain. Proc. ICCV 2007, 2007.
• C.V.Jiji, M.V.Joshi, and Subhasis Chaudhuri. ”Single-frame image super-resolution using learned wavelet coefficients”. International Journal of Imaging Systems and Technology, 14:105–112, 2004.
• Gajjar.P.P and Joshi.M.V. ”Single frame super-resolution: A new learning based approach and use of igmrf prior”. ICVGIP ’08. Sixth Indian Conference on Computer Vision, Graphics and Image Processing, 17:636–643, 2008.
• Isabelle.B and Frank.P.Ferrie. ”Comparison of super-resolution algorithms using image quality measures”. The 3rd Canadian Conference on Computer and Robot Vision, 2006.
• Ashvini A. Tandale; N. D. Kulkarn. Super-resolution of color images using cnn. 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), 2018.
• Lyndsey.Pickup, Stephen.Roberts, and Andrew.Zisserman. ”Optimizing and learning for super resolution”. In Chantler,M.J, Trucco, E. and Fisher, R.B (eds) Proc. British Machine Vision Conf., 3:439–448, 2006.
• Tsai.R.Y and Huang.T.S. ”Multiframe image restoration and registration”. Advances in Computer Vision and Image Processing, 22:317339, 1984.
• William.T.Freeman, Thouis.R.Jones, and Egon.C.Pasztor. ”example-based super-resolution”. IEEE,Image-Based Modeling and Rendering, and Lighting, 82:56–65, 2002.