Hybrid-Thresholding based Image Super-Resolution Technique by the use of Triplet Half-Band Wavelets

This paper presents a modified image super-resolution scheme based on the wavelet coefficients hybrid-thresholding by the use of triplet half-band wavelets (THW) derived from the generalized half-band polynomial. At first, discrete wavelet transform (DWT) is obtained from triplet half-band kernels and it applied on the low-resolution image to obtain the high frequency sub-bands. These high frequency sub-bands and the original low-resolution image are interpolated to enhance the resolution. Second, stationary wavelet transform is obtained by using THW, which is employed to minimize the loss due to the use of DWT. In addition, hybrid thresholding scheme on wavelet coefficients scheme is proposed on these estimated high-frequency sub-bands in order to reduce the spatial domain noise. These sub-bands are combined together by inverse discrete wavelet transform obtained from THW to generate a high-resolution image. The proposed approach is validated by comparing the quality metrics with existing filter banks and well-known super-resolution scheme.

[1]  Truong Q. Nguyen,et al.  Optimal Design of FIR Triplet Halfband Filter Bank and Application in Image Coding , 2011, IEEE Transactions on Image Processing.

[2]  Hui Ji,et al.  Robust wavelet-based super-resolution reconstruction: theory and algorithm. , 2009, IEEE transactions on pattern analysis and machine intelligence.

[3]  H. Demirel,et al.  Image Super Resolution Based on Interpolation of Wavelet Domain High Frequency Subbands and the Spatial Domain Input Image , 2010 .

[4]  Peyman Milanfar,et al.  A wavelet-based interpolation-restoration method for superresolution (wavelet superresolution) , 2000 .

[5]  Marimuthu Palaniswami,et al.  A novel approach to the design of the class of triplet halfband filterbanks , 2004, IEEE Transactions on Circuits and Systems II: Express Briefs.

[6]  Rashid Ansari,et al.  Structure and design of two-channel filter banks derived from a triplet of halfband filters , 1999 .

[7]  Michal Irani,et al.  Motion Analysis for Image Enhancement: Resolution, Occlusion, and Transparency , 1993, J. Vis. Commun. Image Represent..

[8]  P. P. Vaidyanathan,et al.  A new class of two-channel biorthogonal filter banks and wavelet bases , 1995, IEEE Trans. Signal Process..

[9]  Shing-Chow Chan,et al.  On the design and multiplierless realization of perfect reconstruction triplet-based FIR filter banks and wavelet bases , 2004, IEEE Transactions on Circuits and Systems I: Regular Papers.

[10]  Gholamreza Anbarjafari,et al.  IMAGE Resolution Enhancement by Using Discrete and Stationary Wavelet Decomposition , 2011, IEEE Transactions on Image Processing.

[11]  Nirmal K. Bose,et al.  Superresolution with second generation wavelets , 2004, Signal Process. Image Commun..

[12]  Hua Han,et al.  Wavelet-domain HMT-based image super-resolution , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[13]  Manjunath V. Joshi,et al.  Single‐frame image super‐resolution using learned wavelet coefficients , 2004, Int. J. Imaging Syst. Technol..

[14]  Manjunath V. Joshi,et al.  New Learning Based Super-Resolution: Use of DWT and IGMRF Prior , 2010, IEEE Transactions on Image Processing.

[15]  Vikram M. Gadre,et al.  On the Design of FIR Wavelet Filter Banks Using Factorization of a Halfband Polynomial , 2008, IEEE Signal Processing Letters.

[16]  Nirmal K. Bose,et al.  Simultaneous noise filtering and super-resolution with second-generation wavelets , 2005, IEEE Signal Processing Letters.

[17]  Raghunath S. Holambe,et al.  Half-Iris Feature Extraction and Recognition Using a New Class of Biorthogonal Triplet Half-Band Filter Bank and Flexible k-out-of-n:A Postclassifier , 2012, IEEE Transactions on Information Forensics and Security.