Bidirectional texture function image super-resolution using singular value decomposition

2017 ◽  
Vol 56 (10) ◽  
pp. 2745 ◽  
Author(s):  
Wei Dong ◽  
Hui-Liang Shen ◽  
Zhi-Wei Pan ◽  
John H. Xin
Author(s):  
suryanarayana gunnam ◽  
Ravindra Dhuli

Purpose The purpose of this paper is to present an improved wavelet based approach in single image super resolution (SISR). The proposed method generates high resolution (HR) images by preserving the image contrast and edges simultaneously. Design/methodology/approach Covariance based interpolation algorithm is employed to obtain an initial estimate of the unknown HR image. The proposed method preserves the image contrast, by applying singular value decomposition (SVD) based correction on the dual-tree complex wavelet transform (DT-CWT) coefficients. In addition, the dual operating mode diffusion based shock filter (DBSF) ensures noise mitigation and edge preservation. Findings Experimental results on various test images reveal superiority of the proposed method over the existing SISR techniques in terms of peak signal to noise ratio (PSNR), structural similarity index measure (SSIM) and visual quality. Originality/value With SVD based correction, the proposed method preserves the image contrast and also the DBSF operation helps to achieve sharper edges.


2015 ◽  
Vol 65 (6) ◽  
pp. 459 ◽  
Author(s):  
K. Joseph Abraham Sundar ◽  
V. Vaithiyanathan ◽  
M. Manickavasagam ◽  
A.K. Sarkar

<p>The singular value decomposition (SVD) plays a very important role in the field of image processing for applications such as feature extraction, image compression, etc. The main objective is to enhance the resolution of the image based on Singular Value Decomposition. The original image and the subsequent sub-pixel shifted image, subjected to image registration is transferred to SVD domain. An enhanced method of choosing the singular values from the SVD domain images to reconstruct a high resolution image using fusion techniques is proposesed. This technique is called as enhanced SVD based fusion. Significant improvement in the performance is observed by applying enhanced SVD method preceding the various interpolation methods which are incorporated. The technique has high advantage and computationally fast which is most needed for satellite imaging, high definition television broadcasting, medical imaging diagnosis, military surveillance, remote sensing etc.</p>


Sign in / Sign up

Export Citation Format

Share Document