An Improved Iterative Back Projection Based Single Image Super Resolution Approach

Abstract

In this paper, an effort is made to propose an effective image super resolution (SR) approach to recover a high resolution (HR) image from a single low resolution (LR) image. This approach is based on an iterative back projection (IBP) method with the edge preserving infinite symmetric exponential filter (ISEF) and difference image. Amalgamation of ISEF and difference image provides high frequency information. This approach is applied on different type of images and compared results with different existing image SR approaches. Simulation results demonstrate that proposed approach can more precisely enlarge the LR image. This proposed approach decreases mean square error (MSE) and mean absolute error (MAE) and increases the peak signal-to-noise ratio (PSNR) significantly compared to other existing approaches.

Untitled

“…5(a) and 5(b), the proposed method has allocated a higher numerical result (SSIM) for all values of λ. Half-quadratic method also shows an appropriate behavior, but it ranks second in terms of performance. In general, 1 L +BTV and 2 L +BTV methods are ranked 3 rd and 4 th , respectively. Fig.…”

“…In SR literature, reconstruction-based algorithms are well developed in spatial domain. This can be due to their less sensitivity to errors and also more capability in incorporating prior knowledge about the HR image than the frequency domain [1]. The iterative back projection (IBP) [2], non-uniform interpolation [3], and the projection onto convex sets (POCS) [4] are such as non-statistical spatial domain approaches.…”