An accelerated super resolve stood on manufactured edge component and an adaptive leclerc function
暂无分享,去创建一个
Because the algorithm has less complexity and fast executed time, the Super Resolve algorithm, which is one of the famous Super Resolution algorithms, for applying on single image (so called SISR or Single Image Super Resolve) is extremely wanted in the image processing field hence this analytic paper aims to propose the spatial expanding algorithm is formed on the Super Resolve algorithm employed by a robust adaptive Leclerc function and manufactured edge component. Although this Super Resolve algorithm can create an image with superior spatial resolution, the SR performance is extremely hang on the control function, which is controlled by three constants (b, h, k) and the constant adjustment for finding optimized values is demanding computational step for creating a superior spatial resolution image with the highest PSNR. In consideration of fixing of this issue, the robust adaptive Leclerc function, which is theoretically controlled by only one constant (T), instead of three constants of the ingenious function, is substituted in the SISR framework. Under testing on 14 traditional standard images with many noise templates, the proposed accelerated super resolve algorithm can create the high spatial resolution image with superior quality (PSNR) to the original super resolve algorithm in the experimental testing section however the constant alteration procedure of the proposed accelerated super resolve algorithm (using one constant) is more ease and rapid than the original super resolve algorithm (using three constants) thereby the proposed accelerated super resolve algorithm can be easily implemented.
[1] Michael J. Black,et al. On the unification of line processes, outlier rejection, and robust statistics with applications in early vision , 1996, International Journal of Computer Vision.
[2] Edward H. Adelson,et al. The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..
[3] Gerd Ascheid,et al. A performance impact of an edge kernel for the high-frequency image prediction reconstruction , 2014, 2014 14th International Symposium on Communications and Information Technologies (ISCIT).