An Image Filter Based on Improved Shearlet Transformation
Qingfeng Xia, Yan Zhang, Shuting Zeng · Advances in engineering research/Advances in Engineering Research · 2015
Image restoration processing is to rebuild or restore original images with some prior knowledge according to given degraded images or noise-polluted images.This paper proposed an image filter algorithm based on improved Shearlet Transformation.Firstly, it adopted classical Shearlet Transform to decompose noised image into many sub-wavelets under multi-scale and multi-orientation.Secondly, it weighted each sub-wavelets obtained in first step.Then, by classical Shearlet inverse Transform, a new composite image created which composed from those weighted sub-wavelets.Experimental results shown that proposed algorithm eliminates noise effectively and yields good Peak Signal Noise Ratio (PSNR).