Structure-Adaptive Fuzzy Estimation for Random-Valued Impulse Noise Suppression

Abstract

Noise detection accuracy is crucial in suppressing random-valued impulse noise. Both false and miss detections determine the final estimation performance. Deterministic detection methods, which distinctly classify pixels into noisy or uncorrupted pixels, tend to increase the estimation error because some uncorrupted edge points are hard to discriminate from the random-valued impulse noise points. This paper proposes an iterative Structure-adaptive Fuzzy Estimation (SAFE) for random-valued impulse noise suppression. This SAFE method is developed in the framework of Gaussian Maximum Likelihood Estimation (GMLE). The structure-adaptive fuzziness is reflected by two structure-adaptive metrics based on pixel reliability and patch similarity, respectively. The reliability metric for each pixel (as noise free) is estimated via a novel Minimal Path Based Structure Propagation (MPSP) to give full consideration of the spatially varying image structures. A robust iteration stopping strategy is also proposed by evaluating the re-estimation error of the uncorrupted intensity information. Comparative experiment results show that the proposed structure-adaptive fuzziness can lead to effective restoration. Efficient implementation of this SAFE method is also realized via GPU (Graphic Processing Unit)-based parallelization.

A Rigid Motion Artifact Reduction Method for CT Based on Blind Deconvolution

“…As one of the important technologies in medical diagnosis, a CT image can achieve a high performance in detecting and measuring small lesions [1,2]. However, CT has a problem that the reconstructed image will suffer from motion artifacts if a moving object is reconstructed without motion correction, in severe cases resulting in false diagnosis [3]. To reduce motion artifacts, the main approaches are shortening the scan time [4,5], external motion monitoring techniques [6][7][8], and motion estimation and compensation methods [9].…”

Artifact Removal using Improved GoogLeNet for Sparse-view CT Reconstruction

“…Chen et al . 14 , 15 proposed a new sinogram restoration approach (Sinogram Discriminative Feature Representation) to improve projection data inconsistency. Lee et al .…”

Fuzzy averaging filter for impulse noise reduction in colour images with a correction step

“…Recently, detect and replace approaches, also called switching filters, have become the most popular techniques to reduce impulse noise in colour images because of their simplicity, computational efficiency and high performance [1]- [12]. The most advanced approaches in this family have evolved to a little less efficient methods that try to improve performance by adapting the local region under processing [13,14]. All these methods use a crisp threshold based decision and their performance is critically influenced by the threshold setting.…”

“…Also, other important families of filters are the Total Variation filters [27,28] and, in particular, the machine learning and deep learning approaches [29,30,31,33]. Among the latter, we can find the use of deep convolution neural networks (CNN) for image restoration in color images [29], the combination of deep CNN and residual learning for Gaussian noise removal, the application of semi-supervised learning on big image data for impulse noise removal in gray-scale images [13,32], and a new strategy for building adaptive neuro-fuzzy systems for impulse noise removal [33].…”