Topic
Speckle noise
About: Speckle noise is a research topic. Over the lifetime, 8335 publications have been published within this topic receiving 129656 citations.
Papers published on a yearly basis
Papers
More filters
12 Oct 2018
TL;DR: Experimental results show the proposed method that has better performance to retain detail information and suppress Speckle noise, superior to the traditional wavelet transform and contourlet transform method.
Abstract: SAR image enhancement is one of the key issues on SAR image processing. In this paper, a new SAR image enhancement method is presented. Firstly, SAR image is abstracted into a knowledge system by rough sets, and obtained the approximate subsets of the edge and texture respectively. And then the introduction of tetrolet transformation, edge subset and texture subset is so represented sparsely that the signal energy is more concentrated. In Tetrolet transform domain, edge subset is refined by margin adjustment and texture subset is enhanced by threshold method. Finally, the edge and the texture subset processed are inversed by tetrolet transform, and weighted them to obtain the enhanced results. Experimental results show the proposed method that has better performance to retain detail information and suppress Speckle noise, superior to the traditional wavelet transform and contourlet transform method.
10 May 2021
TL;DR: In this paper, the authors developed an optimized Discrete Wavelet Transform (DWT) based on Synergistic Fibroblast Optimization (SFO) algorithm for filtering speckle noise in SAR image which are captured under rough sea condition.
Abstract: Sea surface is rough when the weather condition at sea is rough due to strong wind, waves, swell and storms. Under the rough sea condition, the propagation of radar energy and the subsequent radar coverage is strongly influenced by various atmospheric effects, such as, strong wind, wave height, weather condition, oceanic currents and rainstorms. The identification of ship wakes in Synthetic Aperture Radar (SAR) image under the rough sea condition is viewed as a highly complex task for the real time monitoring and surveillance applications. It becomes a quite big challenge due to coherent radiation of backscattering signals and the multiplicative speckle noise found in SAR images. The objective of this work is to develop an optimized Discrete Wavelet Transform (DWT) based on Synergistic Fibroblast Optimization (SFO) algorithm for filtering speckle noise in SAR image which are captured under rough sea condition. An improved filtering technique is tested with the real time SAR images acquired from European Space Agency (ESA) sentinel scientific data hub and its efficacy is further validated by employing Discrete Radon Transform (DRT) method to detect ship wakes (linear signature) in SAR image under rough sea surface. The performance of SFO based wavelet transform is evaluated and compared with conventional DWT families, namely, daubechies, coiflet, symlet, discrete meyer, biorthogonal and reverse biorthogonal to conduct the better investigation of this study. Investigation of results illustrates the effectiveness of optimized method, in terms of, noise suppression and its implication on radon transform method to localize the identification of ship wakes in SAR imagery.
25 May 2009
TL;DR: In this paper, a target classification algorithm based on C-means and SVM was proposed to suppress speckle noise in feature space, and its back part adopted an SVM classifier to improve classification accuracy in image space.
Abstract: Aim at multiplicative speckle noise and little difference among targets in synthetic aperture radar (SAR) images, a target classification algorithm is proposed based on C-Means and support vector machines (SVMs). Its front part adopts a C-Means clustering method to classify targets and suppress speckle noise in feature space, and its back part adopts an SVM classifier to improve classification accuracy in image space. Experimental results show that this algorithm can reduce the dimension of SVM and have a better classification performance using Ku-band SAR database.
TL;DR: A method for automatic prostate segmentation inTRUS images using support vectors and snake-like contour is presented and the results showed that this new algorithm extracted the prostate boundary with less than 9.3% relative to boundary provided manually by experts.
Abstract: In many diagnostic and treatment procedures for prostate disease accurate detection of prostate boundaries in transrectal ultrasound(TRUS) images is required. This is a challenging and difficult task due to weak prostate boundaries, speckle noise and the short range of gray levels. In this paper a method for automatic prostate segmentation inTRUS images using support vectors and snake-like contour is presented. This method involves preprocessing, extracting Gabor feature, training, and prostate segmentation. Gabor filter bank for extracting the texture features has been implemented. A support vector machine(SVM) for training step has been used to get each feature of prostate and nonprostate. The boundary of prostate is extracted by the snake-like contour algorithm. The results showed that this new algorithm extracted the prostate boundary with less than 9.3% relative to boundary provided manually by experts.
TL;DR: Aimed at imaging technology through scattering medium using electronic holography, a set of image process algorithm is put forward in this article, where every hologram is pre-processed, whose contrast is enhanced.
Abstract: Aimed at imaging technology through scattering medium using fs electronic holography, a set of image process algorithm is put forward. This algorithm can be divided into three stages. First, every hologram is pre-processed, whose contrast is enhanced. Second, the first-order spatial spectrum is low-pass-filtered through a two-step process, so that high-frequency noise can be removed. Finally, many reconstructed images are ensemble-averaged. This stage can smooth random noise and is advantageous to restraining the speckle noise of image. The operation of this algorithm shows that all of processes in the three stages have obvious effects on improving image quality.