Earticle

Background: This study systematically compared the performances of fast non-local means (FNLM), conventional non-local means (NLM), and adaptive non-local means (ANLM) algorithms for Rician noise reduction in clinical breast magnetic resonance imaging (MRI). Materials and Methods: Rician noise with standard deviations of 0.05, 0.10, and 0.15 was synthetically introduced into pre-contrast T1-weighted breast MRI images obtained from 50 patients in a publicly available clinical dataset. For each noise level, the FNLM search window size was optimized using a root mean square error (RMSE)-based tuning procedure. The optimized FNLM was then quantitatively compared with NLM and ANLM. Image quality was assessed using RMSE, structural similarity index (SSIM), high-frequency error norm (HFEN), gradient magnitude similarity deviation, and edge preservation index (EPI). Computational efficiency was evaluated in a MATLAB (MathWorks) environment using central processing unit-based processing. Results and Discussion: The relative performance of FNLM varied according to noise level and evaluation metric. Compared with ANLM, FNLM achieved lower RMSE and HFEN and higher SSIM and EPI across most noise levels, while showing comparable or improved performance relative to NLM. Linear mixed-effects analysis confirmed significant algorithmic differences depending on noise severity. Regarding computational efficiency, FNLM was approximately 7.8–25.1 times faster than ANLM and 2.7–3.2 times faster than NLM across noise levels. Conclusion: The optimized FNLM algorithm provides competitive denoising performance while substantially improving computational efficiency in clinical breast MRI with Rician noise.

Non-local means (NLM) algorithm is an effective and successful denoising method, but it is computationally heavy. To deal with this obstacle, we propose a novel NLM algorithm with fuzzy metric (FM-NLM) for image denoising in this paper. A new feature metric of visual features with fuzzy metric is utilized to measure the similarity between image pixels in the presence of Gaussian noise. Similarity measures of luminance and structure information are calculated using a fuzzy metric. A smooth kernel is constructed with the proposed fuzzy metric instead of the Gaussian weighted L2 norm kernel. The fuzzy metric and smooth kernel computationally simplify the NLM algorithm and avoid the filter parameters. Meanwhile, the proposed FM-NLM using visual structure preferably preserves the original undistorted image structures. The performance of the improved method is visually and quantitatively comparable with or better than that of the current state-of-the-art NLM-based denoising algorithms.

본 연구의 목적은 주석 필터를 사용한 high-pitch 기반 저선량 프로토콜이 적용된 전산화단층영상에서 발생하는 화질 저하 문제를 해결하기 위해 융합형 노이즈 제거 알고리즘을 모델링하고 그 kernel size를 최적화하는 것이다. CT 영상을 획득하기 위하여 AAPM CT performance phantom을 사용하였으며, 고주파 신호 손실 저감을 위하여 median-modified Wiener filter에 Richardson-Lucy 복원 알고리즘이 혼합된 융합형 노이즈 제거 알고리즘을 모델 링하였다. 알고리즘 적용 후의 노이즈 개선 정도를 객관적으로 평가하기 위하여 정량적 평가인자인 coefficient of variation (COV), contrast to noise ratio (CNR), 그리고 natural image quality evaluator (NIQE)를 계산하였다. 그 결과, 7 × 7의 kernel size에서 가장 우수한 영상특성을 나타내었고, 최적화된 융합형 노이즈 제거 알고리즘이 적용된 주석 필터를 사용한 high-pitch 기반 저선량 프로토콜이 적용된 영상을 알루미늄 필터 및 저선량 프로토콜이 적용되지 않은 주석 필터 영상과 비교하였을 때 COV 값은 각각 약 2.36배 및 3.95배, CNR 값은 4.36배 및 7.31배, 그리고 NIQE 값은 1.43배 및 1.45배 향상되었다. 결론적으로, 본 연구를 통해 kernel size가 7 × 7으로 최적화 된 융합형 노이즈 제거 알고리즘을 적용함으로써 주석 필터를 사용한 high-pitch 기반 저선량 프로토콜은 CT 영상의 화질 저하 문제를 해결하는 데에 있어 효과적임을 확인하였다.

In this study, computed tomography (CT) images were obtained using American Association of Physicists in Medicine CT performance phantom to quantitatively evaluate changes in image quality due to the application of high-pitch-based low-dose protocols using tin filters. Median modified Wiener filter algorithm and the Richardson-Lucy restoration algorithm were used fusion noise reduction algorithm, and kernel size was set from 3 × 3 to 15 × 15. We applied a fusion noise reduction algorithm from the acquired images, and quantitatively evaluated the effectiveness of reducing radiation dose and improving image quality. In addition, tin filter images without aluminum filters and low-dose protocols were obtained for comparative evaluation. As a result, the kernel size of 7 × 7 showed the best image quality, it was confirmed that images with low-dose protocols applied with optimized algorithms improved coefficient of variation values by 2.36 times and 3.95 times, contrast to noise ratio values by 4.36 times and 7.31 times, and natural image quality evaluator values by 1.43 times and 1.45 times. In conclusion, if high-pitch based low-dose protocols using tin filters can be stably used by applying the fusion noise reduction algorithm, it is expected that to reduce the exposure dose and provide patient-centered care services.

Holography is the optimal and the final choice among several techniques for imaging and displaying the three-dimensional (3D) objects. In this paper, we propose a new denoising algorithm for digital hologram using Fresnel transform (FT). The proposed algorithm initially transforms a digital hologram into frequency-domain data through a FT, and separates the object from the background in the transformed image. Experimental results show that the technique to reduce noise in a natural 2D image such as a smoothing filter can reduce the noise to improve the image quality for a digital hologram. We expect that the conclusions of this paper will be a very useful technique for further work in the area of signal processing scheme for electronic holographic video service.

Holography is the optimal and the final choice among several techniques for imaging and displaying the three-dimensional (3D) objects. In this paper, we propose a new denoising algorithm for digital hologram using Fresnel transform (FT). The proposed algorithm initially transforms a digital hologram into frequency-domain data through a FT, and separates the object from the background in the transformed image. Experimental results show that the technique to reduce noise in a natural 2D image such as a smoothing filter can reduce the noise to improve the image quality for a digital hologram. We expect that the conclusions of this paper will be a very useful technique for further work in the area of signal processing scheme for electronic holographic video service.

In allusion to the partial texture information loss during image deniosing process, an image denoising algorithm based on non related dictionary learning is proposed in this article. In this algorithm, the noise image is firstly divided into mutually overlapped image blocks, and a certain quantity of these image blocks are randomly selected for subsequent dictionary learning; then, non related dictionary learning technology is adopted to obtain the redundant dictionary with relatively strong irrelevance; finally, the sparse encoding algorithm is adopted to obtain the sparse representation coefficient of each image block in the redundant dictionary, and such sparse representation coefficients are used to recover the original image. The experiment result shows: since the redundant dictionary obtained through non related dictionary learning technology can strongly represent the image texture information, PSNR (Peak Signal to Noise Ratio) of the algorithm proposed in this article is superior to that of the existing advanced algorithm, and the algorithm can well keep the image detail and texture information, thus to improve visual effect.

The problem of estimating a signal that is corrupted by additive noise has been of interest to many researchers for practical as well as theoretical reasons. Many of the traditional denoising methods have been using methods such as the Wiener filtering. Recently, nonlinear methods, especially those based on wavelets have become increasingly popular, due to a number of advantages over the linear methods. It has been shown that wavelet and multiwavelet thresholding guarantees better rate of convergence, despite its simplicity. This paper demonstrates the work of combining Parametric multiwavelet and Sureshrink to remove noise from the signal. Experimental results shows that the proposed work is 4% efficient in terms of SNR values and image quality when compared to other wavelet families

Block-matching and 3D filtering (BM3D) denoising algorithm [1] proposed recently has a problem of computational burden especially for low noise level and a sharp performance drop for high noise level. To solve it, an improved version of BM3D is proposed. The solution combines the digital image characteristic with added noise pollution levels, and adaptively selects block-matching threshold in grouping stage. Experimental results demonstrate it outperforms not only in terms of objective criteria of PSNR and running time, but also in visual quality.

In allusion to remove Racian noise while lessen the loss of details as low as possible, this paper proposed an filter algorithm which comprehensive utilize Multi-Objective Genetic Algorithm (MOGA) and Shearlet transform based on a Multi-scale Geometric Analysis (MGA) theory. First, it performs a wavelet multi-scale decomposition of image. Then, it builds target function in MOGA by several evaluation methods such as Signal to Noise Ratio (SNR). Third, it uses the MOGA to optimal coefficients of Shearlet wavelet threshold value in different scale and different orientation. Finally, it obtains the composite image by using inverse lifting wavelet transform. Experimental results show tha our proposed new algorithm presented here is more effective in removing Rician noise, and giving better Peak Signal Noise Ratio (PSNR) gains, without manual intervention in comparison with other traditional filters.

In the field of image denoising, nonlocal image denoising algorithm is a nonlinear, space average denoising algorithm, it will not cause boundary blurred, it is an effective denoising algorithm. But its application still has limitations because of it taking much longer time, in this paper, the method was improved, image signal can be divided into high frequency and low frequency part using wavelet decomposition, nonlocal denoising algorithm is used in low-frequency approximate signal, for high frequency detail signals using wavelet filtering method for denoising. The experimental results show that the method improves the speed of image processing and has good practical value.

We introduce a fast and effective algorithm extreme learning machine (ELM) and apply it to image denoising. GA-ELM algorithm we proposed uses genetic algorithm(GA) to decide weights and bias in the ELM. It has better global optimal characteristics than traditional optimal ELM algorithm. In this paper, we used GA-ELM to do image denosing researching work. Firstly, this paper uses training samples to train GA-ELM as the noise detector. Then, we utilize the well-trained GA-ELM to recognize noise pixels in target image. And at last, an adaptive weighted average algorithm is used to recover noise pixels recognized by GA-ELM. Experiment data shows that this algorithm has better performance than other denosing algorithm.

As a kind of very effective methods of gathering data processing - principal component method, it can be used to determine the variables between the linear combination rule, reduce the dimension of feature space, select the optimal variables instead of the original. In recent years, as in the field of image processing, a wide range of application of principal component inspection technology, its shortcomings are also needless to say, the main components of investigation can only in the presence of one dimensional vector. Plane principal component, but can be on the premise of reducing data transformation between time, directly with two-dimensional vector matrix, which results in better image processing speed operation. On this basis, in the light of the characteristics of the remote sensing images, principal component and on the plane algorithm combining wavelet transform, put forward a kind of based on wavelet transform and principal component of the denoising algorithm. Experimental results show that the proposed method is better than first when some typical denoising method, this method can effectively remove gaussian noise of remote sensing images, made in the image edge details such as information can be more perfect.

In this paper, we propose a novel approach to explore image denoising for patch based image process. The importance measurement model of Rough Entropy and the importance reduction method of wavelet coefficients are given. This paper combines the rough set theory with the denoising method of wavelet threshold, regarding the high-frequency information blocks in the transform domain as similar ones, and adopting importance Reduction Methods to contract the coefficients. The simulation results show that this method is effective.

The electrocardiogram (ECG) signal processing plays an important role in diagnosing cardiopathy. Sparse decomposition provides a new tool for ECG signal processing. Matching pursuit (MP) algorithm uses overcomplete dictionary to decompose the signal, so it can reflect the properties of the signal. In decomposition process, searching a best atom of the dictionary is an optimal problem; Genetic Algorithm (GA) is used to solve this problem. This paper proposed an improved MP algorithm based on GA to denoise the ECG signal, whose dictionary is composed of Gabor atoms. The experiment simulation results show that the proposed method can get a good denosing effect in a shorter time than not use GA algorithm.

In the production of medical images, noise reduction and contrast enhancement are important methods to increase qualities of processing results. Wavelet transforms have shown promising results for localization in both time and frequency, and hence have been used for image processing applications including noise removal. By using the edge-based denoising and adaptive nonlinear histogram stretching, a novel medical image enhancement algorithm is proposed. First, a medical image is decomposed by wavelet transform, and then all high frequency sub-images are decomposed by Haar transform. At the same time, edge detection with Sobel operator is performed. Second, noises in all high frequency sub-images are reduced by edge-based soft-threshold method. Third, high frequency coefficients are further enhanced by adaptive weight values in different sub-images. Through the inverse Haar transform and the inverse wavelet transform, the enhanced image is obtained. Finally, the proposed adaptive nonlinear histogram stretching method is applied to increase the contrast of resultant image. Experimental results show that the proposed algorithm can enhance a low contrast medical image while preserving edges effectively without blurring the details.

Wavelet denoising is a commonly used method in the field of image denoising algorithms, based on the analysis of the characteristics of estimated wavelet coefficients in the wavelet threshold denoising and the traditional soft threshold and hard threshold method, in the light of the discontinuity of hard threshold and fixed deviation of soft threshold, and non-differentiable of compromise algorithm, a wavelet threshold denoising algorithm is put forward which is continuous based on the wavelet coefficients and differentiable and variable threshold value deviation, the experimental results show that this method has better denoising effect and has good practical value.

The knowledge involved in digital image processing is very wide, and there are many kinds of methods. Traditional image processing technology is mainly focused on the acquisition, transformation, enhancement, restoration, compression encoding, segmentation, edge extraction and so on. With the emergence of new tools and new methods, the image processing technology has been updated and developed. In this paper, an effective method for edge detection and image de-noising is proposed. In this article, the impulse noise detector is composed of a BP neural network (BPNN) and a decision switch. BPNN requires four input values, which are the current pixel value, grey median value, energy value, and contrast. To take these four values as the input values, the impulse noise detector can show good performance. The output of the BPNN is transferred to the decision switch, and the output value is converted to 0 or 1, which is used to distinguish whether the pixels are polluted. At this point, we introduce an additional impulse term and establish the improved BPNN model. The additional impulse term can effectively speed up the convergence of the network, avoid the emergence of the local minimum problem, and ensure the stability of the training process. In this way, the IBPNN filter of this paper only uses the information of the non polluted pixels to filter the noise pixels, which avoids the secondary pollution, and obtains a better performance. This algorithm has high PSNR value and strong detail information and edge preserving ability. Finally, the improved BPNN algorithm is applied to the image edge detection, and we use the improved neural network model to detect the edge of the image. Because the method can be used to include the prior knowledge, the IBPNN method is better than the traditional method in image edge detection.

In the process of image acquisition and transmission, noise is always contained inevitably. So it is necessary to image denoising processing to improve the quality of image. Generally speaking, each algorithm has some filtering and threshold parameters. Taking variety kinds of images into account, it is a key problem of how to set these parameters in denoising algorithms under different conditions to achieve better performance. There are many algorithms for the determination of the parameters, and each of them has its application field. Because the wavelet transform has good performance, therefore, it has been widely applied as a kind of signal and image processing tools. In this paper, wavelet transform is used in the image denoising, and the genetic algorithm is used to estimate the denoising results. Experimental results show the validity of the new algorithm.

Aiming at the problem of ground penetrating radar image denoising, a new adaptive image denoising algorithm based on nonsubsampled Contourlet transform is proposed. The algorithm firstly performs nonsubsampled Contourlet transform to the noise image, to obtain the coefficients of each directional sub band and each scale, then, according to the energy of the coefficient, the denoising threshold value is adjusted adaptively. Simulation results show that, compared with the wavelet threshold denoising algorithm, the proposed algorithm can effectively remove the Gauss white noise in the image, improve the peak signal to noise ratio (PNSR), while preserving the edge details of the image, it can improve the PSNR value and reduce the Gibbs phenomenon.

A video signal through a high-density optical link has been demonstrated to show the reliability of optical link for high-data-rate transmission. To reduce optical point-to-point links, an electrical link has been utilized for control and clock signaling. The latency and flicker with background noise occurred during the transferring of data across the optical link due to electrical-to-optical with optical-to-electrical conversions. The proposed synchronization technology combined with a flicker and denoising algorithm has given good results and can be applied in high-definition serial data interface (HD-SDI), ultra-HD-SDI, and HD multimedia interface transmission system applications.