scholarly journals Image Denoising Using a Novel Deep Generative Network with Multiple Target Images and Adaptive Termination Condition

2021 ◽  
Vol 11 (11) ◽  
pp. 4803
Author(s):  
Shiming Chen ◽  
Shaoping Xu ◽  
Xiaoguo Chen ◽  
Fen Li
Keyword(s):  
Image Denoising ◽  
Similarity Index ◽  
Structural Similarity ◽  
Superior Performance ◽  
Natural Image ◽  
Noisy Image ◽  
Multiple Target ◽  
Convolutional Networks ◽  
Training Images ◽  
Image Priors

Image denoising, a classic ill-posed problem, aims to recover a latent image from a noisy measurement. Over the past few decades, a considerable number of denoising methods have been studied extensively. Among these methods, supervised deep convolutional networks have garnered increasing attention, and their superior performance is attributed to their capability to learn realistic image priors from a large amount of paired noisy and clean images. However, if the image to be denoised is significantly different from the training images, it could lead to inferior results, and the networks may even produce hallucinations by using inappropriate image priors to handle an unseen noisy image. Recently, deep image prior (DIP) was proposed, and it overcame this drawback to some extent. The structure of the DIP generator network is capable of capturing the low-level statistics of a natural image using an unsupervised method with no training images other than the image itself. Compared with a supervised denoising model, the unsupervised DIP is more flexible when processing image content that must be denoised. Nevertheless, the denoising performance of DIP is usually inferior to the current supervised learning-based methods using deep convolutional networks, and it is susceptible to the over-fitting problem. To solve these problems, we propose a novel deep generative network with multiple target images and an adaptive termination condition. Specifically, we utilized mainstream denoising methods to generate two clear target images to be used with the original noisy image, enabling better guidance during the convergence process and improving the convergence speed. Moreover, we adopted the noise level estimation (NLE) technique to set a more reasonable adaptive termination condition, which can effectively solve the problem of over-fitting. Extensive experiments demonstrated that, according to the denoising results, the proposed approach significantly outperforms the original DIP method in tests on different databases. Specifically, the average peak signal-to-noise ratio (PSNR) performance of our proposed method on four databases at different noise levels is increased by 1.90 to 4.86 dB compared to the original DIP method. Moreover, our method achieves superior performance against state-of-the-art methods in terms of popular metrics, which include the structural similarity index (SSIM) and feature similarity index measurement (FSIM). Thus, the proposed method lays a good foundation for subsequent image processing tasks, such as target detection and super-resolution.

BM3D Denoising Algorithm with Adaptive Block-Match Thresholds

2012 ◽  
Vol 229-231 ◽  
pp. 1715-1720 ◽  
Author(s):  
You Sai Zhang ◽  
Shu Jin Zhu ◽  
Yuan Jiang Li
Keyword(s):  
Similarity Index ◽  
Block Size ◽  
Structural Similarity ◽  
Block Matching ◽  
Natural Image ◽  
Noisy Image ◽  
Nonlocal Means ◽  
Good Improvement ◽  
High Degree ◽  
The Relationship

A number of image filtering algorithms based on nonlocal means have been proposed in recent years which take advantage of the high degree of redundancy of any natural image. The block-matching with 3D transform domain collaborative filtering (BM3D) proposed in [1] achieves excellent performance in image denoising. But the choice of shrinkage operator in block-matching step is not discussed, only given the threshold by experience in its related papers. In this work, we introduce an improved version of BM3D with adaptive block-match thresholds. The proposed method firstly seeks the relationship between the Structural Similarity index (SSIM) [2] and match distance in blocks and obtains the data with fine SSIM values. Then, compute the Noise level and Gradient values in blocks of the same block size. Finally, surface fitting is adopted to get a formula which applies weak thresholds for flat blocks and strong thresholds for detail blocks. Experiment results are given to demonstrate the same class of denoising performance with less time-consuming to slightly noisy image and good improvement in denoising performance to seriously noisy image.

scholarly journals GPR B-Scan Image Denoising via Multi-Scale Convolutional Autoencoder with Data Augmentation

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1269
Author(s):  
Jiabin Luo ◽  
Wentai Lei ◽  
Feifei Hou ◽  
Chenghao Wang ◽  
Qiang Ren ◽  
...  
Keyword(s):  
Image Denoising ◽  
Data Augmentation ◽  
Noise Suppression ◽  
Random Noise ◽  
Similarity Index ◽  
Structural Similarity ◽  
Training Dataset ◽  
Generative Adversarial Network ◽  
Multi Scale ◽  
Convolutional Autoencoder

Ground-penetrating radar (GPR), as a non-invasive instrument, has been widely used in civil engineering. In GPR B-scan images, there may exist random noise due to the influence of the environment and equipment hardware, which complicates the interpretability of the useful information. Many methods have been proposed to eliminate or suppress the random noise. However, the existing methods have an unsatisfactory denoising effect when the image is severely contaminated by random noise. This paper proposes a multi-scale convolutional autoencoder (MCAE) to denoise GPR data. At the same time, to solve the problem of training dataset insufficiency, we designed the data augmentation strategy, Wasserstein generative adversarial network (WGAN), to increase the training dataset of MCAE. Experimental results conducted on both simulated, generated, and field datasets demonstrated that the proposed scheme has promising performance for image denoising. In terms of three indexes: the peak signal-to-noise ratio (PSNR), the time cost, and the structural similarity index (SSIM), the proposed scheme can achieve better performance of random noise suppression compared with the state-of-the-art competing methods (e.g., CAE, BM3D, WNNM).

scholarly journals A Multi-Scale Feature Extraction-Based Normalized Attention Neural Network for Image Denoising

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 319
Author(s):  
Yi Wang ◽  
Xiao Song ◽  
Guanghong Gong ◽  
Ni Li
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Image Denoising ◽  
Color Image ◽  
Rapid Development ◽  
Similarity Index ◽  
Structural Similarity ◽  
Convolutional Network ◽  
Scale Feature ◽  
Multi Scale

Due to the rapid development of deep learning and artificial intelligence techniques, denoising via neural networks has drawn great attention due to their flexibility and excellent performances. However, for most convolutional network denoising methods, the convolution kernel is only one layer deep, and features of distinct scales are neglected. Moreover, in the convolution operation, all channels are treated equally; the relationships of channels are not considered. In this paper, we propose a multi-scale feature extraction-based normalized attention neural network (MFENANN) for image denoising. In MFENANN, we define a multi-scale feature extraction block to extract and combine features at distinct scales of the noisy image. In addition, we propose a normalized attention network (NAN) to learn the relationships between channels, which smooths the optimization landscape and speeds up the convergence process for training an attention model. Moreover, we introduce the NAN to convolutional network denoising, in which each channel gets gain; channels can play different roles in the subsequent convolution. To testify the effectiveness of the proposed MFENANN, we used both grayscale and color image sets whose noise levels ranged from 0 to 75 to do the experiments. The experimental results show that compared with some state-of-the-art denoising methods, the restored images of MFENANN have larger peak signal-to-noise ratios (PSNR) and structural similarity index measure (SSIM) values and get better overall appearance.

A compensating total variation image denoising model combining L1 and L2 norm

2020 ◽  
pp. 002072092092330
Author(s):  
Liqiong Zhang ◽  
Min Li ◽  
Xiaohua Qiu
Keyword(s):  
Image Denoising ◽  
Total Variation ◽  
Structural Information ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Structural Similarity ◽  
Isotropic Diffusion ◽  
Model Combining ◽  
L2 Norm ◽  
Staircase Effect

To overcome the “staircase effect” while preserving the structural information such as image edges and textures quickly and effectively, we propose a compensating total variation image denoising model combining L1 and L2 norm. A new compensating regular term is designed, which can perform anisotropic and isotropic diffusion in image denoising, thus making up for insufficient diffusion in the total variation model. The algorithm first uses local standard deviation to distinguish neighborhood types. Then, the anisotropic diffusion based on L1 norm plays the role of edge protection in the strong edge region. The anisotropic and the isotropic diffusion simultaneously exist in the smooth region, so that the weak textures can be protected while overcoming the “staircase effect” effectively. The simulation experiments show that this method can effectively improve the peak signal-to-noise ratio and obtain the higher structural similarity index and the shorter running time.

scholarly journals New model for local fractional integral of Chebyshev polynomials for image denoising

2019 ◽  
pp. 22-28
Author(s):  
Suzan J Obaiys ◽  
Hamid A Jalab ◽  
Rabha W Ibrahim
Keyword(s):  
Image Denoising ◽  
Chebyshev Polynomials ◽  
Fractional Integral ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Structural Similarity ◽  
Input Image ◽  
Convolution Product ◽  
Local Fractional Integral ◽  
Image Pixels

The use of local fractional calculus has increased in different applications of image processing. This study proposes a new algorithm for image denoising to remove Gaussian noise in digital images. The proposed algorithm is based on local fractional integral of Chebyshev polynomials. The proposed structures of the local fractional windows are obtained by four masks created for x and y directions. On four directions, a convolution product of the input image pixels with the local fractional mask window has been performed. The visual perception and peak signal-to-noise ratio (PSNR) with the structural similarity index (SSIM) are used as image quality measurements. The experiments proved that the accomplished filtering results are better than the Gaussian filter. Keywords: local fractional; Chebyshev polynomials; Image denoising

Dictionary Learning With Convolutional Structure for Seismic Data Denoising and Interpolation

Geophysics ◽  
2021 ◽  
pp. 1-102
Author(s):  
Murad Almadani ◽  
Umair bin Waheed ◽  
Mudassir Masood ◽  
Yangkang Chen
Keyword(s):  
Dictionary Learning ◽  
Seismic Data ◽  
Matching Pursuit ◽  
Random Noise ◽  
Similarity Index ◽  
Structural Similarity ◽  
Superior Performance ◽  
Full Data ◽  
Noisy Input ◽  
L2 Norm

Seismic data inevitably suffers from random noise and missing traces in field acquisition. This limits the utilization of seismic data for subsequent imaging or inversion applications. Recently, dictionary learning has gained remarkable success in seismic data denoising and interpolation. Variants of the patch-based learning technique, such as the K-SVD algorithm, have been shown to improve denoising and interpolation performance compared to the analytic transform-based methods. However, patch-based learning algorithms work on overlapping patches of data and do not take the full data into account during reconstruction. By contrast, the Convolutional Sparse Coding (CSC) model treats signals globally and, therefore, has shown superior performance over patch-based methods in several image processing applications. In consequence, we test the use of CSC model for seismic data denoising and interpolation. In particular, we use the Local Block Coordinate Descent (LoBCoD) algorithm to reconstruct missing traces and clean seismic data from noisy input. The denoising and interpolation performance of the LoBCoD algorithm has been compared with that of K-SVD and Orthogonal Matching Pursuit (OMP) algorithms using synthetic and field data examples. We use three quality measures to test the denoising accuracy: the peak signal-to-noise ratio (PSNR), the relative L2-norm of the error (RLNE), and the structural similarity index (SSIM). We find that LoBCoD performs better than K-SVD and OMP for all test cases in improving PSNR and SSIM, and in reducing RLNE. These observations suggest enormous potential of the CSC model in seismic data denoising and interpolation applications.

A Natural Image Compression Approach Based on ICA and Visual Saliency Detection

2011 ◽  
Vol 128-129 ◽  
pp. 457-460
Author(s):  
Li Juan Duan ◽  
Chun Xia Ke ◽  
Chun Peng Wu ◽  
Zhen Yang ◽  
Jun Miao
Keyword(s):  
Image Compression ◽  
Saliency Detection ◽  
Similarity Index ◽  
Visual Saliency ◽  
Structural Similarity ◽  
Natural Image ◽  
Compression Method ◽  
Method Performance ◽  
Important Region ◽  
Visual Saliency Detection

In this paper, a natural image compression method is proposed based on independent component analysis (ICA) and visual saliency detection. The proposed compression method learns basis functions trained from data using ICA to transform the image at first; and then sets percentage of the zero coefficient number in the total transforming coefficients. After that, transforming coefficients are sparser which indicates further improving of compression ratio. Next, the compression method performance is compared with the discrete cosine transform (DCT). Evaluation through both the usual PSNR and Structural Similarity Index (SSIM) measurements showed that proposed compression method is more robust to DCT. And finally, we proposed a visual saliency detection method to detect automatically the important region of image which is not or low compressed while the other regions are highly compressed. Experiment shows that the method can guarantee the quality of important region effectively.

scholarly journals Frequency-Based Haze and Rain Removal Network (FHRR-Net) with Deep Convolutional Encoder-Decoder

2021 ◽  
Vol 11 (6) ◽  
pp. 2873
Author(s):  
Dong Hwan Kim ◽  
Woo Jin Ahn ◽  
Myo Taeg Lim ◽  
Tae Koo Kang ◽  
Dong Won Kim
Keyword(s):  
Real World ◽  
Similarity Index ◽  
Structural Similarity ◽  
Superior Performance ◽  
Structural Similarity Index ◽  
Atmospheric Scattering ◽  
Rain Removal ◽  
Robust Network ◽  
Computer Vision Applications ◽  
Convolutional Encoder

Removing haze or rain is one of the difficult problems in computer vision applications. On real-world road images, haze and rain often occur together, but traditional methods cannot solve this imaging problem. To address rain and haze problems simultaneously, we present a robust network-based framework consisting of three steps: image decomposition using guided filters, a frequency-based haze and rain removal network (FHRR-Net), and image restoration based on an atmospheric scattering model using predicted transmission maps and predicted rain-removed images. We demonstrate FHRR-Net’s capabilities with synthesized and real-world road images. Experimental results show that our trained framework has superior performance on synthesized and real-world road test images compared with state-of-the-art methods. We use PSNR (peak signal-to-noise) and SSIM (structural similarity index) indicators to evaluate our model quantitatively, showing that our methods have the highest PSNR and SSIM values. Furthermore, we demonstrate through experiments that our method is useful in real-world vision applications.

scholarly journals Research on the Image Denoising Method Based on Partial Differential Equations

2016 ◽  
Vol 16 (5) ◽  
pp. 109-118
Author(s):  
Xiaolu Xie
Keyword(s):  
Image Denoising ◽  
High Performance ◽  
Signal To Noise Ratio ◽  
Similarity Index ◽  
Structural Similarity ◽  
Structural Similarity Index ◽  
Denoising Method ◽  
New Approach ◽  
Proposed Model ◽  
Index Measure

Abstract In this paper we propose a new approach for image denoising based on the combination of PM model, isotropic diffusion model, and TV model. To emphasize the superiority of the proposed model, we have used the Structural Similarity Index Measure (SSIM) and Peak Signal to Noise Ratio (PSNR) as the subjective criterion. Numerical experiments with different images show that our algorithm has the highest PSNR and SS1M, as well as the best visual quality among the six algorithms. Experimental results confirm the high performance of the proposed model compared with some well-known algorithms. In a word, the new model outperforms the mentioned three well known algorithms in reducing the Gibbs-type artifacts, edges blurring, and the block effect, simultaneously.

Sign in / Sign up

Export Citation Format

Share Document