scholarly journals Hyperspectral Unmixing with Bandwise Generalized Bilinear Model

2018 ◽  
Vol 10 (10) ◽  
pp. 1600 ◽  
Author(s):  
Chang Li ◽  
Yu Liu ◽  
Juan Cheng ◽  
Rencheng Song ◽  
Hu Peng ◽  
...  
Keyword(s):  
Gaussian Noise ◽  
Impulse Noise ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
Additive White Gaussian Noise ◽  
Bilinear Model ◽  
Hyperspectral Unmixing ◽  
Noise Impulse ◽  
Mixed Noise ◽  
Alternative Direction Method

Generalized bilinear model (GBM) has received extensive attention in the field of hyperspectral nonlinear unmixing. Traditional GBM unmixing methods are usually assumed to be degraded only by additive white Gaussian noise (AWGN), and the intensity of AWGN in each band of hyperspectral image (HSI) is assumed to be the same. However, the real HSIs are usually degraded by mixture of various kinds of noise, which include Gaussian noise, impulse noise, dead pixels or lines, stripes, and so on. Besides, the intensity of AWGN is usually different for each band of HSI. To address the above mentioned issues, we propose a novel nonlinear unmixing method based on the bandwise generalized bilinear model (NU-BGBM), which can be adapted to the presence of complex mixed noise in real HSI. Besides, the alternative direction method of multipliers (ADMM) is adopted to solve the proposed NU-BGBM. Finally, extensive experiments are conducted to demonstrate the effectiveness of the proposed NU-BGBM compared with some other state-of-the-art unmixing methods.

scholarly journals When AWGN-Based Denoiser Meets Real Noises

2020 ◽  
Vol 34 (07) ◽  
pp. 13074-13081
Author(s):  
Yuqian Zhou ◽  
Jianbo Jiao ◽  
Haibin Huang ◽  
Yang Wang ◽  
Jue Wang ◽  
...  
Keyword(s):  
Gaussian Noise ◽  
Impulse Noise ◽  
State Of The Art ◽  
Additive White Gaussian Noise ◽  
White Gaussian Noise ◽  
Discriminative Learning ◽  
Real Image ◽  
Deep Model ◽  
Novel Approach ◽  
Noise Data

Discriminative learning based image denoisers have achieved promising performance on synthetic noises such as Additive White Gaussian Noise (AWGN). The synthetic noises adopted in most previous work are pixel-independent, but real noises are mostly spatially/channel-correlated and spatially/channel-variant. This domain gap yields unsatisfied performance on images with real noises if the model is only trained with AWGN. In this paper, we propose a novel approach to boost the performance of a real image denoiser which is trained only with synthetic pixel-independent noise data dominated by AWGN. First, we train a deep model that consists of a noise estimator and a denoiser with mixed AWGN and Random Value Impulse Noise (RVIN). We then investigate Pixel-shuffle Down-sampling (PD) strategy to adapt the trained model to real noises. Extensive experiments demonstrate the effectiveness and generalization of the proposed approach. Notably, our method achieves state-of-the-art performance on real sRGB images in the DND benchmark among models trained with synthetic noises. Codes are available at https://github.com/yzhouas/PD-Denoising-pytorch.

scholarly journals SAR Image Despeckling by Deep Neural Networks: from a Pre-Trained Model to an End-to-End Training Strategy

2020 ◽  
Vol 12 (16) ◽  
pp. 2636
Author(s):  
Emanuele Dalsasso ◽  
Xiangli Yang ◽  
Loïc Denis ◽  
Florence Tupin ◽  
Wen Yang
Keyword(s):  
Neural Networks ◽  
Gaussian Noise ◽  
State Of The Art ◽  
Additive White Gaussian Noise ◽  
Hybrid Approach ◽  
White Gaussian Noise ◽  
Training Data ◽  
Speckle Reduction ◽  
Sar Image ◽  
Sar Images

Speckle reduction is a longstanding topic in synthetic aperture radar (SAR) images. Many different schemes have been proposed for the restoration of intensity SAR images. Among the different possible approaches, methods based on convolutional neural networks (CNNs) have recently shown to reach state-of-the-art performance for SAR image restoration. CNN training requires good training data: many pairs of speckle-free/speckle-corrupted images. This is an issue in SAR applications, given the inherent scarcity of speckle-free images. To handle this problem, this paper analyzes different strategies one can adopt, depending on the speckle removal task one wishes to perform and the availability of multitemporal stacks of SAR data. The first strategy applies a CNN model, trained to remove additive white Gaussian noise from natural images, to a recently proposed SAR speckle removal framework: MuLoG (MUlti-channel LOgarithm with Gaussian denoising). No training on SAR images is performed, the network is readily applied to speckle reduction tasks. The second strategy considers a novel approach to construct a reliable dataset of speckle-free SAR images necessary to train a CNN model. Finally, a hybrid approach is also analyzed: the CNN used to remove additive white Gaussian noise is trained on speckle-free SAR images. The proposed methods are compared to other state-of-the-art speckle removal filters, to evaluate the quality of denoising and to discuss the pros and cons of the different strategies. Along with the paper, we make available the weights of the trained network to allow its usage by other researchers.

scholarly journals l0Sparsity for Image Denoising with Local and Global Priors

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Xiaoni Gao ◽  
Mei Yu ◽  
Jianrong Wang ◽  
Jianguo Wei
Keyword(s):  
Computational Complexity ◽  
Gaussian Noise ◽  
State Of The Art ◽  
Additive White Gaussian Noise ◽  
White Gaussian Noise ◽  
Superior Performance ◽  
Redundant Information ◽  
Search Window ◽  
Global Consistency ◽  
Image Set

We propose al0sparsity based approach to remove additive white Gaussian noise from a given image. To achieve this goal, we combine the local prior and global prior together to recover the noise-free values of pixels. The local prior depends on the neighborhood relationships of a search window to help maintain edges and smoothness. The global prior is generated from a hierarchicall0sparse representation to help eliminate the redundant information and preserve the global consistency. In addition, to make the correlations between pixels more meaningful, we adopt Principle Component Analysis to measure the similarities, which can be both propitious to reduce the computational complexity and improve the accuracies. Experiments on the benchmark image set show that the proposed approach can achieve superior performance to the state-of-the-art approaches both in accuracy and perception in removing the zero-mean additive white Gaussian noise.

Mixed Noise Image De-Noising Based on EM Algorithm

2014 ◽  
Vol 556-562 ◽  
pp. 4734-4741 ◽  
Author(s):  
Gui Cun Shi ◽  
Fei Xing Wang
Keyword(s):  
Applied Sciences ◽  
Wavelet Analysis ◽  
Em Algorithm ◽  
Gaussian Noise ◽  
Impulse Noise ◽  
Noise Source ◽  
High Quality ◽  
Noise Image ◽  
Mixed Noise ◽  
Non Gaussian

Obtaining high quality images is very important in many areas of applied sciences, but images are usually polluted by noise in the process of generation, transmission and acquisition. In recent years, wavelet analysis achieves significant results in the field of image de-noising. However, most of the studies of noise-induced phenomena assume that the noise source is Gaussian. The use of mixed Gaussian and impulse noise is rare, mainly because of the difficulties in handling them. In the process of image de-noising, the noise model’s parameter estimation is a key issue, because the accuracy of the noise model’s parameters could affect the de-noising quality. In the case of mixed Gaussian noises, EM algorithm is an iterative algorithm, which simplifies the maximum likelihood equation. This thesis takes wavelet analysis and statistics theory as tools, studies on mixed noise image de-noising, provides two classes of algorithms for dealing with a special type of non-Gaussian noise, mixed Gaussian and Pepper & Salt noise.

scholarly journals Approximate Sparse Regularized Hyperspectral Unmixing

2014 ◽  
Vol 2014 ◽  
pp. 1-11
Author(s):  
Chengzhi Deng ◽  
Yaning Zhang ◽  
Shengqian Wang ◽  
Shaoquan Zhang ◽  
Wei Tian ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Optimization Model ◽  
Optimization Problem ◽  
Augmented Lagrangian ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
Experimental Results ◽  
Hyperspectral Images ◽  
Hyperspectral Unmixing ◽  
Variable Splitting

Sparse regression based unmixing has been recently proposed to estimate the abundance of materials present in hyperspectral image pixel. In this paper, a novel sparse unmixing optimization model based on approximate sparsity, namely, approximate sparse unmixing (ASU), is firstly proposed to perform the unmixing task for hyperspectral remote sensing imagery. And then, a variable splitting and augmented Lagrangian algorithm is introduced to tackle the optimization problem. In ASU, approximate sparsity is used as a regularizer for sparse unmixing, which is sparser thanl1regularizer and much easier to be solved thanl0regularizer. Three simulated and one real hyperspectral images were used to evaluate the performance of the proposed algorithm in comparison tol1regularizer. Experimental results demonstrate that the proposed algorithm is more effective and accurate for hyperspectral unmixing than state-of-the-artl1regularizer.

scholarly journals Hybrid Filter Based on Fuzzy Techniques for Mixed Noise Reduction in Color Images

2019 ◽  
Vol 10 (1) ◽  
pp. 243 ◽  
Author(s):  
Josep Arnal ◽  
Luis Súcar
Keyword(s):  
Noise Reduction ◽  
Gaussian Noise ◽  
State Of The Art ◽  
Peer Group ◽  
Median Filter ◽  
Block Matching ◽  
Group Method ◽  
Hybrid Filter ◽  
Mixed Noise ◽  
Vector Median

To decrease contamination from a mixed combination of impulse and Gaussian noise on color digital images, a novel hybrid filter is proposed. The new technique is composed of two stages. A filter based on a fuzzy metric is used for the reduction of impulse noise at the first stage. At the second stage, to remove Gaussian noise, a fuzzy peer group method is applied on the image generated from the previous stage. The performance of the introduced algorithm was evaluated on standard test images employing widely used objective quality metrics. The new approach can efficiently reduce both impulse and Gaussian noise, as much as mixed noise. The proposed filtering method was compared to the state-of-the-art methodologies: adaptive nearest neighbor filter, alternating projections filter, color block-matching 3D filter, fuzzy peer group averaging filter, partition-based trimmed vector median filter, trilateral filter, fuzzy wavelet shrinkage denoising filter, graph regularization filter, iterative peer group switching vector filter, peer group method, and the fuzzy vector median method. The experiments demonstrated that the introduced noise reduction technique outperforms those state-of-the-art filters with respect to the metrics peak signal to noise ratio (PSNR), the mean absolute error (MAE), and the normalized color difference (NCD).

Advance in Image and Audio Restoration and their Assessments: A Review

2021 ◽  
Vol 12 (2) ◽  
pp. 1-16
Author(s):  
Omar H. Mohammed ◽  
Basil Sh. Mahmood
Keyword(s):  
Image Restoration ◽  
Gaussian Noise ◽  
Impulse Noise ◽  
Degradation Process ◽  
Motion Blur ◽  
Original Image ◽  
Restoration Techniques ◽  
Degradation Models ◽  
Noise Impulse ◽  
Audio Restoration

Image restoration is the process of restoring the original image from a degraded one. Images can be affected by various types of noise, such as Gaussian noise, impulse noise, and affected by blurring, which is happened during image recordings like motion blur, Out-of-Focus Blur, and others. Image restoration techniques are used to reverse the effect of noise and blurring. Restoration of distorted images can be done using some information about noise and the blurring nature or without any knowledge about the image degradation process. Researchers have proposed many algorithms in this regard; in this paper, different noise and degradation models and restoration methods will be discussed and review some researches in this field.

scholarly journals Hyperspectral Image Mixed Noise Removal Using Subspace Representation and Deep CNN Image Prior

2021 ◽  
Vol 13 (20) ◽  
pp. 4098
Author(s):  
Lina Zhuang ◽  
Michael K. Ng ◽  
Xiyou Fu
Keyword(s):  
Hyperspectral Image ◽  
Signal To Noise Ratio ◽  
Noise Removal ◽  
Hyperspectral Data ◽  
Image Prior ◽  
Noise Impulse ◽  
Mixed Noise ◽  
Deep Cnn ◽  
Mixed Noise Removal ◽  
The Cost

The ever-increasing spectral resolution of hyperspectral images (HSIs) is often obtained at the cost of a decrease in the signal-to-noise ratio (SNR) of the measurements. The decreased SNR reduces the reliability of measured features or information extracted from HSIs, thus calling for effective denoising techniques. This work aims to estimate clean HSIs from observations corrupted by mixed noise (containing Gaussian noise, impulse noise, and dead-lines/stripes) by exploiting two main characteristics of hyperspectral data, namely low-rankness in the spectral domain and high correlation in the spatial domain. We take advantage of the spectral low-rankness of HSIs by representing spectral vectors in an orthogonal subspace, which is learned from observed images by a new method. Subspace representation coefficients of HSIs are learned by solving an optimization problem plugged with an image prior extracted from a neural denoising network. The proposed method is evaluated on simulated and real HSIs. An exhaustive array of experiments and comparisons with state-of-the-art denoisers were carried out.

A Mixed Noise Filtering Algorithm for High-Speed Sequence Image Processing

2013 ◽  
Vol 415 ◽  
pp. 318-324
Author(s):  
Yan Zhu Yang ◽  
Wei Liang Liu ◽  
Neng Jie Chen ◽  
Wei Zhu
Keyword(s):  
Image Processing ◽  
Gaussian Noise ◽  
High Speed ◽  
Impulse Noise ◽  
Effective Means ◽  
Weighted Average ◽  
Frame Rate ◽  
Good Effect ◽  
Filtering Algorithm ◽  
Mixed Noise

t is a effective means by using high-speed vision to locate mobile targets. Under the circumstance of high frame rate and high sensitivity (300Hz), in addition to the Gaussian noise and impulse noise, the image quality is also influenced by atmospheric instability, and it is mainly expressed as Gaussian noise. An improved adaptive threshold weighted mean (IATWM) de-noising algorithm is proposed in this paper. According to the characteristics of impulse noise, the algorithm is able to obtain the threshold adaptively and separate the impulse noise. Then, the weighted median filtering algorithm is used to remove the impulse noise. And the improved weighted average filter algorithm is adopted to remove the Gaussian noise for graphics with Gaussian noise. The algorithm could deal with the Gaussian noise and impulse noise separately, avoiding the weaken handling for the parts not subject to pixels pollution of the impulse noise. The experimental results show that the processing result of the algorithm is able to retain the image details, superior to the traditional filtering algorithms and MTM algorithm. In addition, the algorithm provides an effective way to eliminate the mixed noise, along with a good effect on the high-speed sequence image processing.

scholarly journals Adaptation Strategies for Applying AWGN-Based Denoiser to Realistic Noise

2019 ◽  
Vol 33 ◽  
pp. 10085-10086
Author(s):  
Yuqian Zhou ◽  
Jianbo Jiao ◽  
Haibin Huang ◽  
Jue Wang ◽  
Thomas Huang
Keyword(s):  
Gaussian Noise ◽  
Impulse Noise ◽  
Additive White Gaussian Noise ◽  
Super Resolution ◽  
Adaptation Strategies ◽  
Noise Model ◽  
Discriminative Learning ◽  
Preliminary Results ◽  
Multi Scale ◽  
Multiple Strategies

Discriminative learning based denoising model trained with Additive White Gaussian Noise (AWGN) performs well on synthesized noise. However, realistic noise can be spatialvariant, signal-dependent and a mixture of complicated noises. In this paper, we explore multiple strategies for applying an AWGN-based denoiser to realistic noise. Specifically, we trained a deep network integrating noise estimating and denoiser with mixed Gaussian (AWGN) and Random Value Impulse Noise (RVIN). To adapt the model to realistic noises, we investigated multi-channel, multi-scale and super-resolution approaches. Our preliminary results demonstrated the effectiveness of the newly-proposed noise model and adaptation strategies.

Sign in / Sign up

Export Citation Format

Share Document