scholarly journals Image Defogging Algorithm Based on Sparse Representation

Complexity ◽  
2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Di Fan ◽  
Xinyun Guo ◽  
Xiao Lu ◽  
Xiaoxin Liu ◽  
Bo Sun
Keyword(s):  
Sparse Representation ◽  
Color Space ◽  
Image Brightness ◽  
Low Contrast ◽  
Image Defogging ◽  
Degraded Image ◽  
Hsi Space ◽  
Definition Of ◽  
Nonlinear Stretching ◽  
Sparse Features

Aiming at the problems of low contrast and low definition of fog degraded image, this paper proposes an image defogging algorithm based on sparse representation. Firstly, the algorithm transforms image from RGB space to HSI space and uses two-level wavelet transform extract features of image brightness components. Then, it uses the K-SVD algorithm training dictionary and learns the sparse features of the fog-free image to reconstructed I-components of the fog image. Using the nonlinear stretching approach for saturation component improves the brightness of the image. Finally, convert from HSI space to RGB color space to get the defog image. Experimental results show that the algorithm can effectively improve the contrast and visual effect of the image. Compared with several common defog algorithms, the percentage of image saturation pixels is better than the comparison algorithm.

scholarly journals A Low-Light Sensor Image Enhancement Algorithm Based on HSI Color Model

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3583 ◽  
Author(s):  
Shiping Ma ◽  
Hongqiang Ma ◽  
Yuelei Xu ◽  
Shuai Li ◽  
Chao Lv ◽  
...  
Keyword(s):  
Image Enhancement ◽  
Color Space ◽  
Color Model ◽  
Low Light ◽  
Image Brightness ◽  
Low Contrast ◽  
Light Sensor ◽  
Hsi Color Model ◽  
Art Research ◽  
Enhancement Algorithm

Images captured by sensors in unpleasant environment like low illumination condition are usually degraded, which means low visibility, low brightness, and low contrast. In order to improve this kind of images, in this paper, a low-light sensor image enhancement algorithm based on HSI color model is proposed. At first, we propose a dataset generation method based on the Retinex model to overcome the shortage of sample data. Then, the original low-light image is transformed from RGB to HSI color space. The segmentation exponential method is used to process the saturation (S) and the specially designed Deep Convolutional Neural Network is applied to enhance the intensity component (I). At the end, we back into the original RGB space to get the final improved image. Experimental results show that the proposed algorithm not only enhances the image brightness and contrast significantly, but also avoids color distortion and over-enhancement in comparison with some other state-of-the-art research papers. So, it effectively improves the quality of sensor images.

scholarly journals Variational Histogram Equalization for Single Color Image Defogging

2016 ◽  
Vol 2016 ◽  
pp. 1-17 ◽  
Author(s):  
Li Zhou ◽  
Du Yan Bi ◽  
Lin Yuan He
Keyword(s):  
Color Image ◽  
State Of The Art ◽  
Color Space ◽  
Histogram Equalization ◽  
Degradation Model ◽  
Image Defogging ◽  
Hsi Color Space ◽  
General Variation ◽  
Bad Weather ◽  
Physical Degradation

Foggy images taken in the bad weather inevitably suffer from contrast loss and color distortion. Existing defogging methods merely resort to digging out an accurate scene transmission in ignorance of their unpleasing distortion and high complexity. Different from previous works, we propose a simple but powerful method based on histogram equalization and the physical degradation model. By revising two constraints in a variational histogram equalization framework, the intensity component of a fog-free image can be estimated in HSI color space, since the airlight is inferred through a color attenuation prior in advance. To cut down the time consumption, a general variation filter is proposed to obtain a numerical solution from the revised framework. After getting the estimated intensity component, it is easy to infer the saturation component from the physical degradation model in saturation channel. Accordingly, the fog-free image can be restored with the estimated intensity and saturation components. In the end, the proposed method is tested on several foggy images and assessed by two no-reference indexes. Experimental results reveal that our method is relatively superior to three groups of relevant and state-of-the-art defogging methods.

A Method to Enhance the Fog Image Based on Dark Object Subtraction

2014 ◽  
Vol 543-547 ◽  
pp. 2484-2487
Author(s):  
Jing Zhang ◽  
Wei Dong ◽  
Jian Xin Wang ◽  
Xu Ning Liu
Keyword(s):  
Dynamic Range ◽  
Color Space ◽  
Threshold Value ◽  
Entropy Method ◽  
Image Contrast ◽  
Dark Object ◽  
Image Contrast Enhancement ◽  
Degraded Image ◽  
Enhancement Method ◽  
Rgb Color Space

Aiming at the problem of poor image contrast and low visibility, a single image contrast enhancement method is put forward in this paper. The method is based on Dark-object subtraction technique, translating the fog degraded image from RGB color space to YIQ color space, and taking out the Y component. Then using the maximum entropy method to get the threshold value of image segmentation, we can put different portion of the image according to the different formula for image restoration. The processed image must be converted from YIQ color space to RGB color space In the back of the steps. Finally, the image needs a linear dynamic range adjustment to enhance the contrast and brightness. Experiments show that the method can effectively remove haze effect on the image. The dehazing effect of the processed image is obvious. The image becomes clear and bright, and the details is outstanding, which is convenient for observation and analysis.

Image Defogging Based on Fog Veil Subtraction

2011 ◽  
Vol 121-126 ◽  
pp. 887-891
Author(s):  
Bin Xie ◽  
Fan Guo ◽  
Zi Xing Cai
Keyword(s):  
Original Image ◽  
Single Image ◽  
Image Defogging ◽  
Real Scene ◽  
Degraded Image ◽  
The Veil ◽  
Contrast Stretching ◽  
Reflectance Map ◽  
Fog Density

In this paper, we propose a new defog algorithm based on fog veil subtraction to remove fog from a single image. The proposed algorithm first estimates the illumination component of the image by applying smoothing to the degraded image, and then obtains the uniform distributed fog veil through a mean calculation of the illumination component. Next, we multiply the uniform veil by the original image to obtain a depth-like map and extract its intensity component to produce a fog veil whose distribution is according with real fog density of the scene. Once the fog veil is calculated, the reflectance map can be obtained by subtracting the veil from the degraded image. Finally, we apply an adaptive contrast stretching to the reflectance map to obtain an enhanced result. This algorithm can be easily extended to video domains and is verified by both real-scene photographs and videos.

Neutron Image Restoration by Combining Richardson-Lucy With Steering Kernel

2013 ◽  
Author(s):  
Shuang Qiao ◽  
Qiao Wang ◽  
Jipeng Huang
Keyword(s):  
Imaging System ◽  
Signal To Noise Ratio ◽  
Neutron Imaging ◽  
Low Contrast ◽  
Image Characteristics ◽  
Restoration Algorithm ◽  
Degraded Image ◽  
Neutron Image ◽  
Noise Amplification ◽  
Work Done

Neutron image obtained from a small digital neutron imaging system, always has characteristics of low contrast, blurred edges and serious noise. It is disadvantageous to further analyse information about the sample’s internal structure, so it is essential for the observer to process the degraded image to improve its visual quality. In order to avoid the noise amplification problem of the original Richardson-Lucy (R-L) algorithm, which is adopted to recover degraded image, a restoration algorithm by combining R-L algorithm with Steering Kernel (S-K) algorithm for neutron image is presented in this paper. First S-K algorithm is applied to restrain the noise of the blurred noisy neutron image, as well as improving the signal-to-noise ratio of the image, and then R-L algorithm is used to reconstruct the blurred noisy image. The proposed algorithm is able to make up for the deficiency of R-L algorithm in dealing with the noise amplification problem, which is caused by the repeated iteration, while retaining the details of the image characteristics as much as possible. Comparative experimental results show that the algorithm can obtain satisfactory restoration visual effect for neutron image. The details of the work done are described in this paper.

scholarly journals An Image Defogging Approach Based on a Constrained Energy Functional under Bayesian and Variation Theories

2015 ◽  
Vol 2015 ◽  
pp. 1-14
Author(s):  
Li Zhou ◽  
Du-Yan Bi ◽  
Lin-Yuan He
Keyword(s):  
State Of The Art ◽  
Regularization Parameter ◽  
Energy Functional ◽  
Maximum A Posteriori ◽  
A Posteriori ◽  
Unknown Quantity ◽  
Low Contrast ◽  
Multiplicative Noises ◽  
Image Defogging ◽  
Dark Channel

Hazy images produce negative influences on visual applications in the open air since they are in poor visibility with low contrast and whitening color. Numerous existing methods tend to derive a totally rough estimate of scene depth. Unlike previous work, we focus on the probability distribution of depth that is considered as a scene prior. Inspired by the denoising work of multiplicative noises, the inverse problem for hazy removal is recast as deriving the optimal difference between scene irradiance and the airlight from a constrained energy functional under Bayesian and variation theories. Logarithmic maximum a posteriori estimator and a mixed regularization term are introduced to formulate the energy functional framework where the regularization parameter is adaptively selected. The airlight, another unknown quantity, is inferred precisely under a geometric constraint and dark channel prior. With these two estimates, scene irradiance can be recovered. The experimental results on a series of hazy images reveal that, in comparison with several relevant and most state-of-the-art approaches, the proposed method outperforms in terms of vivid color and appropriate contrast.

scholarly journals Bringing luminance histograms of low-contrast digital images to two-level piecewise uniform distribution

2020 ◽  
Vol 2020 (1) ◽  
pp. 57-63
Author(s):  
Alexey Raukhvarger ◽  
Nikita Poshekhonov
Keyword(s):  
Numerical Methods ◽  
Uniform Distribution ◽  
Digital Images ◽  
Differential Distribution ◽  
Image Brightness ◽  
Low Contrast ◽  
Piecewise Constant ◽  
Average Brightness ◽  
Mathematical Foundations ◽  
Contrast Image

The paper describes the problems of processing digital images for enhancing contrast to increase the distinguishability of details, performed by histogram methods that approximate the reduction of the histogram of image brightness to a given distribution. Using the uniform distribution algorithm does not take much time, but it does not regulate the brightness and contrast of the image processed. It is possible to achieve better distinguishability of details using a normal distribution, as compared to the uniform distribution, but in this case the solution requires numerical methods which take much more time. There has been proposed the algorithm of controlling the contrast of a digital image by bringing the luma histogram to a distribution determined by a piecewise constant differential distribution function with two levels of values. This algorithm helps to control the average brightness and contrast, without resorting to numerical methods, very dark and very light low-contrast images having greater distinguishability of details. The mathematical foundations of the proposed algorithm are presented. There have been studied the possibilities of increasing the detail distinguishability in the processed low-contrast image, as compared to the popular method based on bringing the brightness histogram to a uniform distribution.

scholarly journals METHODS FOR MODELS PARAMETERS ESTIMATE TO SOLVE PROBLEMS ON 3D RECONSTRUCTION OF REAL OBJECTS COMPLEX MODELS

2016 ◽  
Vol 2016 (3) ◽  
pp. 233-242 ◽  
Author(s):  
Владислав Колякин ◽  
Vladislav Kolyakin ◽  
Владимир Аверченков ◽  
Vladimir Averchenkov ◽  
Максим Терехов ◽  
...  
Keyword(s):  
Computer Games ◽  
Three Dimensional ◽  
3D Models ◽  
Model Parameters ◽  
Complex Objects ◽  
Image Brightness ◽  
Real Objects ◽  
Complex Models ◽  
Three Dimensional Models ◽  
Definition Of

Virtual threedimensional (3 D) models of complex objects are used in many fields of science and engineering, such as architecture, industry, medicine, robotics. Besides, 3D models are used in geoinformation systems, computer games, virtual and supplemented reality and so on. Three dimensional models can be formed in dif-ferent ways, one of which consists in 3 D reconstruc-tion. One of the stages of the 3 D reconstruction of complex models of real objects is a definition of the mathematical models of geometric primitives emphasized on the image. One of the ways for the estimate of model parameters is a method of Hough vote and its modifications – Hough probabilistic transformation, Hough random transformation, Hough hierarchical transformation, phase space blurriness, use of a gra-dient of image brightness and so on. As an alternative way for models selection is a choice of suitable points from a set of data.

scholarly journals Homogenization of Random Porous Materials With Low-Order Virtual Elements

2019 ◽  
Vol 5 (3) ◽  
Author(s):  
Marco Pingaro ◽  
Emanuele Reccia ◽  
Patrizia Trovalusci
Keyword(s):  
Elastic Moduli ◽  
Volume Element ◽  
Homogenization Procedure ◽  
Virtual Element Method ◽  
Low Contrast ◽  
Statistical Homogenization ◽  
Random Composites ◽  
Material Contrast ◽  
Virtual Element ◽  
Definition Of

A fast statistical homogenization procedure (FSHP) based on virtual element method (VEM)—previously developed by the authors has been successfully adopted for the homogenization of particulate random composites, via the definition of the representative volume element (RVE), and of the related equivalent elastic moduli. In particular, the adoption of virtual elements of degree one for modeling the inclusions provided reliable results for materials with low contrast, defined as the ratio between mechanical properties of inclusions and matrix. Porous media are then here described as bimaterial systems in which soft circular inclusions, with a very low value of material contrast, are randomly distributed in a continuous stiffer matrix. Several simulations have been performed by varying the level of porosity, highlighting the effectiveness of FSHP in conjunction with virtual elements of degree one.

Edge Enhancement from Low-Light Image by Convolutional Neural Network and Sigmoid Function

IJOSTHE ◽  
2020 ◽  
Vol 7 (1) ◽  
pp. 8
Author(s):  
Puspad Kumar Sharma ◽  
Nitesh Gupta ◽  
Anurag Shrivastava
Keyword(s):  
Input Image ◽  
Sigmoid Function ◽  
Single Image ◽  
Low Light ◽  
Lighting Condition ◽  
Low Contrast ◽  
General Terms ◽  
Degraded Image ◽  
Result Analysis

Due to camera resolution or any lighting condition, captured image are generally over-exposed or under-exposed conditions. So, there is need of some enhancement techniques that improvise these artifacts from recorded pictures or images. So, the objective of image enhancement and adjustment techniques is to improve the quality and characteristics of an image. In general terms, the enhancement of image distorts the original numerical values of an image. Therefore, it is required to design such enhancement technique that do not compromise with the quality of the image. The optimization of the image extracts the characteristics of the image instead of restoring the degraded image. The improvement of the image involves the degraded image processing and the improvement of its visual aspect. A lot of research has been done to improve the image. Many research works have been done in this field. One among them is deep learning. Most of the existing contrast enhancement methods, adjust the tone curve to correct the contrast of an input image but doesn’t work efficiently due to limited amount of information contained in a single image. In this research, the CNN with edge adjustment is proposed. By applying CNN with Edge adjustment technique, the input low contrast images are capable to adapt according to high quality enhancement. The result analysis shows that the developed technique significantly advantages over existing methods.

Sign in / Sign up

Export Citation Format

Share Document