New algorithm for infrared small target image enhancement based on wavelet transform and human visual properties

The key to the wavelet based denoising teehniquea is how to manipulate the wavelet coefficients. By referring to the idea of Inclusive-OR in the design of circuits, this paper proposes a new algorithm called wavelet domain Inclusive-OR denoising algorithm（WDIDA）, which distinguishes the wavelet coefficients belonging to image or noise by considering their phases and modulus maxima simultaneously. Using this new algorithm, the denoising effects are improved and the computation time is reduced. Furthermore, in order to enhance the edges of the image but not magnify noise, a contrast nonlinear enhancing algorithm is presented according to human visual properties. Compared with traditional enhancing algorithms, the algorithm that we proposed has a better noise reducing performanee , preserving edges and improving the visual quality of images.

Method of Infrared Image Enhancement Based on Stationary Wavelet Transform

Aiming at the problem,i.e.infrared images own the characters of bad contrast ratio and fuzzy edges,a method to enhance the contrast of infrared image is given,which is based on stationary wavelet transform.After making stationary wavelet transform to an infrared image,denoising is done by the proposed method of double-threshold shrinkage in detail coefficient matrixes that have high noisy intensity.For the approximation coefficient matrix with low noisy intensity,enhancement is done by the proposed method based on histogram.The enhanced image can be got by wavelet coefficient reconstruction.Furthermore,an evaluation criterion of enhancement performance is introduced.The results show that this algorithm ensures target enhancement and restrains additive Gauss white noise effectively.At the same time,its amount of calculation is small and operation speed is fast.

WavEnhancer: Unifying Wavelet and Transformer for Image Enhancement

Image enhancement is a widely used technique in digital image processing that aims to improve image aesthetics and visual quality. However, traditional methods of enhancement based on pixel-level or global-level modifications have limited effectiveness. Recently, as learning-based techniques gain popularity, various studies are now focusing on utilizing networks for image enhancement. However, these techniques often fail to optimize image frequency domains. This study addresses this gap by introducing a transformer-based model for improving images in the wavelet domain. The proposed model refines various frequency bands of an image and prioritizes local details and high-level features. Consequently, the proposed technique produces superior enhancement results. The proposed model’s performance was assessed through comprehensive benchmark evaluations, and the results suggest it outperforms the state-of-the-art techniques.

Comparative analysis of different methods for image enhancement

Image enhancement technology plays a very important role to improve image quality in image processing. By enhancing some information and restraining other information selectively, it can improve image visual effect. The objective of this work is to implement the image enhancement to gray scale images using different techniques. After the fundamental methods of image enhancement processing are demonstrated, image enhancement algorithms based on space and frequency domains are systematically investigated and compared. The advantage and defect of the above-mentioned algorithms are analyzed. The algorithms of wavelet based image enhancement are also deduced and generalized. Wavelet transform modulus maxima(WTMM) is a method for detecting the fractal dimension of a signal, it is well used for image enhancement. The image techniques are compared by using the mean(μ),standard deviation(?), mean square error(MSE) and PSNR(peak signal to noise ratio). A group of experimental results demonstrate that the image enhancement algorithm based on wavelet transform is effective for image de-noising and enhancement. Wavelet transform modulus maxima method is one of the best methods for image enhancement.

Low-light image enhancement based on Retinex theory and dual-tree complex wavelet transform

In order to enhance the contrast of low-light images and reduce noise in them, we propose an image enhancement method based on Retinex theory and dual-tree complex wavelet transform(DT-CWT). The method first converts an image from the RGB color space to the HSV color space and decomposes the V-channel by dual-tree complex wavelet transform. Next, an improved local adaptive tone mapping method is applied to process the low frequency components of the image, and a soft threshold denoising algorithm is used to denoise the high frequency components of the image. Then, the V-channel is rebuilt and the contrast is adjusted using white balance method. Finally, the processed image is converted back into the RGB color space as the enhanced result. Experimental results show that the proposed method can effectively improve the performance in terms of contrast enhancement, noise reduction and color reproduction.

A Dual-Tree Complex Wavelet Transform-Based Model for Low-Illumination Image Enhancement

Image enhancement is a monumental task in the field of computer vision and image processing.Existing methods are insufficient for preserving naturalness and minimizing noise in images.This article discusses a technique that is based on wavelets for optimizing images taken in low-light.First,the V channel is created by mapping an image’s RGB channel to the HSV color space.Second,the acquired V channel is decomposed using the dual-tree complex wavelet transform(DT-CWT)in order to recover the concentrated information within its high and low-frequency subbands.Thirdly,an adaptive illumination boost technique is used to enhance the visibility of a low-frequency component.Simultaneously,anisotropic diffusion is used to mitigate the high-frequency component’s noise impact.To improve the results,the image is reconstructed using an inverse DT-CWT and then converted to RGB space using the newly calculated V.Additionally,images are white-balanced to remove color casts.Experiments demonstrate that the proposed approach significantly improves outcomes and outperforms previously reported methods in general.

Biomedical Image Processing Using FCM Algorithm Based on the Wavelet Transform

An effective processing method for biomedical images and the Fuzzy C-mean (FCM) algorithm based on the wavelet transform are investigated.By using hierarchical wavelet decomposition, an original image could be decomposed into one lower image and several detail images. The segmentation started at the lowest resolution with the FCM clustering algorithm and the texture feature extracted from various sub-bands. With the improvement of the FCM algorithm, FCM alternation frequency was decreased and the accuracy of segmentation was advanced.

Multi-level denoising and enhancement method based on wavelet transform for mine monitoring

Based on low illumination and a large number of mixed noises contained in coal mine, denoising with one method usually cannot achieve good results, so a multi-level image denoising method based on wavelet correlation relevant inter-scale is presented. Firstly, we used directional median filter to effectively reduce impulse noise in the spatial domain, which is the main cause of noise in mine. Secondly, we used a Wiener filtration method to mainly reduce the Gaussian noise, and then finally used a multi-wavelet transform to minimize the remaining noise of low-light images in the transform domain. This multi-level image noise reduction method combines spatial and transform domain denoising to enhance benefits, and effectively reduce impulse noise and Gaussian noise in a coal mine, while retaining good detailed image characteristics of the underground for improving quality of images with mixing noise and effective low-light environment.

Research on Wavelet-Based Algorithm for Image Contrast Enhancement

A novel wavelet-based algorithm for image enhancement is proposed in the paper. On the basis of multiscale analysis, the proposed algorithm solves efficiently the problem of noise over-enhancement, which commonly occurs in the traditional methods for contrast enhancement. The decomposed coefficients at same scales are processed by a nonlinear method, and the coefficients at different scales are enhanced in different degree. During the procedure, the method takes full advantage of the properties of Human visual system so as to achieve better performance. The simulations demonstrate that these characters of the proposed approach enable it to fully enhance the content in images, to efficiently alleviate the enhancement of noise and to achieve much better enhancement effect than the traditional approaches. Key words wavelet transform - image contrast enhancement - multiscale analysis CLC number TP 391 Foundation item: Supported by the National Natural Science Foundation of China (69931010)Biography: Wu Ying-qian (1974-), male, Ph. D, research direction: image processing, image compression and wavelet.

Vision Enhancement Technology of Drivers Based on Image Fusion

The rise of urban traffic flow highlights the growing importance of traffic safety.In order to reduce the occurrence rate of traffic accidents,and improve front vision information of vehicle drivers,the method to improve visual information of the vehicle driver in low visibility conditions is put forward based on infrared and visible image fusion technique.The wavelet image confusion algorithm is adopted to decompose the image into low-frequency approximation components and high-frequency detail components.Low-frequency component contains information representing gray value differences.High-frequency component contains the detail information of the image,which is frequently represented by gray standard deviation to assess image quality.To extract feature information of low-frequency component and high-frequency component with different emphases,different fusion operators are used separately by low-frequency and high-frequency components.In the processing of low-frequency component,the fusion rule of weighted regional energy proportion is adopted to improve the brightness of the image,and the fusion rule of weighted regional proportion of standard deviation is used in all the three high-frequency components to enhance the image contrast.The experiments on image fusion of infrared and visible light demonstrate that this image fusion method can effectively improve the image brightness and contrast,and it is suitable for vision enhancement of the low-visibility images.

Enhancement of Biomass Material Characterization Images Using an Improved U-Net

For scanning electronmicroscopes with high resolution and a strong electric field,biomass materials under observation are prone to radiation damage from the electron beam.This results in blurred or non-viable images,which affect further observation of material microscopic morphology and characterization.Restoring blurred images to their original sharpness is still a challenging problem in image processing.Traditionalmethods can’t effectively separate image context dependency and texture information,affect the effect of image enhancement and deblurring,and are prone to gradient disappearance during model training,resulting in great difficulty in model training.In this paper,we propose the use of an improvedU-Net(U-shapedConvolutional Neural Network)to achieve image enhancement for biomass material characterization and restore blurred images to their original sharpness.The main work is as follows:use of depthwise separable convolution instead of standard convolution in U-Net to reduce model computation effort and parameters;embedding wavelet transform into the U-Net structure to separate image context and texture information,thereby improving image reconstruction quality;using dense multi-receptive field channel modules to extract image detail information,thereby better transmitting the image features and network gradients,and reduce the difficulty of training.The experiments show that the improved U-Net model proposed in this paper is suitable and effective for enhanced deblurring of biomass material characterization images.The PSNR(Peak Signal-to-noise Ratio)and SSIM(Structural Similarity)are enhanced as well.

Contrast Enhancement of Radiographs Using Shift Invariant Wavelet Transform

A novel approach using shift invariant wavelet transform is presented for the contrast enhancement of radiographs. By exploiting cross-scale correlation among wavelet coefficients, edge information of radiographic images is extracted and protected, while noise is smoothed out in the wavelet domain. Radiographs are then reconstructed from the transform coefficients modified at multi-scales by nonlinear enhancement operator. The method can achieve effectively contrast enhancement and edge-preserved denoising simultaneously, yet it is capable of giving visually distinct images and offering considerable benefits in medical diagnosis.

A Robust Non-Blind Watermarking for Biomedical Images Based on Chaos

The advent of the Internet in these last years encouraged a considerable traffic of digital images. In the sanitary field, precisely in telemedicine branch, medical images play a very important role for therapeutic diagnoses. Thus, it is necessary to protect medical images data before transmission over the network to preserve their security and prevent unauthorized access. In this paper, a secure algorithm for biomedical images encryption scheme based on the combination of watermarking technique and chaotic function is proposed. In the proposed method, to achieve high security level performances, a non-blind hybrid watermarking technique with audio signal, Discrete Wavelet Transform is used;smoothness is also used as selected criteria;the iterations obtained by the chaotic sequences are essential and allow a good realization of the encryption process. One of the main advantages of chaos-based encryption schemes is the generation of a large number of key spaces to resist brute force attacks from the encryption algorithm. The experimental results presented in this paper attest to the invisibility and robustness of the proposed algorithm combining watermarking and chaos-based encryption.

灰度变换下多模态刚性医学图像分层增强仿真

为了提升医学图像增强效果,有效保留图像细节,提出基于灰度变换的多模态刚性医学图像增强算法。对多模态刚性医学图像去噪处理,采用免疫优化算法对自适应阈值优化处理,选择最佳阈值。根据去噪结果通过小波变换将医学图像分解为多个不同区间,分别对各个区间实行灰度变换处理,根据变换后的结果获取分层增强效果,实现多模态刚性医学图像的整体增强。经实验测试结果表明,所提算法可以获取更加满意的医学图像增强效果,提高了图像清晰度,图像视觉效果显著增强。

深度生成模型下缺损图像修复方法仿真研究

图像在存储或传输过程中容易产生缺损,为获取全面的图像信息,提出一种基于深度生成模型的缺损图像修复方法。利用小波线性变换特征,在小波逆变换过程中选取合适的阈值去除图像噪声,得到初始图像,利用深度生成模型中的生成对抗网络增强图像质量,通过对抗训练增强缺损图像质量,将图像修复问题转换成像素填充问题,缩短结构部分与破损区域的距离,生成缺损图像预填充结果,利用PDE有限差分修复缺损图像中心点信息,利用人工复原法修改等照度线方向权重,实现缺损图像修复。实验结果表明,所提方法修复效果较好,能最大程度保留原始图像信息。

小波域在无线局域网络信号增强中的应用

为提升无线局域网络信号增强中的去噪效果,应用小波域思想,设计一种无线局域网络信号增强算法.针对无线局域网络,收集无线局域网络原始功率谱数据,通过功率谱拟合因子提取信号特征,识别网络信号.对于识别的无线局域网络信号,通过过零率和短时功率提取该信号.基于小波域对无线局域网络信号实施去噪处理,分为二维小波变换、二进剖分、信号重构三个步骤.通过贝叶斯方法,在实施稀疏字典训练的同时,实现无线局域网络信号的增强处理,在训练中结合K-SVD算法,将信号增强过程和稀疏字典学习过程进行迭代和融合.将MATLAB R2019a作为测试设计算法的实验平台,利用计算机开展算法性能测试.测试结果表明:设计算法的无线局域网络信号增强性能良好,同时信号去噪性能较强,说明算法满足设计需求,在完善细节后可以投入实际应用.

级联离散小波多频带分解注意力图像去噪方法

针对图像去噪网络中下采样导致高频信息损失和细节保留能力差的问题,设计了一种级联离散小波多频带分解注意力图像去噪网络。其中多尺度级联离散小波变换结构将原始图像分解为多个尺度下的高低频子带来代替传统下采样,能减少高频信息损失。多频带特征增强模块使用不同尺度的卷积核并行处理高低频特征,在子网络每一级下重复使用两次,可增强全局和局部的关键特征信息。多频带分解注意力模块通过注意力评估纹理细节成分的重要性并加权不同频带的细节特征,有助于多频带特征增强模块更好地区分噪声和边缘细节。多频带选择特征融合模块融合多尺度多频带特征增强选择性特征,提高模型对于不同尺度噪声的去除能力。在SIDD和DND数据集上,所提方法的PSNR/SSIM指标分别达到了39.35 dB/0.918、39.72 dB/0.955。实验结果表明,该方法的性能优于主流去噪方法,同时具有更清晰的纹理细节和边缘等视觉效果。

一种激光红外图像的小区域目标定位方法

激光红外图像中的小区域目标定位复杂程度较高,在提取图像特征过程中容易降低图像分辨率,导致小区域目标模糊,对目标定位精度产生一定影响。为了提高目标定位效果,引入投影变换矩阵,提出激光红外图像的小区域目标定位方法。采用小波变换方法分解激光红外图像,结合直方图均衡方法增强图像处理,通过卷积操作增强图像边缘点,提升激光红外图像对比度及分辨率。使用覆盖算子提取激光红外图像目标特征,根据特征点相似性确定小区域目标范围,建立投影变换矩阵匹配小区域目标,实现目标位置定位。实验结果表明,使用所提方法开展激光红外图像小区域目标定位时,定位误差为0.7%、定位精度平均为94.0%、算法计算效率为96.3%、定位匹配度为100%,可以准确定位目标位置。

基于改进小波变换的造纸车间网络通信弱信号增强研究

传统造纸车间网络通信弱信号增强方法由于仅提取了造纸车间网络通信弱信号的单一参量,导致对其的增强效果不佳。为解决这一问题,设计一种基于改进小波变换的造纸车间网络通信弱信号增强方法。首先,利用信号采集设备采集造纸车间网络通信信号,并对采集信号进行预处理;其次,计算感知造纸车间网络通信弱信号,在传统小波变换的基础上对其进行改进,并由此提取造纸车间网络通信弱信号的频率参量、幅度参量等多个信号参量;最后,利用提取的信号参量,将相似信号进行叠加,以完成弱信号增强。实验结果表明,与以往的造纸车间网络通信弱信号增强方法相比,设计的基于改进小波变换的造纸车间网络通信弱信号增强方法在实际应用中信号强度更高,增强效果更好。

基于离散小波域深度残差学习的矿区遥感图像增强算法

实现矿区遥感图像增强处理,有助于提升后续图像判别以及相关监测分析效率。以往矿区遥感图像增强一般采用滤波、灰度变换等方法,往往会导致图像大量细节信息丢失,在很大程度上影响了后续判读分析。近年来,深度学习方法逐步应用于图像增强处理,但该方法很大程度上依赖于模型设计和参数合理取值,需要进行大量的试验和优化方可取得理想效果。将深度学习方法(Deep Learning,DL)与离散小波变换(Discrete Wavelet Transform,DWT)相结合,提出了一种基于离散小波域深度残差学习的矿区遥感图像增强算法。首先将图像进行单级二维离散小波变换,得到4个子带;然后将4个子带系数输入深度学习残差网络,预测相应的残差图像增加4个子带图像和残差图像作为二维小波变换的新子带;最后通过二维离散小波逆变换得到增强图像。试验结果表明:所提算法相对于直方图均衡化和超分辨率重建等方法而言,无论在图像视觉效果以及峰值信噪比、结构相似性、均方误差等评价指标上都具有较好优势,反映出将离散小波变换与深度学习方法相结合,有助于提升矿区遥感图像视觉效果,方便后续图像解译判读工作。