A fracture enhancement method based on the histogram equalization of eigenstructure-based coherence

Eigenstructure-based coherence attributes are efficient and mature techniques for large-scale fracture detection. However, in horizontally bedded and continuous strata, buried fractures in high grayscale value zones are difficult to detect. Furthermore, middleand small-scale fractures in fractured zones where migration image energies are usually not concentrated perfectly are also hard to detect because of the fuzzy, clouded shadows owing to low grayscale values. A new fracture enhancement method combined with histogram equalization is proposed to solve these problems. With this method, the contrast between discontinuities and background in coherence images is increased, linear structures are highlighted by stepwise adjustment of the threshold of the coherence image, and fractures are detected at different scales. Application of the method shows that it can also improve fracture cognition and accuracy.

Improved Algorithm of Histogram Equalization and Its Actualization

A new improved algorithm of histogram equalization was discussed and actualized by analyzing the traditional algorithm. This improved algorithm has better effect than the traditional one, especially it is used to process poor quality images.

Contrast Limited Adaptive Histogram Equalization for Qualitative Enhancement of Myocardial Perfusion Images

This paper establishes an efficient color space for the contrast enhancement of myocardial perfusion images. The effects of histogram equalization and contrast limited adaptive histogram equalization are investigated and the one which gives good enhancement results is extended to the suitable color space. The color space which gives better results is chosen experimentally. Uniqueness of this work is that contrast limited adaptive histogram equalization technique is applied to the chrominance channels of the cardiac nuclear image, leaving the luminance channel unaffected which results in an enhanced image output in color space.

Morphological Filters and Wavelet-based Histogram Equalization Image Enhancement for Weak Target Detection

Image enhancement methods are typically aimed at improvement of the overall visibility of features. Though histogram equalization can enhance the contrast by redistributing the gray levels, it has the drawback that it reduces the information in the processed image. In this paper, we present a new image enhancement algorithm. After histogram equalization is carried out, morphological filters and wavelet-based enhancement algorithm is used to clean out the unwanted details and further enhance the image and compensate for the information loss during histogram equalization. Experimental results show that the morphological filters and wavelet-based histogram equalization algorithm can significantly enhance the contrast and increase the information entropy of the image.

An Improved Histogram Equalization Method in the Traffic Monitoring Image Processing Field

To process the traffic monitoring image, a local Histogram Equalization method based on fuzzy mathematics was proposed in this paper. In this paper, firstly, we define a function to measure the similarity degree of two images. Then, a suitable Gaussian fuzzy distribution function was chose to generate a 3 × 3 matrix of influential factors. In order to reduce the artificial boundaries, we combined the 3 × 3 influential matrix with a 3 × 3 smooth filter matrix to get the final smooth-influ- ence matrix. Finally, the smooth-influence matrix was used to process the center block image. The simulation results demonstrated that the proposed method can reduce time consumption while improving the image contrast and can get satisfactory results.

Contrast Enhancement Using Weighted Coupled Histogram Equalization with Laplace Transform

Histogram equalization is a traditional algorithm improving the image contrast,but it comes at the cost of mean brightness shift and details loss.In order to solve these problems,a novel approach to processing foreground pixels and background pixels independently is proposed and investigated.Since details are mainly contained in the foreground,the weighted coupling of histogram equalization and Laplace transform were adopted to balance contrast enhancement and details preservation.The weighting factors of image foreground and background were determined by the amount of their respective information.The proposed method was conducted to images acquired from CVG⁃UGR and US⁃SIPI image databases and then compared with other methods such as clipping histogram spikes,histogram addition,and non⁃linear transformation to verify its validity.Results show that the proposed algorithm can effectively enhance the contrast without introducing distortions,and preserve the mean brightness and details well at the same time.

Underwater Image Saliency Detection Based on Improved Histogram Equalization

In order to solve the problem of unsatisfactory detection effect of underwater visual saliency map, an image saliency detection algorithm based on improved histogram equalization is proposed. Underwater images are often not clear enough because the refraction of light underwater causes insufficient image resolution. Therefore, in order to solve the existing problems of traditional histogram equalization algorithm, an improved histogram equalization method is proposed to enhance the quality of images, which makes the saliency regions smoother and clearer. In this paper, the simulation experiments were conducted on UIEBD dataset and DLOU_underwater dataset. The experimental results show the effectiveness, robustness and accuracy of the proposed algorithm.

Marchenko imaging based on self-adaptive traveltime updating

Marchenko imaging obtains the subsurface reflectors using one-way Green’s functions,which are retrieved by solving the Marchenko equation.This method generates an image that is free of spurious artifacts due to internal multiples.The Marchenko imaging method is a target-oriented technique;thus,it can image a user specified area.In the traditional Marchenko method,an accurate velocity model is critical for estimating direct waves from imaging points to the surface.An error in the velocity model results in the inaccurate estimation of direct waves.In turn,this leads to errors in computation of one-way Green’s functions,which then affects the final Marchenko images.To solve this problem,in this paper,we propose a self-adaptive traveltime updating technique based on the principle of equal traveltime to improve the Marchenko imaging method.The proposed method calculates the time shift of direct waves caused by the error in the velocity model,and corrects the wrong direct wave according to the time shift and reconstructs the correct Green’s functions.The proposed method improves the results of imaging using an inaccurate velocity model.By comparing the results from traditional Marchenko and the new method using synthetic data experiments,we demonstrated that the adaptive traveltime updating Marchenko imaging method could restore the image of geological structures to their true positions.

基于强噪声条件下的激光图像边缘检测研究

边缘检测是激光图像处理的一个重要步骤,针对当前激光图像边缘检测误差大,易受噪声干扰等缺陷,为了获得完整的激光图像边缘,设计了基于强噪声条件下的激光图像边缘检测方法。首先采集激光图像,采用直方图均衡技术对原始激光图像进行增强处理,改善激光图像质量,然后采用小波变换去除激光图像噪声,并采用Canny算子进行激光图像边缘检测,最后测试结果表明,与当前激光图像边缘检测方法相对比,本方法能够检测出更多激光图像边缘细节,激光图像边缘检测精度的平均值超过93%,而且激光图像边缘检测时间控制60 ms以内,为激光图像提供了一种高精度检测技术。

基于改进直方图均衡的SF6泄漏区域增强算法

SF6气体红外成像易受环境噪声影响,呈低对比度与低信噪比特性。导致现有算法无法自适应增强SF6泄漏区域和抑制高斯噪声。针对上述问题,提出一种基于改进HE的SF6泄漏区域增强算法。该算法首先采用单尺度Retinex处理原始SF6图像获得反射图像,然后利用引导滤波将反射图像分解为细节层和基本层,最后采用改进的直方图均衡化来自适应处理基本层,并将增强后的图像进行融合来获得最终的图像。实验结果表明:本文算法不仅能够自适应增强泄漏区域的对比度,而且具有良好边缘保持特性和抑制高斯噪声的性能。其增强效果优于现有的SF6红外图像增强算法。有效改善了SF6红外图像低对比度和低信噪比特性。

基于Raspberry Pi的安全帽识别系统设计与实现

为了便于施工危险区域人员的自动化识别,提出了一种基于Raspberry Pi的安全帽识别算法。该算法将摄像头采集到的原始视频图像进行滤波、形态学等处理,再对图像中的安全帽进行识别。对于彩色安全帽,将原始图像转换到HSV空间,根据不同颜色色调阈值的设定同时识别红、黄、蓝三种颜色的安全帽,并结合形状特征剔除错误目标。对于白色安全帽,将原始图像转化成B通道下的灰度图像,解决了将黄色误检为白色的问题。采用V通道直方图均衡化的方法,提升了昏暗光线条件下的图像亮度。实验结果表明:在无需提前训练的情况下,算法对于单色安全帽识别准确率超过了91%,对于多色安全帽识别率超过了90%,为施工危险区域的安全隐患排查和作业管控提供了解决方案。

用于实时图像增强的灰度等间距密度均衡改进算法

实时图像的增强处理,除了保证单帧图像具有较高的对比度,还应考虑处理算法的实时性和图像序列间增强效果的连贯性。灰度等间距密度均衡算法通过去除冗余灰度级后进行有效灰度级等间距重排,可以有效增强图像对比度。本文以灰度等间距密度均衡增强算法为基础,对其有效灰度级有效阈值选取、过度增强等问题进行了相应改进,以满足连续图像序列的实时增强处理需求。实验结果表明,改进算法可以有效避免图像局部变化对整体增强效果的影响。对于1920×1080分辨率的图像,单帧处理时间约为32 ms。本改进算法对于连续图像序列具有良好的增强效果,且能够较好地满足实时图像增强对于连贯性、实时性、鲁棒性的处理需求。

基于直方图均衡化的毛织物服装印花缺陷检测

为了保证毛织物印花服装的生产质量,提出基于直方图均衡化的毛织物服装印花缺陷检测方法。设置毛织物服装印花不同缺陷特征作为检测标准,利用光学成像原理采集毛织物服装印花图像,通过颜色转换、图像滤波等步骤,实现初始印花图像的预处理;利用直方图均衡化技术提取服装印花图像特征,通过特征匹配确定缺陷状态与类型,实现毛织物服装印花缺陷的检测。测试结果表明,优化设计方法得出缺陷面积检测误差的平均值为0.09 mm^(2),缺陷类型检测错误率较低。

基于改进凸包缺陷算法的扎带定位方法

针对传统视觉在检测捆扎带时存在难检、漏检、定位扎带位置困难和速度慢等问题,提出一种基于改进凸包缺陷算法的扎带定位方法。采用自适应直方图均衡化图像增强算法,以增强编织袋区域与背景的对比度;利用快速凸包算法获得编织袋轮廓的凸包,减少获取凸包的时间;最后,通过改进凸包缺陷算法对编织袋轮廓凸包进行缺陷检测,根据检测结果中凸包缺陷点的位置和缺陷深度进行筛选得到扎带定位点。同时为验证该算法的准确性与鲁棒性,在具有复杂背景干扰的环境下进行实验,将传统凸包缺陷算法与改进后的凸包缺陷算法进行对比分析。实验结果表明:相比于传统凸包缺陷算法无法检测出编织袋轮廓的全部缺陷从而存在漏检,改进后的凸包缺陷算法漏检率为0,定位误差小于4 mm,可有效定位扎带位置并具有较高的鲁棒性。

线性变换与局部均衡融合的红外图像增强

为了改善红外图像的效果,提升对比度和清晰度,丰富边缘细节信息,提出了融合线性变换和局部均衡的红外图像增强方法。利用图像的像素值分布,对像素值进行自适应的分段线性变换,并用局部的直方图均衡增强图像;分别计算两张增强图像的权重图。对比度权重、显著性权重和亮度分布权重;以拉普拉斯金字塔和高斯金字塔的方式,分别对增强图像和权重图进行分解,将分解的图像与权重图进行多尺度线性融合,获得效果理想的增强图像。结果表明,相对于现有方法,本文中提出的方法增强图像的视觉效果更清晰,信息熵、平均梯度和变异系数分别比现有方法高出9.03%、23.87%和9.97%以上。该研究可更有效地提高红外图像增强的性能。

基于CLAHE-PCA的矿井低照度图像增强研究

地下矿山巷道环境往往面临光线不足,难以通过获取其暗通道图像判断岩体剥落等异常情况。针对矿井巷道暗通道图像对比度低的问题,提出了一种基于CLAHE-PCA的图像增强算法。首先使用CLAHE算法将获取的矿井巷道原始暗通道图像做对比度增强处理,然后使用自适应Gamma算法对亮度低的图像予以增加对比度矫正;将矫正后获得的灰度图转为RGB图像,通过PCA对其进行平滑处理,以便更多地还原暗通道图像的细节。以峰值信噪比、结构相似性、平均梯度和信息熵等作为评价指标,对试验结果进行验证。结果表明:该方法能够有效处理低对比度的矿井巷道图像,处理后的图像结构相似性达到93%,鲁棒性强,同时能够更多地还原图像的细节。

复杂特征全景图像视觉传达效果优化仿真

由于全景拍摄中不同相机镜头的焦点距离不固定,因此在拼接之前相邻两个局部图像间就会产生视差,且距离越近的物体产生视差会越大。全景图像效果的优化是提升视觉质量的关键。提出一种复杂特征全景图像视觉传达效果优化方法。利用两种色彩空间模型与二维经验小波变换法,提取出图像的光谱特征与纹理特征。采用马拉特算法完成小波变换与小波分解,得到复杂特征融合后的全景图像重构结果。基于能量函数及负相关性,界定视觉传达效果的降噪优化目标,设计四阶偏微分方程的降噪模型,完成图像降噪处理。基于此,融合冲击滤波器与直方图均衡化,根据各连通分量对应的子图像,拉伸图像灰度级分布形式,增强细节信息,实现视觉传达效果优化。选取一幅具有复杂特征的全景图像,从感官与数据量化两方面评价不同方法下全景图像的优化效果。实验结果验证了上述方法提高了图像的对比度、清晰度、丰富度,且处理时间更短,具备良好的实践性与实时性。

基于前背景特性的逆光交通场景图像增强

由于逆光交通场景下采集到的图像存在前景亮度过低、背景亮度失真等特点,导致采集图像清晰度低、信息丢失严重和可识别性差,针对逆光图像前背景的不同特性,研究提出了一种分区域增强方法。对逆光图像使用最大类间方差法(OTSU法)分割图像的前景和背景;对逆光图像全局使用LIME方法,提升前景亮度的同时保持色彩的失真度;单独将背景部分RGB三个通道上的全局直方图均衡化结果一一映射到对应的限定区间内,提高了背景的对比度;使用Canny算子检测出前背景拼接处的黑边,根据黑边生成3个自适应的滤波模板对黑边进行分步均值滤波处理,消除了黑色边缘,提升了图像的视觉质量。在实验室自建的CHD_B数据集上,所提方法在4种常用客观评价指标上综合占优。实验结果表明,所提出的图像增强算法能有效地消除图像中的逆光现象。

港口场景集装箱锁孔目标智能检测研究

为解决集装箱图像受到外界光线环境的影响造成信息对比度低、暗部细节信息不明显和图像信息难以辨认清等问题,提出一种新的图像增强算法,其重点是利用非线性变换,提高图像的暗部细节,将原本的RGB模型转化到HSV模型进行均衡化。利用实际工程中港口所提供的测试数据集,使用已训练好的模型进行广泛的实验。实验还探究了图像增强算法对卷积神经网络性能的影响,利用对比度受限的自适应直方图均衡化、伽马校正、拉普拉斯变换以及原始图像与该算法进行对比,使用10折交叉验证了该算法的精确率、召回率均大于其他的算法。采用配对T检验,比较分析采用各算法间的各项指标差异,结果表明:该算法相比其他算法的效果要好。

基于自适应条件直方图均衡的红外图像细节增强算法

红外图像普遍存在对比度低、细节不清晰、边缘特征不突出等问题。针对这些问题,本文提出了一种自适应条件直方图均衡的红外图像细节增强算法。采用引导滤波将红外图像分解为背景层和细节层;然后采用自适应阈值邻域条件直方图结合对比度受限直方图均衡方式,对背景层图像进行灰度压缩和对比度增强;接着利用引导滤波的中间计算结果构造滤噪掩模,在对细节层进行增强的同时有效滤除背景噪声;最后将背景层和细节层处理结果进行线性融合得到细节增强后红外图像。主观评价和客观数据计算表明,本文提出的红外图像细节增强算法无须手动调节参数即可实现对各类场景的自适应,可以在抑制噪声的前提下,有效增强图像细节,并提升图像整体对比度水平。对算法进行了嵌入式移植,显示效果和资源占用表明算法具有很强的工程化应用水平。