基于空频结合的图像增强的脑肿瘤分割

针对脑部核磁共振图像中含有噪音、对比度低及肿瘤边界不连续模糊等造成肿瘤难以准确分割的问题,提出了一种基于空频域图像增强的脑肿瘤分割算法.首先,采用空频域相结合的增强方法对图像进行增强处理.该方法利用基于邻域的方法,结合了空间域增强算法与基于方向滤波器组的频率域增强算法,具有它们优点的同时,克服了前者导致的图像细节模糊的缺陷及后者带来的对比度降低的缺陷.然后,利用液体向量流的分割方法,对增强后的图像进行分割,得到脑肿瘤区域.实验结果表明,本文的增强方法在增强肿瘤边界特征的同时改善了图像的对比度和清晰度,提高了脑肿瘤分割的准确性.     

融合遗传算法的多域值分块低照度图像增强算法

针对低照度图像对比度低、细节模糊等问题,提出了融合遗传算法的多域值分块低照度图像增强算法.通过遗传算法寻找输入图像亮度通道的最优分割阈值,根据得到的阈值,将亮度通道划分为多个不同曝光级的子图.通过多阈值分块增强算法对所有子图进行评估,根据评估结果调整每个子图的亮度.最后使用多尺度融合方法将输入图像细节信息融合到亮度增强...     

结合小波融合和深度学习的脑胶质瘤自动分割

针对水肿区域边界模糊和瘤内结构复杂多变导致的脑胶质瘤分割不精确问题,本文提出了一种基于小波融合和3D-UNet网络的脑胶质瘤磁共振图像自动分割算法.首先,对脑胶质瘤磁共振图像的T1、T1ce、T2、Flair四种模态进行小波融合以及偏置场校正;然后,提取待分类的图像块;再利用提取的图像块训练3D-UNet网络以对图像块中的像素进行分类;最后加载损失率较小的网络模型进行分割,并采用基于连通区域的轮廓提取方法,以降低假阳性率.对57组Brats2018（Brain Tumor Segmentation 2018）磁共振图像测试集进行分割的结果显示,肿瘤的整体、核心和水肿部分的平均分割准确率（DSC）分别达到90.64%、80.74%和86.37%,这表明该算法分割脑胶质瘤准确率较高,与金标准相近.相比多模态图像融合前,该算法在减少输入网络数据量和图像冗余信息的同时,还一定程度上解决了胶质瘤边界模糊、分割不精确的问题,提高了分割的准确度和鲁棒性.     

基于曲率滤波和梯度变换的图像增强

针对基于梯度变换的图像增强算法抗噪声干扰能力差的问题,引入曲率滤波理论,提出了基于高斯曲率滤波和梯度变换的图像增强算法.该算法通过对图像梯度场进行非线性变换来增强图像对比度,通过构造能量泛函,采用梯度下降法从变换后的梯度场重构出增强后的图像,并利用高斯曲率滤波对梯度下降法迭代过程中的重构图像及其各阶偏微分进行平滑,有效解决了图像重构过程中的噪声非线性放大和扩散问题,同时保留了丰富的细节信息.采用多组边缘模糊图像进行仿真实验,实验结果表明该算法在增强图像边缘对比度的同时,能够有效抑制噪声.     

结合MRF能量和DCE-MRI时域特征的乳腺癌灶分割算法

针对动态增强磁共振影像中乳腺癌灶对比度低、边界模糊且亮度不均匀等特点,提出了一种结合马尔科夫随机场能量和动态增强磁共振影像时域特征的混合活动轮廓模型。首先,基于模糊C均方聚类算法以图像的时域变化特征和亮度构建特征向量,构建模糊速度函数作为活动轮廓模型的边缘探测函数。其次,计算图像的隐马尔科夫场能量,以增强乳腺癌病灶与其他组织的差异。最后,以图中每个像素及其邻近像素的马尔科夫场能量为特征,利用k最近邻算法构建活动轮廓模型的区域项。轮廓曲线在病灶边界上时,区域项及边缘项最小,活动轮廓曲线停止演变,完成对乳腺癌灶的分割。实验结果表明,马尔科夫随机场能量和时域特征均能增强癌灶与其他组织的对比度,使所提方法的分割结果较其他活动轮廓模型更接近医生手工分割结果,对实现精确分割乳腺癌灶有重要意义。     

基于3D卷积神经网络的脑肿瘤图像分割

三维脑胶质瘤磁共振成像肿瘤形状各异、边缘模糊,目前大多数基于2D卷积神经网络的分割方法不能很好的分割三维图像。为了能够准确分割出三维图像中的肿瘤部分,提出一种融合多尺度特征信息的3D卷积神经网络脑肿瘤图像分割方法。利用并行的3D空洞卷积提取特征信息,将不同感受野的信息融合。将Dice损失和BCE损失结合,形成一种新的损失函数并配合恒等映射,进一步提高分割精度。在BraTs2020数据集上对模型进行验证,结果表明,该模型分割的全肿瘤区、核心区和增强区的Dice系数分别为89.1%、83.9%和82.6%。在LGG脑部肿瘤图像数据集上对模型进行验证,结果表明,Dice系数达到了93.3%。所提出的分割方法不仅能够精确的分割三维脑胶质瘤图像,而且同样适用于分割二维脑胶质瘤图像。     

基于Retinex理论与概率非局部均值的红外图像增强方法

针对传统红外图像增强算法中细节模糊及过度增强的问题,提出了一种基于Retinex理论与概率非局部均值相结合的红外图像增强方法.首先通过单尺度Retinex方法调整图像中过暗与过亮部分的灰度级;然后利用概率非局部均值对图像进行分解处理得到基本层与细节层,对基本层采用直方图均衡化拉伸对比度,对细节层采用非线性函数进行增强;最后,将不同层次的结果融合得到对比度与细节增强的红外图像.用该方法对多组不同场景的红外图像进行仿真实验,并将其与多种增强方法进行主、客观对比分析,结果表明所提方法在红外图像的细节及对比度增强方面都获得了更好的效果.     

复杂背景下钢索图像的纹理分割与边界识别

针对复杂背景下钢索图像难以准确分割的问题,提出一种基于纹理分析的钢索图像分割与边界识别方法.采用基于模糊Hough变换的纹理方向检测方法确定钢索走向,利用边缘方向密度直方图作为纹理特征,对与钢索纹理方向相应的边缘方向赋予不同权重,抑制纹理分割中背景的干扰,对钢丝绳图像进行聚类分割,采用检测平行直线的方法确定其边界,并根据算法参量对边界进行修正.在实验中,对比了边缘方向密度直方图特征与灰度共生矩阵、局部二值模式在钢索图像纹理分割中的结果与计算时间,结果表明边缘方向密度直方图特征计算速度快、受背景干扰小,分割准确率高.本文方法无须预先训练,受背景干扰小,可以准确地识别出钢索并确定其边界,能满足钢丝绳视觉检测的要求.     

基于边缘流的煤电厂炉膛火焰图像分割方法

针对炉膛火焰灰度变化不明显采用传统的分割算法无法达到满意分割效果的问题,采用了基于边缘流的分割方法对电厂炉膛火焰图像进行分割;首先选用高精度的灰度边缘流对图像进行分割,得到边缘流的矢量方向和边缘能量,然后再对图像闭合处理得到初始分割图像,最后,再利用颜色相似度对相邻区域进行处理,得到最终分割图像,该方法不仅避免了单纯边缘流算法提取边界不连续无法检出较弱边界的问题,而且也可以避免过分割问题;通过实验表明,基于边缘流的方法是对炉膛火焰图像进行分割的有效方法。     

基于人工蚁群的红外图像分割算法

基于人工蚁群的红外图像分割方法利用模糊非线性增强算子作为启发信息,与信息素共同指导蚂蚁的行为。通过蚂蚁行走路径上的信息素分布进行更新,使得分布在目标路径上的信息素逐渐增大,逐渐向分割图像收敛,最后根据信息素分布提取分割结果。仿真和实验表明,该算法对真实图像得到了理想的分割结果。     

几种直方图变换法在输电接头红外热像增强中的对比研究

由红外热像仪直接得到的热像会受很多外来因素的干扰而致使图像模糊不清、对比度差,由此在故障诊断过程中,需要对热像进行后续增强处理。总结了影响热故障红外检测准确性的外部因素,分析了输电接头热像的基本特征,采用了基于平方根灰度变换直方图修正和全局均衡化两种方法对热像进行了增强处理。在分析上述两种方法优劣的基础上,提出了一种基于线性平滑滤波的局部均衡化方法。结果表明,基于线性平滑滤波的局部均衡化方法对于处理输电接头热像更有效。     

Perceptual contrast enhancement with dynamic range adjustment

Recent years, although great efforts have been made to improve its performance, few Histogram equalization (HE) methods take human visual perception (HVP) into account explicitly. The human visual system (HVS) is more sensitive to edges than brightness. This paper proposes to take use of this nature intuitively and develops a perceptual contrast enhancement approach with dynamic range adjustment through histogram modification. The use of perceptual contrast connects the image enhancement problem with the HVS. To pre-condition the input image before the HE procedure is implemented, a perceptual contrast map (PCM) is constructed based on the modified Difference of Gaussian (DOG) algorithm. As a result, the contrast of the image is sharpened and high frequency noise is suppressed. A modified Clipped Histogram Equalization (CHE) is also developed which improves visual quality by automatically detecting the dynamic range of the image with improved perceptual contrast. Experimental results show that the new HE algorithm outperforms several state-of-the-art algorithms in improving perceptual contrast and enhancing details. In addition, the new algorithm is simple to implement, making it suitable for real-time applications.     

Two-dimensional Otsu's thresholding segmentation method based on grid box filter

Otsu algorithm, an automatic thresholding method, is widely used in classic image segmentation applications. In this paper, a novel two-dimensional (2D) Otsu thresholding algorithm based on local grid box filter is proposed. In our method, firstly by utilizing the coarse-to-fine idea, the 2D histogram is divided into regions by grid technique, and each region is used as a point to form a new 2D histogram, to which 2D Otsu thresholding algorithm and an improved particle swarm optimization (PSO) algorithm are applied to get the region number of the new 2D histogram threshold. Then on the result region, the mean of the 2D histogram is computed base on box filter, and the two algorithms are applied again to obtain the final threshold for the original image. Experimental results on real data show that the proposed algorithm gets better segmentation results than the traditional recursion Otsu algorithm. It significantly reduces the time of segmentation process and simultaneously has the higher segmentation accuracy.     

Image contrast enhancement using adjacent-blocks-based modification for local histogram equalization

Infrared images usually have some non-ideal characteristics such as weak target-to-background contrast and strong noise. Because of these characteristics, it is necessary to apply the contrast enhancement algorithm to improve the visual quality of infrared images. Histogram equalization (HE) algorithm is a widely used contrast enhancement algorithm due to its effectiveness and simple implementation. But a drawback of HE algorithm is that the local contrast of an image cannot be equally enhanced. Local histogram equalization algorithms are proved to be the effective techniques for local image contrast enhancement. However, over-enhancement of noise and artifacts can be easily found in the local histogram equalization enhanced images. In this paper, a new contrast enhancement technique based on local histogram equalization algorithm is proposed to overcome the drawbacks mentioned above. The input images are segmented into three kinds of overlapped sub-blocks using the gradients of them. To overcome the over-enhancement effect, the histograms of these sub-blocks are then modified by adjacent sub-blocks. We pay more attention to improve the contrast of detail information while the brightness of the flat region in these sub-blocks is well preserved. It will be shown that the proposed algorithm outperforms other related algorithms by enhancing the local contrast without introducing over-enhancement effects and additional noise.     

基于热像仪的太赫兹成像及图像增强初步研究

初步利用美国生产的Pyrocam Ⅲ热像仪和SIFIR-50激光器构建了太赫兹(THz)面阵成像系统, 对20元人民币水印进行了2.52 THz激光成像实验, 探索了面阵成像机制和图像增强方法。针对5幅图像叠加后的太赫兹面阵图像, 研究了对比拉伸变换、直方图均衡化和中值滤波等图像增强方法的效果。实验结果表明, 利用此成像系统和后续的图像处理, 能够获得与成像物体较相似的图像; 对于比较暗的图像, 不能单靠对比拉伸变换。采用直方图均衡化方法效果较好, 在直方图均衡化后再运用中值滤波, 图像增强效果会更好。     

自适应红外目标特征增强算法

利用直方图均衡化和灰度变换增强算法,不能有效增强红外图像目标。鉴于此,在研究红外图像特点的基础上,提出了一种自适应红外目标特征增强算法。该算法先对红外图像进行中值滤波,滤除掉图像中的随机噪声,然后利用直方图分割将红外图像分为目标和背景2部分,通过线性加权叠加抑制背景和增强目标。实验表明,该算法不仅能够根据红外图像中目标的灰度特性自适应地选取直方图分割阈值,而且在去除噪声和增加对比度的同时还抑制了背景,达到了预期的效果。该算法尤其适用于目标和背景像素比例相近时直方图具有局域双峰特征的红外图像中目标的增强。     

基于改进型平台直方图的红外均衡化算法

针对红外图像特别是红外弱小目标图像的特点,提出了一种基于改进型平台的直方图均衡算法。在设置统计上限平台阈值的基础上,设置了累计直方图上限阈值,并用修改的映射函数算法对图像进行均衡化处理。算法中的上限统计平台阈值对噪声进行了适当抑制,累计平台阈值自适应控制映射动态范围,从而克服了平台直方图均衡化对动态范围较窄的红外图像过分拉仲的缺点。相对平台直方图的均衡算法,该方法能够对多种复杂场景增强图像整体效果,在抑制噪声的同时较好地保持了图像细节。     

Image enhancement via Median-Mean Based Sub-Image-Clipped Histogram Equalization

This paper presents a robust contrast enhancement algorithm based on histogram equalization methods named Median-Mean Based Sub-Image-Clipped Histogram Equalization (MMSICHE). The proposed algorithm undergoes three steps: (i) The Median and Mean brightness values of the image are calculated. (ii) The histogram is clipped using a plateau limit set as the median of the occupied intensity. (iii) The clipped histogram is first bisected based on median intensity then further divided into four sub images based on individual mean intensity, subsequently performing histogram equalization for each sub image. This method achieves multi objective of preserving brightness as well as image information content (entropy) along with control over enhancement rate, which in turn suits for consumer electronics applications. This method avoids excessive enhancement and produces images with natural enhancement. The simulation results show that MMSICHE method outperforms other HE methods in terms of various image quality measures, i.e. average luminance, average information content (entropy), absolute mean brightness error (AMBE) and background gray level.     

基于动态直方图均匀化的对比度增强方法

为增强显示设备进行视频信号显示时的图像对比度,提出了一种动态直方图均匀化算法,该算法根据对比度增强系数可实现在不同灰度范围内的直方图均匀化,达到不同程度的对比度增强效果。同时为减少进行对比度增强所需的帧存储器,开发出了一种快速简单的输入视频图像帧间相似性检测方法及电路实现,当判定输入视频图像具有相似性时,后续帧的图像采用前面输入图像的对比度增强映射函数。仿真结果表明,提出的对比度增强方法能根据对比度增强系数实现不同程度的对比度增强,有效地提高了显示设备的图像显示质量。