Mean Shift的渐进无偏变换图像配准

基于标志点对应关系的图像配准方法不能保证变换的无偏性,一般不适用于大形变配准问题。该文提出了一种基于标志点对应关系的渐进式无偏变换图像配准方法,该方法利用少量的初始标志点对,通过Mean Shift迭代寻找对应标志点对,构造无偏性较好的变换函数,逐步得到一致的配准结果。文中详细讨论了标志点的分布对变换函数无偏性的影响,实验结果表明该文方法可以同时适用于大形变和小形变配准,是一种简单、有效的配准方法。     

基于紧支径向基函数内插的图像修复算法

该文提出一种基于紧支径向基函数插值的图像修复算法,该算法将图像看成残缺的三维散乱点集,将图像修复问题转化为三维数据的曲面重建问题。采用径向基函数曲面重建的方法构造出逼近三维点集的隐函数曲面,实现对残缺部分的插值,并对重构曲面采样得到残缺部分的像素值。紧支径向基函数可使求解权系数的线性系统的系数矩阵具有稀疏带状结构,从而降低算法的复杂度。实验结果表明,该算法是一种实用对图像修复算法,可得到良好的修复效果。     

周期紧支撑径向基函数对BEMD的优化

该文提出了一种优化二维经验模式分解 (Bidimensional Empirical Mode Decomposition, BEMD)的方法。周期紧支撑径向基函数满足不同程度光滑性,能够容忍数据点集不规则性,避免出现上冲现象,而且大大减少了计算量和存储量,特别是能够消除Gibbs现象,抑制边界效应。实验证实本文提出的利用周期紧支撑径向基函数改进BEMD方法,能够获得较好的BEMD分解结果。     

基于径向基函数物质点法的数值模拟和软件开发

物质点法的求解精度依赖于物质点和背景网格节点之间映射插值函数的选取,传统的物质点法使用的是线性插值函数,但是由于单元之间只存在着C0连续性,传统的物质点法容易产生噪声。径向基函数保存了无网格法的优点,并具有高阶光滑连续的特点,而且径向基函数只需要局部支撑域中的节点信息来构造插值函数,这就大大简化了形函数及其导数的形成。本文将径向基函数引入物质点法以克服传统物质点法中单元数据映射产生的各种问题。同时利用Fortran语言开发了径向基函数物质点法数值模拟工具箱,对所开发的工具箱算例验证。     

边界模糊图像的径向基函数神经网络分割方法研究

边界模糊图像不同区域之间没有明确的分界,用传统的图像分割方法难以得到很好的分割结果。本文研究了径向基函数网络的工作实质及其用于图像分割的机理,分析了径向基函数神经网络的特点,针对边界模糊图像,应用不同结构的径向基函数神经网络对其进行图像分割,验证了径向基函数网络用于图像分割的有效性以及算法速度上的优越性。     

基于GA-RBF神经网络的光学图像背景抑制方法

根据图像背景的局部平稳性,提出了通过逼近背景局部相关特性来估计图像背景的方法,并且采用RBF神经网络来逼近图像背景的这种局部相关性.文中根据径向基函数神经网络的训练要求,用遗传算法来训练神经网络中的各个参数.实验结果表明,训练后的神经网络背景抑制算法能够很好地抑制图像中的背景,并同时增强了目标信号.     

一种新的保边缘滤波算法

该文提出了一种新的保边缘滤波算法,该算法根据图像区域的局部方差大小动态调整滤波器的支撑集的大小。方差越大的区域,说明其高频分量越多,支撑集就越小。为了能在滤波的同时尽量保护图像边缘,该算法还根据像素点和中心点的方向矢量同支撑集内的平均梯度的夹角把支撑集内的像素点分成不同的集合,并给予沿着图像边缘的集合以较大的加权值以及垂直边缘方向的集合小的加权值,从而保证了边缘不模糊。从滤波结果看,经该算法处理过的图像的峰值信噪比(PSNR)明显高于中值滤波器处理过的图像,对细节比较丰富的图像,高于近 3dB。     

基于Hough变换的低分辨率雷达目标识别

针对低分辨率雷达目标的识别问题,提出了一种基于Hough变换的特征提取方法.通过对Hough变换后参数空间进行特征定义来描述参数空间灰度图像的纹理分布特点,进而描述图像空间目标的形状特征.文中利用该方法结合径向基函数神经网络对低分辨率雷达船只目标轮廓像进行特征提取并识别,取得了较高的识别率.     

数字水印中的正交小波基

该文主要研究了水印算法中小波基的选择和正交小波基的性质与水印稳健性的关系。研究结果表明:正交小波基的正则性、消失矩阶数、支撑长度以及小波图像能量在低频带的集中程度对水印稳健性的影响极小。同时也得到了一个有意义的结论:Haar小波比较适合应用于图像水印。该文还研究了在水印算法中,小波变换级数和嵌入公式的选取及其它一些问题。     

基于邻域结构和高斯混合模型的非刚性点集配准算法

非刚性点集配准算法在实际应用中要求对噪声、遮挡或异常点具有很好的鲁棒性。该文采用高斯混合模型并结合点的邻域结构信息实现非刚性点集配准。使用高斯混合模型表示模型点集,通过高斯径向基函数构建变换模型。并根据点的邻域结构信息决定高斯混合模型中每个高斯组成部分所占的比例。在EM算法的期望步(E-step)阶段求解点的对应关系,在最大化步(M-step)阶段求解异常点比例系数和变换的闭合形式解,直至算法收敛得到最优解。通过在合成数据和实际的视网膜图像上的实验,与目前几种先进的点集配准方法进行了比较,证明该算法具有较好的配准效果和鲁棒性。     

COMPACT SUPPORT THIN PLATE SPLINE ALGORITHM

Common tools based on landmarks in medical image elastic registration are Thin Plate Spline (TPS) and Compact Support Radial Basis Function (CSRBF). TPS forces the corresponding landmarks to exactly match each other and minimizes the bending energy of the whole image. However, in real application, such scheme would deform the image globally when deformation is only local. CSRBF needs manually determine the support size, although its deformation is limited local. Therefore, to limit the effect of the deformation, new Compact Support Thin Plate Spline algorithm (CSTPS) is approached, analyzed and applied. Such new approach gains optimal mutual information, which shows its registration result satisfactory. The experiments also show it can apply in both local and global elastic registration.     

Multiple transformation function estimation for image enhancement

Most deep learning-based image enhancement algorithms have been developed based on the image-to-image translation approach, in which enhancement processes are difficult to interpret. In this paper, we propose a novel interpretable image enhancement algorithm that estimates multiple transformation functions to describe complex color mapping. First, we develop a histogram-based multiple transformation function estimation network (HMTF-Net) to estimate multiple transformation functions by exploiting both the spatial and statistical information of the input images. Second, we estimate pixel-wise weight maps, which indicate the contribution of each transformation function at each pixel, based on the local structures of the input image and the transformed images obtained by each transformation function. Finally, we obtain the enhanced image as the weighted sum of the transformed images using the estimated weight maps. Extensive experiments confirm the effectiveness of the proposed approach and demonstrate that the proposed algorithm outperforms state-of-the-art image enhancement algorithms for different image enhancement tasks.     

基于二维概率密度函数比较的SAR图像变化检测方法

该文将传统区域统计分布特征变化检测方法拓展到2维特征空间,提出一种基于2维概率密度函数比较的SAR图像变化检测方法。该方法首先将观测区域内相邻像素的灰度值组合成2维观测矢量,而后采用2维Gram- Charlier展开式对观测矢量在不同时相图像中的2维概率密度函数分别进行估计,在此基础上,借助K-L散度理论对2维概率密度函数在不同时相图像间的变化大小进行定量分析以实现变化检测。实验结果表明,与传统方法相比,该文方法具有更优的检测性能。     

Robust image hash function using local color features

Conventional image hash functions only exploit luminance components of color images to generate robust hashes and then lead to limited discriminative capacities. In this paper, we propose a robust image hash function for color images, which takes all components of color images into account and achieves good discrimination. Firstly, the proposed hash function re-scales the input image to a fixed size. Secondly, it extracts local color features by converting the RGB color image into HSI and YCbCr color spaces and calculating the block mean and variance from each component of the HSI and YCbCr representations. Finally, it takes the Euclidian distances between the block features and a reference feature as hash values. Experiments are conducted to validate the efficiency of our hash function. Receiver operating characteristics (ROC) curve comparisons with two existing algorithms demonstrate that our hash function outperforms the assessed algorithms in classification performances between perceptual robustness and discriminative capability.     

A physics-based coordinate transformation for 3-D image matching

Many image matching schemes are based on mapping coordinate locations, such as the locations of landmarks, in one image to corresponding locations in a second image. A new approach to this mapping (coordinate transformation), called the elastic body spline (EBS), is described. The spline is based on a physical model of a homogeneous, isotropic three-dimensional (3-D) elastic body. The model can approximate the way that some physical objects deform. The EBS as well as the affine transformation, the thin plate spline and the volume spline are used to match 3-D magnetic resonance images (MRI's) of the breast that are used in the diagnosis and evaluation of breast cancer. These coordinate transformations are evaluated with different types of deformations and different numbers of corresponding (paired) coordinate locations. In all but one of the cases considered, using the EBS yields more similar images than the other methods     

An improved radial basis function based method for image warping

A new image warping method is proposed in this letter, which can warp a given image by some manual defined features. Based on the radial basis interpolation function algorithm, the proposed method can transform the original optimized problem into nonsingular linear problem by adding one-order term and affine differentiable condition. This linear system can get the steady unique solution by choosing suitable kernel function. Furthermore, the proposed method demonstrates how to set up the radial basis function in the target image so as to achieve supports to adopt the backward re-sampling technology accordingly which could gain the very slippery warping image. The experimental result shows that the proposed method can implement smooth and gradual image warping with multi-anchor points‘ accurate interpolation.     

一种基于SVM的超分辨成像算法研究

为了提高逆合成孔径雷达(ISAR)成像分辨力,提出了一种基于支持向量机(SVM)的ISAR成像算法,通过适当地选择核函数的参数,可以在小观测角度的情况下,获得大观测角度图像,提高了ISAR成像的分辨力,实现了ISAR的超分辨成像.引入图像质量指数,仿真结果表明:基于SVM的超分辨方法在小转角条件下得到的目标像,具有和大转角实测数据下的目标像一样的图像质量,提出的方法可靠有效.     

基于图像配准的纸币图像识别方法

提出了基于图像配准的多光谱纸币图像识别架构,通过对纸币图像的配准来实现相似纸币识别、纸币防伪特征检测。由于纸币图像同时具有显著的结构特性和不稳定的局部特性,采用分级的变换模型对纸币图像配准：对于全局的刚性形变采用基于Harris角点特征的仿射变换算法,对于纸币图像局部非刚性形变采用基于B-样条的FFD模型的非刚性配准算法。实验表明,本模型能很好的完成纸币图像的配准,并在相似纸币识别和红外防伪特征检测方面能达到较高的精确度。     

基于免疫克隆与核匹配追踪的快速图像目标识别

为了避免核匹配追踪通过贪婪算法在基函数字典中寻找一组基函数的线性组合来逼近目标函数的计算量大的缺陷,本文利用免疫克隆选择算法全局最优和局部快速收敛的特性,加快对核匹配追踪算法每次的匹配过程进行优化,提出了一种免疫克隆核匹配追踪图像目标识别算法,该算法有效降低了核匹配追踪算法的计算量,对UCI数据集和遥感图像进行的仿真实验结果表明,相比标准核匹配追踪,该算法保持相当识别率情况下可以明显缩短一次匹配追踪的时间,尤其当字典规模较大时效果更为明显;同基于遗传算法优化相比,本文方法目标识别速度快,精度高。     

基于支持向量回归的光度配准算法

在空域内将图像之间的光度对应假设为线性的、或一些简单的非线性模型进行处理．配准后的图像仍存在较大的光度差异。将支持向量回归技术应用到光度配准中，利用支持向量回归估计图像问的光度对应关系，再根据估计得到的回归曲线对图像进行光度变换，消除图像间的光度差异，针对实际图像的对比实验表明，基于支持向量回归的光度配准算法。优于常用的空域内回归估计光度配准算法。