基于容积约束Power图的图像分片逼近

给出一种在容积约束Power图结构上的图像分片多项式逼近方法.将Power图的权重与图像颜色信息相关联,设计了一种带容积约束Power图的顶点位置与权值交替优化的图像逼近算法.该算法运用误差反馈机制以及图像显著性检测等方法生成密度函数图像,并根据原始图像的颜色信息和得到的密度函数图像分两次来指导初始化点集生成,通过构建最终的Power图来逼近目标图像.利用Power图对目标图像进行区域分割,定义了度量逼近误差的带容积约束的优化能量函数,分别计算能量函数关于位置和权重的梯度,将原问题分解为两个子问题分而治之,借助密度函数图像生成的高效初始化点分布,通过不断更新Power图的顶点位置和权值得到相对较优的Power图,最终拟合出逼近图像.实验结果表明,该算法能够较好地逼近彩色图像,并有效保持了图像显著区域的特征.     

基于混合反射模型的SFS有限元方法的研究

提出了基于混合反射模型的由明暗恢复物体三维形状的有限元算法。用正方形面元逼近光滑曲面,把曲面表示为所有节点基函数的线性组合;基于既含有漫反射成分又有镜面反射成分的混合模型,结合节点基函数,将反射图线性化。考虑数字图像的特点,直接使用离散形式的SFS问题的亮度约束形式,用最小化方法得到高度满足的线性方程;使用Kaczmarz算法计算出表面三维形状。使用合成图像和实际图像验证该文算法的有效性,探讨了该算法的性能。     

从阴影恢复形状的径向基函数反射模型研究

目的 为解决传统阴影恢复形状（SFS）算法由于光源方向初始信息估计不准确,恢复的物体表面过于光滑,3维表面形状误差较大等问题,建立了基于径向基函数神经网络的反射模型,并对传统的神经网络进行了改进。方法 建立的基于径向基函数（SFS）神经网络的从阴影恢复形状反射模型代替了传统方法中采用的理想朗伯体表面反射模型。该模型利用径向基函数优秀的局部映射和函数逼近能力来处理SFS问题,通过网络训练过程中的权值代替物体所受到的初始光源信息,解决了传统算法在进行计算时,必须已知光源参数的限制。在该网络模型中添加自适应学习率算法,加速网络的收敛和训练速度。结果 针对SFS问题处理的两幅经典合成图像以及两幅实际图像进行了实验,实验结果表明,改进后的算法在3维视觉效果和3维形状信息的恢复方面都明显优于传统算法。归一化后的3维高度误差结果相比传统算法缩小了60%以上,而且同时适用合成图像和实际图像;自适应学习率的加入,使得网络的训练速度大大加快,对一幅128×128像素的图像,运算速度提升了50%。结论 本文针对SFS问题建立了基于RBF神经网络的从阴影恢复形状反射模型,利用网络模型中的参数代替SFS问题中的初始光源信息,通过最优化方法求解SFS问题。并针对传统的神经网络固定学习率造成网络收敛速度慢,容易陷入局部极小值的问题,加入了自适应学习率算法。实验结果表明,改进后的算法在处理该SFS问题时表现了优秀的性能,适用范围更广,收敛速度更快。     

基于樽海鞘群体优化非负矩阵分解的高光谱图像解混算法

针对鲁棒非负矩阵分解应用于高光谱图像处理时,存在对初始值的敏感性,求解目标函数时易陷入局部最优的缺点,提出基于樽海鞘群体优化鲁棒非负矩阵分解的高光谱图像解混算法.该算法基于鲁棒线性混合模型,在RNMF框架下,采用樽海鞘群体算法取代乘法迭代策略,以增强算法全局搜索能力,在约束空间内随机搜索满足目标函数的全局最优解,可有效地完成非线性高光谱图像解混.仿真数据与真实遥感数据实验结果表明,本文算法在处理高光谱图像时,能够有效地避免RNMF算法易陷入局部最优解的局限性,具有更好的解混性能.     

单幅植物叶片图像的3维重建

目的 植物叶片形态复杂,在虚拟场景中很难真实表现。为了从信息量有限的单幅图像中恢复植物叶片的3维形状,本文基于从明暗恢复形状（shape from shading,SFS）的方法,利用亮度统计规律和植物形态特征恢复叶片的3维形状。方法 在SFS的基础上,设计基于图像骨架的距离场偏置加强表面细节;针对SFS对恢复宏观几何形状的不足,提出根据图像亮度统计分布选取控制点控制表面宏观形状变化,并利用叶片中轴的距离场约束恢复宏观几何形状,每种方法对于表面宏观几何形状恢复的权重基于恢复的反射图和输入图像间的相似度设定;将表面细节添加到宏观几何形状上得到目标对象的3维形状。结果 选取植物叶片图像进行实验,并与其他方法进行比较,实验结果表明本文方法增强了表面细节显示,并有明显的宏观几何形状变化。同时为了验证本文方法对其他物体表面细节恢复的适用性,分别对硬币和恐龙恢复表面细节,实验结果表明提出的增强表面细节的方法同样适用于其他物体。结论 针对单幅植物叶片图像的3维重建,在SFS的基础上提出了根据骨架特征加强表面细节,根据图像亮度统计分布和叶片中轴距离场约束共同恢复表面宏观几何形状的算法,实验结果验证了本文方法的可行性。     

一种改进的双模态图像分割算法

在Mumford-Shah模型基础上提出了一个改进的双模态图像分割算法。该算法基于图像局部化信息创建驱动曲线演化的能量,引入的配准项提高了曲线的演化速度,基于曲线演化竞争的数据拟合项,使得曲线能更稳定地收敛到一个全局静态最小值,且算法对水平集函数初始化位置不敏感。实验结果表明,改进的算法具有收敛速度快、分割结果稳定的特点,尤其在医学CT图像方面具有更强的分割能力,更高的稳定性。     

基于非局部相似及加权截断核范数的高光谱图像去噪

受仪器噪声干扰,高光谱图像(Hyperspectral Image,HSI)往往会受到高斯噪声的破坏,严重影响图像后续处理的精度,因此图像去噪是一项重要的预处理工作.此外,由于高光谱数据维度极高,因此算法效率成为模型应用能力的重要指标.为实现高效H SI去噪,文中首先将高维高光谱图像投影到低维光谱子空间上,从中学习一个正交基矩阵,然后结合高光谱的空间非局部相似性与全局光谱低秩性对低维子空间进行去噪,最后将复原后的低维图像与正交基结合恢复成原始数据维度.其中,非局部去噪过程要先通过图像的非局部相似性以邻域匹配方法寻找相似张量块组成具有强低秩属性的张量群组.针对各张量群组,文章联合加权核范数与截断核范数各自的优势,提出加权截断核范数作为低秩约束正则项,能更好地逼近本质秩属性.进一步,为快速获取模型的最优解,提出改进的近端加速梯度(Accelerated Proximal Gradient,APG)算法对低秩项进行优化求解.通过两组高光谱图像和一组多光谱图像对所提算法进行实验验证,结果表明,所提方法在视觉效果和时间效率上取得了良好的平衡,综合性能明显优于其他基于非局部去噪的对比算法.     

基于神经网络的三维重建

从明暗恢复形状(shapefromshading,即SFS)是计算机视觉研究领域的一个热门话题。SFS利用图像中明暗变化与物体平面特征的对应关系来恢复物体表面特征。传统方法有估计光源方向,引入梯度光滑约束等方法,但传统的方法存在误差大,重建后物体表面过于光滑等问题,不适合表面起伏大的电镜图像的重建。本文提出以高度z连续作为约束条件,利用神经网络对单幅电镜图像进行重建的算法,并在实验中取得很好的重建效果。     

基于Phong模型的明暗恢复形状的新算法

针对传统的混合表面形状恢复算法存在较大误差的问题,提出一种透视投影下从单幅图像混合表面明暗信息恢复形状的新算法。采用Phong反射模型来描述物体表面反射特性,假设光源处于相机的光心处,建立透视投影下的图像辐照度方程。然后由辐照度方程构造包含物体深度信息的Hamilton Jacobi偏微分方程,引入局部高阶LLF通量分裂格式和五阶WENO格式逼近微分方程的粘性解,最终得到物体表面三维形状。实验结果表明,与传统算法相比,新算法的恢复高度的最大误差和平均误差均显著降低。     

从明暗恢复形状（SFS）的几类典型算法分析与评价

从明暗恢复形状（shape from shading,简称SFS）是计算机视觉中三维形状恢复问题的关键技术之一,其任务是利用单幅图象中物体表面的明暗变化来恢复其表面三维形状。为了使人们对SFC研究现状及求解SFS问题的各种算法的优缺点有个概略了解,首先介绍了求解传统SFS问题的4类方法中几个典型算法的基本原理及求解方法,并给出了实验结果,然后从算法解的唯一性、对真解的逼近程度、求解效率及适用范围等方面对这4类算法进行了比较和评价。     

Shape from intensity gradient

We propose a new shape-from-shading (SFS) algorithm which replaces the brightness constraint with an intensity gradient constraint. This is a global approach which obtains the solution by the minimization of an error function over the entire image. Through the linearization of the gradient of the reflectance map and the discretization of the surface gradient, the intensity gradient can be expressed as a linear function of the surface height. A quadratic error function, which involves the intensity gradient constraint and the traditional smoothness constraint, is minimized efficiently by solving a sparse linear system using the multigrid technique. Neither the information at singular points nor the information at occluding boundaries is needed for the initialization of the height. Results for real images are presented to show the robustness of the algorithm, and the execution time is demonstrated to prove its efficiency     

Shape from shading based on needle map and cellular automata

This paper presents a method for computing depth from a single grayscale image in two steps. Firstly, surface normals are parallelly and gradually adjusted by a procedure which includes three constraints: the smooth constraint ensures the recovered normals are smooth and integrable, the intensity gradient constraint ensures the recovered normals are consistent with the image gradient field, and the intensity constraint guarantees the recovered intensity is equal to the input image. Unlike their usage in global methods, those constraints are separately used in local area in our method. Secondly, the surface is recovered from needle map using a two-dimensional cellular automata system. An experimental assessment is provided for our methods on both real world images and synthetic images with known ground truth. The experiment results demonstrate this approach is practicable and has better precision than traditional methods.     

基于自适应标记提取的分水岭彩图分割算法

针对分水岭算法过分割问题,提出一种基于自适应提取标记的改进算法。该算法结合极小值深度和汇水盆地尺度信息提取与物体相关的极小值标记,根据梯度图像中极值点的统计信息自适应设定标记提取的阈值。提取到的标记采用形态学极小值标定技术强制作为原始梯度图像的极小值,在修改过的梯度图像上进行分水岭分割。仿真结果表明,该算法能有效解决分水岭算法的过分割问题,具有更强的抗噪性能和边缘定位能力,且计算复杂度较小。     

基于小波模极大值的混合立体匹配算法的仿真

该文提出一种新的,利用小波模极大值的基于特征和区域的混合立体匹配算法。首先详细地叙述了如何利用小波模极大值提取图像边缘,并用该点的小波模极大值和幅角作为这些边缘点的特征描述。并在图像边缘立体匹配的过程中,将以前用于图像灰度域的互相关函数应用于小波域,边缘点的视差仿真图显示,该边缘匹配算法取得了很好的效果。然后,在基于区域的匹配中,利用边缘匹配的结果,减少了匹配互相关的搜索的范围,大大减少了计算量,增加了正确率。最后,将两个视差图结合起来,就得到了最终的稠密的视差图。     

一种改进的桥梁图像分水岭分割算法

针对传统分水岭分割方法存在的过分割问题,提出了一种改进的桥梁图像分水岭分割算法。该算法首先对桥梁裂缝图像进行高低帽形态学滤波,并运用多尺度梯度算子提取梯度图像,在分水岭变换之前使用自适应的标记提取方法对区域极小值进行标定,然后对初步分水岭分割的过分割区域使用改进fisher距离的区域合并算法进行合并,取散度作为停止度量。实验表明,该算法减少了分水岭算法的过分割现象,提高了桥梁图像分割的精确性,具有很好的鲁棒性和适应性。     

Inferring surface trace and differential structure from 3-D images

Early image understanding seeks to derive analytic representations from image intensities. The authors present steps towards this goal by considering the inference of surfaces from three-dimensional images. Only smooth surfaces are considered and the focus is on the coupled problems of inferring the trace points (the points through which the surface passes) and estimating the associated differential structure given by the principal curvature and direction fields over the estimated smooth surfaces. Computation of these fields is based on determining an atlas of local charts or parameterizations at estimated surface points. Algorithm robustness and the stability of results are essential for analyzing real images; to this end, the authors present a functional minimization algorithm utilizing overlapping local charts to refine surface points and curvature estimates, and develop an implementation as an iterative constraint satisfaction procedure based on local surface smoothness properties. Examples of the recovery of local structure are presented for synthetic images degraded by noise and for clinical magnetic resonance images     

An improved image blind identification based on inconsistency in light source direction

In this study, an improved image blind identification algorithm based on inconsistency in light source direction was proposed. And a new method defined as “neighborhood method” was presented, which was used to calculate surface normal matrix of image in the blind identification algorithm. For an image, there is an error function between its actual light intensity and calculated light intensity, and for different light source models, there are different constraint functions of light. Light source direction which makes both error function and constraint function get the minimum is the one we want to seek. On this basis, according to the error function and the corresponding constraint function, search means and the Hestenes–Powell multiplier method were used in the improved algorithm to calculate the light source direction for local and infinite light source images, respectively. Further, the authenticity of image can be determined by the inconsistency in light source direction of different areas in the image. Experimental results showed that the light source direction of different areas in an image could be calculated accurately, and then the image tampering can be detected effectively by the improved algorithm. Moreover, the performance of the improved algorithm of the proposed blind identification is superior to that of the existing one in terms of detection rate and time complexity.     

Recovering facial shape using a statistical model of surface normal direction

In this paper, we show how a statistical model of facial shape can be embedded within a shape-from-shading algorithm. We describe how facial shape can be captured using a statistical model of variations in surface normal direction. To construct this model, we make use of the azimuthal equidistant projection to map the distribution of surface normals from the polar representation on a unit sphere to Cartesian points on a local tangent plane. The distribution of surface normal directions is captured using the covariance matrix for the projected point positions. The eigenvectors of the covariance matrix define the modes of shape-variation in the fields of transformed surface normals. We show how this model can be trained using surface normal data acquired from range images and how to fit the model to intensity images of faces using constraints on the surface normal direction provided by Lambert's law. We demonstrate that the combination of a global statistical constraint and local irradiance constraint yields an efficient and accurate approach to facial shape recovery and is capable of recovering fine local surface details. We assess the accuracy of the technique on a variety of images with ground truth and real-world images     

Adaptive multi-scale segmentation of surface data using unsupervised learning of seed positions

This paper presents a method for multi-scale segmentation of surface data using scale-adaptive region growing. The proposed segmentation algorithm is initiated by an unsupervised learning of optimal seed positions through the surface attribute clustering with a two-criterion score function. The seeds are selected as consecutive local maxima of the clustering map, which is computed by an aggregation of the local isotropic contrast and local variance maps. The proposed method avoids typical segmentation errors caused by an inappropriate choice of seed points and thresholds used in the region-growing algorithm. The scale-adaptive threshold estimate is based on the image local statistics in the neighborhoods of seed points. The performance of this method was evaluated on LiDAR surface images.     

Elastic shape-texture matching for human face recognition

In this paper, a novel, elastic, shape-texture matching method, namely ESTM, for human face recognition is proposed. In our approach, both the shape and the texture information are used to compare two faces without establishing any precise pixel-wise correspondence. The edge map is used to represent the shape of an image, while the texture information is characterized by both the Gabor representations and the gradient direction of each pixel. Combining these features, a shape-texture Hausdorff distance is devised to compute the similarity of two face images. The elastic matching is robust to small, local distortions of the feature points such as those caused by facial expression variations. In addition, the use of the edge map, Gabor representations and the direction of the image gradient can all alleviate the effect of illumination to a certain extent.With different databases, experimental results show that our algorithm can always achieve a better performance than other face recognition algorithms under different conditions, except when an image is under poor and uneven illumination. Experiments based on the Yale database, AR database, ORL database and YaleB database show that our proposed method can achieve recognition rates of 88.7%, 97.7%, 78.3% and 89.5%, respectively.