Image registration and object recognition using affine invariantsand convex hulls

This paper is concerned with the problem of feature point registration and scene recognition from images under weak perspective transformations which are well approximated by affine transformations and under possible occlusion and/or appearance of new objects. It presents a set of local absolute affine invariants derived from the convex hull of scattered feature points (e.g., fiducial or marking points, corner points, inflection points, etc.) extracted from the image. The affine invariants are constructed from the areas of the triangles formed by connecting three vertices among a set of four consecutive vertices (quadruplets) of the convex hull, and hence do make direct use of the area invariance property associated with the affine transformation. Because they are locally constructed, they are very well suited to handle the occlusion and/or appearance of new objects. These invariants are used to establish the correspondences between the convex hull vertices of a test image with a reference image in order to undo the affine transformation between them. A point matching approach for recognition follows this. The time complexity for registering L feature points on the test image with N feature points of the reference image is of order O(NxL). The method has been tested on real indoor and outdoor images and performs well.     

基于仿射不变的分段可变形模型的图像分割

提出了一种用于图像分割的分段可变形模型，并在模型的能量函数中引入了仿射不变量信息．将模型轮廊进行层次化的分段变形能够保持标记点移动的相关性，改进的内外部能量函数定义减少了计算量，试验表明与传统方法相比，本模型运算速度快，抗噪声和避免陷入局部极小值的能力较强，对医学图像的分割有较好的效果。     

Automatic matching of homologous histological sections

The role of neuroanatomical atlases is undergoing a significant redefinition as digital atlases become available. These have the potential to serve as more than passive guides and to hold the role of directing segmentation and multimodal fusion of experimental data. Key elements needed to support these new tasks are registration algorithms. For images derived from histological procedures, the need is for techniques to map the two-dimensional (2-D) images of the sectional material into the reference atlas which may be a full three-dimensional (3-D) data set or one consisting of a series of 2-D images. A variety of 2-D-2-D registration methods are available to align experimental images with the atlas once the corresponding plane of section through the atlas has been identified. Methods to automate the identification of the homologous plane, however, have not been previously reported. Here, the authors use the external section contour to drive the identification and registration procedure. For this purpose, the authors model the contours by B-splines because of their attractive properties the most important of which are: (1) smoothness and continuity; (2) local controllability which implies that local changes in shape are confined to the B-spline parameters local to that change; (3) shape invariance under affine transformation, which means that the affine transformed curve is still a B-spline whose control points are related to the object control points through the transformation. The authors present a fast algorithm for estimating the control points of the B-spline which is robust to nonuniform sampling, noise, and local deformations. Curve matching is achieved by using a similarity measure that depends directly on the parameters of the B-spline. Performance tests are reported using histological material from rat brains     

Atlas-based indexing of brain sections via 2-D to 3-D image registration

A 2-D to 3-D nonlinear intensity-based registration method is proposed in which the alignment of histological brain sections with a volumetric brain atlas is performed. First, sparsely cut brain sections were linearly matched with an oblique slice automatically extracted from the atlas. Second, a planar-to-curved surface alignment was employed in order to match each section with its corresponding image overlaid on a curved-surface within the atlas. For the latter, a PDE-based registration technique was developed that is driven by a local normalized-mutual-information similarity measure. We demonstrate the method and evaluate its performance with simulated and real data experiments. An atlas-guided segmentation of mouse brains' hippocampal complex, retrieved from the Mouse Brain Library (MBL) database, is demonstrated with the proposed algorithm.     

Elastic 3-D alignment of rat brain histological images

A three-dimensional wavelet-based algorithm for nonlinear registration of an elastic body model of the brain is developed. Surfaces of external and internal anatomic brain structures are used to guide alignment. The deformation field is represented with a multiresolution wavelet expansion and is modeled by the partial differential equations of linear elasticity. A progressive estimation of the registration parameters and the usage of an adaptive distance map reduce algorithm complexity, thereby providing computational flexibility that allows mapping of large, high resolution datasets. The performance of the algorithm was evaluated on rat brains. The wavelet-based registration method yielded a twofold improvement over affine registration.     

Automatic segmentation of thalamus from brain MRI integrating fuzzy clustering and dynamic contours

Thalamus is an important neuro-anatomic structure in the brain. In this paper, an automated method is presented to segment thalamus from magnetic resonance images (MRI). The method is based on a discrete dynamic contour model that consists of vertices and edges connecting adjacent vertices. The model starts from an initial contour and deforms by external and internal forces. Internal forces are calculated from local geometry of the model and external forces are estimated from desired image features such as edges. However, thalamus has low contrast and discontinues edges on MRI, making external force estimation a challenge. The problem is solved using a new algorithm based on fuzzy C-means (FCM) unsupervised clustering, Prewitt edge-finding filter, and morphological operators. In addition, manual definition of the initial contour for the model makes the final segmentation operator-dependent. To eliminate this dependency, new methods are developed for generating the initial contour automatically. The proposed approaches are evaluated and validated by comparing automatic and radiologist's segmentation results and illustrating their agreement.     

Affine invariance contour descriptor based on iso-area normalisation

In pattern recognition, by observing a contour extracted from a shape, the position of the points of this contour can be normalised by using a set of triangles with the same area whose vertices consist of the centroid of the contour and a pair of successive points on the contour. Contour characterisation can be obtained by lowpass filtering and observing the resulting changes in the areas of the triangles. It is proved that, for a filtered contour, the areas of the triangles are linear under affine transforms. The experimental results show that the approach is resistant to affine transformations and noise     

基于两尺度自卷积的直方图仿射不变量提取方法

提出了一种新的两尺度自卷积直方图仿射不变量。以图像二维坐标线性变换生成新图像为基点,建立两尺度自卷积变换,进而把新图像度密度函数值转化成直方图区间划分,由此推导出新的直方图仿射不变量。另外,重点分析了新不变量的参数选择范围,并详述了其计算步骤。利用经典的“fish”和“coil-100”测试数据库,对比性能优的多尺度自卷积归一化直方图仿射不变量,从时间效率、抗图像变形、抗视角变化等方面,全面验证了所提新仿射不变量的有效性。     

一种应用于图像配准中的点特征匹配算法

点特征匹配在机器视觉、图像配准等领域中有着重要的应用.针对空间存在较大仿射几何差异的图像中的点特征匹配问题,提出了一种利用马氏距离仿射不变性进行约束的松弛匹配算法,并将该算法应用于遥感图像配准中.实验结果表明,算法可以很好的完成点特征匹配,匹配点对数量充足且具备很高的正确率,从而可以保证图像配准的精度.     

Improvement on dynamic elastic interpolation technique for reconstructing 3-D objects from serial cross sections [biomedical application

An improved method for automatically reconstructing a three-dimensional object from serial cross sections is presented. The method improves the dynamic elastic contour interpolation technique. There are two major improvements: (1) in the case of branching that involves concave contours, instead of pairwise interpolation between the start contour and each goal contour, the goal image is considered globally and local constraints are imposed on the forces exerting upon the vertices; and (2) it takes the continuity of high-order derivatives into consideration and incorporates the schemes of spline theory, quadratic-variation-based surface interpolation, and finite-element-based multilevel surface interpolation to create smoother surfaces of the reconstructed object. Based on the output from the preliminary processing, two alternatives, a quadratic-variation-based surface interpolation algorithm and a finite-element-based multilevel surface interpolation algorithm, can be adopted to obtain the final surface representation     

用神经元网络识别仿射变换下的飞机模型

本文推广了付立叶描绘矛的方法,产生了一组在任意仿射变换下都不改变的不变量,用这些不变量来训练一个三层网感知器对飞机模型进行识别和分类.在本文中我们引进了一个加速算法可以大大减少学习时间.最后,给出了用这个神经网分类器进行识别和分类的结果及其抗噪声性能.     

Reconstruction of 3-D head geometry from digitized point sets: an evaluation study

In this paper, we evaluate different methods to estimate patient-specific scalp, skull, and brain surfaces from a set of digitized points from the target's scalp surface. The reconstruction problem is treated as a registration problem: An a priori surface model, consisting of the scalp, skull, and brain surfaces, is registered to the digitized surface points. The surface model is generated from segmented magnetic resonance (MR) volume images. We study both affine and free-form deformation (FFD) registration, the use of average models, the averaging of individual registration results, a model selection procedure, and statistical deformation models. The registration algorithms are mainly previously published, and the objective of this paper is to evaluate these methods in this particular application with sparse data. The main interest of this paper is to generate geometric head models for biomedical applications, such as electroencephalography and magnetoencephalographic. However, the methods can also be applied to other anatomical regions and to other application areas. The methods were validated using 15 MR volume images, from which the scalp, skull, and brain were manually segmented. The best results were achieved by averaging the results of the FFD registrations of the database: the mean distance from the manually segmented target surface to a deformed a priori model surface for the studied anatomical objects was 1.68-2.08 mm, depending on the point set used. The results support the use of the evaluated methods for the reconstruction of geometric models in applications with sparse data.     

基于局部仿射配准的鲁棒非刚体配准算法

针对传统点集非刚体配准算法对复杂局部形变数据配准精度低,收敛速度慢等问题,该文提出一种基于局部仿射配准的鲁棒非刚体配准算法。该算法采用分层迭代的方式由粗到精地完成点集的非刚体配准。在每层迭代中,首先对子形状点集集合和子目标点集集合进行分块处理并更新分块后每一类子点集的形状控制点。然后利用控制点引导仿射迭代最近点(ICP)算法求解对应子点集间的局部仿射变换。接着利用上一步求解的局部仿射变换,更新子形状点集集合及其形状控制点集合。直到配准误差收敛时,循环结束并输出更新后的形状点集。实验结果表明,所提算法与传统点集非刚体算法相比具有更强的精确性和收敛性。     

Affine-permutation invariance of 2-D shapes.

Shapes provide a rich set of clues on the identity and topological properties of an object. In many imaging environments, however, the same object appears to have different shapes due to distortions such as translation, rotation, reflection, scaling, or skewing. Further, the order by which the object's feature points are scanned changes, i.e., the order of the pixels may be permuted. Relating two-dimensional shapes of the same object distorted by different affine and permutation transformations is a challenge. We introduce a shape invariant that we refer to as the intrinsic shape of an object and describe an algorithm, BLAISER, to recover it. The intrinsic shape is invariant to affine-permutation distortions. It is a uniquely defined representative of the equivalence class of all affine-permutation distortions of the same object. BLAISER computes the intrinsic shape from any arbitrarily affine-permutation distorted image of the object, without prior knowledge regarding the distortions or the undistorted shape of the object. The critical step of BLAISER is the determination of the shape orientation and we provide a detailed discussion on this topic. The operations of BLAISER are based on low-order moments of the input shape and, thus, robust to error and noise. Examples illustrate the performance of the algorithm.     

基于红外图像特征与K-means的边缘检测

为解决红外图像边缘模糊导致边缘提取困难的问题,提出一种基于边缘特征与K-means结合的红外图像边缘检测方法。首先将人眼视觉特性与红外图像边缘点处的灰度分布特点结合,构造出反映其结构特征的数据集;再利用K-means将数据集分为边缘点和非边缘点,提取出图像边缘;最后利用二步法将边缘进行细化,以便实现红外图像边缘检测。实验结果表明:该方法能够通过自适应阈值提取出红外图像的完整外部轮廓,并保留内部边缘信息,对弱边缘起到良好的提取效果,并有效抑制噪声干扰。     

一种仿射不变的直线描述子与直线匹配

从图像中提取的直线常出现不完整、端点位置不准确等问题,针对这些问题造成的直线匹配难点,本文提出了一种仿射不变的直线描述子.首先将待匹配直线离散为对应点的集合,将直线描述转化为点的描述,避免了直线不完整造成的支撑区域大小不一致的问题;然后结合直线的方向和长度,定义点描述子的主方向和尺度,通过统计离散点集的局部邻域的梯度信息使描述子具有仿射不变性.为了提高直线匹配速度,在进行直线描述之前,本文采用了极线约束精简了待匹配直线集合,再利用最近邻距离比准则对直线精确匹配.实验结果表明本文提出的直线描述子在仿射、亮度、视点、遮挡等变化条件下具有精确的匹配性能.     

结合图像局部信息和Hausdorff距离的活动轮廓模型医学图像分割算法

本文提出了一种新的基于距离局部信息的活动轮廓摸型。该模型的能量函数将区域可扩展能量项(region scalable fitting, RSF)和Hausdorff距离项结合,其中RSF项在目标边缘附近起主导作用,用来吸引水平集函数曲线到达目标边界;而Hausdorff距离由于包含了局部区域的相似信息,可以提高分割方法的稳定性。在保证分割精度的情况下,相对于区域可伸缩拟合及局部巴氏距离的活动轮廓模型RSFB方法,本文方法具有更快的收敛速度和更好的参数选择鲁棒性,对于解决图像分割中的边界模糊和噪声问题效果显著。实验结果显示本文提出的方法在超声图像和不均匀图像的分割中都有非常好的效果,且计算量较小。      

Computation of the mid-sagittal plane in 3-D brain images

We present a new method to automatically compute, reorient, and recenter the mid-sagittal plane in anatomical and functional three-dimensional (3-D) brain images. This iterative approach is composed of two steps. At first, given an initial guess of the mid-sagittal plane (generally, the central plane of the image grid), the computation of local similarity measures between the two sides of the head allows to identify homologous anatomical structures or functional areas, by way of a block matching procedure. The output is a set of point-to-point correspondences: the centers of homologous blocks. Subsequently, we define the mid-sagittal plane as the one best superposing the points on one side and their counterparts on the other side by reflective symmetry. Practically, the computation of the parameters characterizing the plane is performed by a least trimmed squares estimation. Then, the estimated plane is aligned with the center of the image grid, and the whole process is iterated until convergence. The robust estimation technique we use allows normal or abnormal asymmetrical structures or areas to be treated as outliers, and the plane to be mainly computed from the underlying gross symmetry of the brain. The algorithm is fast and accurate, even for strongly tilted heads, and even in presence of high acquisition noise and bias field, as shown on a large set of synthetic data. The algorithm has also been visually evaluated on a large set of real magnetic resonance (MR) images. We present a few results on isotropic as well as anisotropic anatomical (MR and computed tomography) and functional (single photon emission computed tomography and positron emission tomography) real images, for normal and pathological subjects.