Rotation and intensity invariant shoeprint matching using Gabor transform with application to forensic science

Shoe marks at the place of crime provide valuable forensic evidence. This paper presents a technique for rotation and intensity invariant automatic shoeprint matching. Multiresolution features of a shoeprint have been extracted using Gabor transform. Rotation of the shoeprint image has been estimated using Radon transform and is compensated by rotating the features in opposite direction. The performance of the proposed algorithm has been compared with the technique in which the features have been determined using Fourier transform and its power spectral density. Shoeprint database has been generated by inviting participants to tread on an inkpad and then stamp on a piece of paper. Euclidian distance classifier has been used to find a suitable match. The performance of the proposed algorithm has been evaluated in terms of correct recognition rate computed using best match score at rank ‘1’ and cumulative match score for the first four matches with rotation, intensity and/or mixed attacks. A good matching performance has been achieved with rotation attack; typically 91 percent at rank ‘1’ and 100 percent at rank ‘2’ for full prints. Performance of the proposed technique is better even for partial shoeprints. Experimentation has also been carried out by perturbing shoeprint images with Gaussian white noise, salt and pepper noise to evaluate the robustness of the proposed technique.     

基于特征点匹配的改进模板匹配算法

特征点匹配是图像匹配领域中一项重要研究内容.暴力匹配中强调缺少特征匹配不是由于太少的正确匹配,而在于很难分辨真假,故加入模板匹配进行约束,提出一种改进模板匹配算法.为了提升匹配速度和精度,该算法通过提供特征点的坐标,可以计算出每个特征点的得分值,并将其用于从输入图像中提取模板.基于输入图像和另一幅图像之间的模板匹配,使...     

迭代的图变换匹配算法

目的：图像的精确匹配在图像处理与识别中起着重要的作用。为了提高图像的匹配效果,本文提出了一种迭代的图变换匹配算法来实现误匹配关系的去除从而提高图像的匹配精度。方法：该算法首先利用传统的图变换匹配(GTM)算法从初始匹配关系集合中获得较为精确的匹配关系子集,然后,利用已经获得的正确匹配点集与初始匹配点集之间的几何关系对初始匹配进行修正。最后,利用GTM对修正后的匹配关系进一步优化,从而得到更多的精确匹配关系。结果：实验结果显示在不同的图像变换场景下,相比于传统GTM算法,该算法具有较高的查全率。结论：所提算法能够克服传统GTM算法所得正确匹配关系少的缺陷。     

Matching 3-D line segments with applications to multiple-objectmotion estimation

A two-stage algorithm for matching line segments using three-dimensional data is presented. In the first stage, a tree-search based on the orientation of the line segments is applied to establish potential matches. the sign ambiguity of line segments is fixed by a simple congruency constraint. In the second stage, a Hough clustering technique based on the position of line segments is applied to verify potential matches. Any paired line segments of a match that cannot be brought to overlap by the translation determined by the clustering are removed from the match. Unlike previous methods, this algorithm combats noise more effectively, and ensures the global consistency of a match. While the original motivation for the algorithm is multiple-object motion estimation from stereo image sequences, the algorithm can also be applied to other domains, such as object recognition and object model construction from multiple views     

SAR与可见光图象匹配方法的研究

由于SAR和可见光成象传感器图象的物理特征不同,因此进行匹配难度很大。本文在深入分析了这两种传感器图象物理特征的基础上,提出了一种图象匹配的新方法。该方法运用形态学滤波方法去除SAR图象斑点噪声,利用图象的边缘特征进行匹配,并采用多分辨率分级搜索技术减少计算量,在对实验结果进行分析的基础上提出了搜索真实匹配位置的原则,大大提高了匹配的准确率。通过实验对SAR图象斑点噪声滤波和SAR与可见光图象匹配算法进行了验证,实验证明本算法的SAR图象去噪效果明显优于传统的Frost方法,图象匹配精度高,稳定性好。     

彩色图像非参数变换立体匹配研究

将非参数Rank变换引用到彩色图像的立体配算法中,采用绝对值指数方法来计算像素的颜色相似性,对彩色图像进行一种分等级的改进Rank变换,将彩色图像转变了一个整数矩阵,然后建立一种新的匹配测度,同时加入色差梯度约束进行匹配。通过对比实验,表明这种新的匹配基元进行匹配,与直接采用灰度特征作为匹配基元的算法相比,有更好的抗噪性和匹配准确性。     

基于网格对应的双约束特征点匹配算法

常用的特征点匹配算法通常设置严苛的阈值以剔除错误匹配,但这样也会导致过多的正确匹配被删除。针对这一问题,提出了一种采用双约束的特征点匹配方法。首先,在局部上统计特征点匹配数量,运用网格对应的方法过滤部分错误匹配;然后,在全局上运用RANSAC方法计算基础矩阵,通过极线约束对匹配进行再一次筛选。实验表明,相比于传统的匹配算法,该算法能在不增加算法运行时间的前提下,获得更高数量和更高质量的匹配集合。     

一种全自动稳健的图像拼接融合算法

提出了一种全自动稳健的图像拼接融合算法。此算法采用Harris角检测算子进行特征点提取，使提取的精度达到了亚像素级，然后以特征点邻域灰度互相关法进行特征点匹配得到了初步的伪匹配集合，并运用稳健的RANSAC算法将伪匹配点集合划分为内点和外点，在内点域上运用LM优化算法精确地估计出了图像间的点变换关系，最后采用颜色插值对交接处进行颜色过渡。整个算法自动完成，它对有较大误差或错误的特征点数据迭代过滤，并用提纯后的数据来做模型估计，因而对图像噪声和特征点提取不准确有强健的承受能力。在参数估计时，以特征点的坐标位置误差而不是亮度误差来构造优化函数，克服了以往算法对光照的敏感性，使算法更具有实用性。实验结果表明，该算法融合效果比较理想，鲁棒性强，具有较高的使用价值。     

Learning and feature selection in stereo matching

We present a novel stereo matching algorithm which integrates learning, feature selection, and surface reconstruction. First, a new instance based learning (IBL) algorithm is used to generate an approximation to the optimal feature set for matching. In addition, the importance of two separate kinds of knowledge, image dependent knowledge and image independent knowledge, is discussed. Second, we develop an adaptive method for refining the feature set. This adaptive method analyzes the feature error to locate areas of the image that would lead to false matches. Then these areas are used to guide the search through feature space towards maximizing the class separation distance between the correct match and the false matches. Third, we introduce a self-diagnostic method for determining when apriori knowledge is necessary for finding the correct match. If the a priori knowledge is necessary then we use a surface reconstruction model to discriminate between match possibilities. Our algorithm is comprehensively tested against fixed feature set algorithms and against a traditional pyramid algorithm. Finally, we present and discuss extensive empirical results of our algorithm based on a large set of real images     

Image clustering segmentation based on SLIC superpixel and transfer learning

Traditional fuzzy C-means clustering algorithm has poor noise immunity and clustering results in image segmentation. To overcome this problem, a novel image clustering algorithm based on SLIC superpixel and transfer learning is proposed in this paper. In the proposed algorithm, SLIC superpixel method is used to improve the edge matching degree of image segmentation and enhances the robustness to noise. Transfer learning is adopted to correct the image segmentation result and further improve the accuracy of image segmentation. In addition, the proposed algorithm improves the original SLIC superpixel algorithm and makes the edge of the superpixel more accurate. Experimental results show that the proposed algorithm can obtain better segmentation results.     

Robust multi-scale image matching for deriving ice surface velocity field from sequential satellite images

The cross-correlation-based image matching method has been widely used to derive ice surface motion information from sequential satellite images through tracking spatial displacements of surface features over time. However, this conventional method is not adequate for handling areas with a high velocity variation, in which case a large search window has to be specified in order to find the correct match points for fast-moving features. The computation involved in the cross-correlation matching with a large search window is often so intensive that only a sparse set of velocity measurements can be attempted. Furthermore, with a greater search window the cross-correlation method is prone to more spurious matches. This article presents a robust multi-scale image matching method to address the deficiencies of the conventional cross-correlation technique. The main idea is to use approximate match points obtained at a coarse resolution as a guide for searching for more precise matches at a higher resolution. A robust local statistical operator is embedded at each scale in the multi-scale matching process to eliminate match outliers. The strategy of progressively refining the match precision from coarse-resolution images to the full-resolution image allows for a small search range in pixels. Our robust multi-scale matching method significantly speeds up the computation and also reduces the occurrences of bad and spurious match points. We have implemented our method as a software tool with a graphical user interface and successfully applied it to process sequential Radarsat synthetic aperture radar images for extracting high-resolution velocity fields for Antarctic glaciers and ice shelves. This software tool will be freely available to the public through the Internet.     

基于相似三角形的SIFT错误匹配点剔除算法研究

图像匹配是图像处理应用于诸多领域的一项关键技术,基于不变特征的图像匹配是近年来图像匹配的研究热点。尺度不变特征是最有效的平移、尺度、旋转和亮度局部不变特征之一,但该算法一般会产生大量的错误匹配点。首先给出了交叉线和"一对多"类型的错误匹配点的剔除方法。然后针对一般性错误匹配点,提出了一种基于相似三角形的剔除方法,并通过实验将该算法与另外两种常用剔除算法进行了比较,证实本文提出的方法速度更快,且在剔除错误匹配点的同时保留了较多的正确匹配点。     

基于区域增长的自适应稠密匹配算法

针对目前主流方法对图像中纹理单一区域匹配效果不佳的问题,提出了一种自适应的基于区域增长的立体像对稠密匹配算法。该算法利用灰度共生矩阵,在区域增长过程中的匹配窗内计算其纹理数量,然后根据纹理数量的多少自适应调节匹配窗的大小。当匹配窗内纹理数量足够多时,该匹配窗就能够表征该匹配窗中心点的特征,因此可以减少误匹配发生的几率。实验结果证明,该算法具有良好的性能。     

一种基于距离变换的不规则区域匹配算法

针对不规则区域难以直接匹配的问题,提出了一种新颖的不规则区域匹配算法,即基于距离变换的不规则区域描述子DTIRD。为了避免椭圆拟合误差和主方向不准确产生的匹配错误,该算法采用区域边界附近纹理和区域内部纹理确定不规则区域的支撑区域;然后给出了一种基于距离变换的子区域划分方法,与传统方法相比,能够减少图像亮度变化带来的匹配错误;最后针对区域存在形状、尺寸大小不一且具有不同像素点数的问题,采用均值标准差MS构造描述算法。实验结果表明,该算法对旋转、光照、模糊以及压缩变化图像具有更好的匹配性能。     

Robust multi-view feature matching from multiple unordered views

This paper explores the problem of multi-view feature matching from an unordered set of widely separated views. A set of local invariant features is extracted independently from each view. First we propose a new view-ordering algorithm that organizes all the unordered views into clusters of related (i.e. the same scene) views by efficiently computing the view-similarity values of all view pairs by reasonably selecting part of extracted features to match. Second a robust two-view matching algorithm is developed to find initial matches, then detect the outliers and finally incrementally find more reliable feature matches under the epipolar constraint between two views from dense to sparse based on an assumption that changes of both motion and feature characteristics of one match are consistent with those of neighbors. Third we establish the reliable multi-view matches across related views by reconstructing missing matches in a neighboring triple of views and efficiently determining the states of matches between view pairs. Finally, the reliable multi-view matches thus obtained are used to automatically track all the views by using a self-calibration method. The proposed methods were tested on several sets of real images. Experimental results show that it is efficient and can track a large set of multi-view feature matches across multiple widely separated views.     

Probabilistic 3D Object Recognition

A probabilistic 3D object recognition algorithm is presented. In order to guide the recognition process the probability that match hypotheses between image features and model features are correct is computed. A model is developed which uses the probabilistic peaking effect of measured angles and ratios of lengths by tracing iso-angle and iso-ratio curves on the viewing sphere. The model also accounts for various types of uncertainty in the input such as incomplete and inexact edge detection. For each match hypothesis the pose of the object and the pose uncertainty which is due to the uncertainty in vertex position are recovered. This is used to find sets of hypotheses which reinforce each other by matching features of the same object with compatible uncertainty regions. A probabilistic expression is used to rank these hypothesis sets. The hypothesis sets with the highest rank are output. The algorithm has been fully implemented, and tested on real images.     

自适应邻域测试的图像误匹配点剔除算法

针对图像特征点暴力匹配与比率测试得到的匹配点对在数量与正确率不能兼顾的情况,提出了一种基于自适应邻域测试的误匹配点对剔除算法。对特征点进行暴力匹配与高阈值的比率测试得到初始匹配点集,对初始匹配点对中的每个匹配特征点进行自适应邻域测试,测试出初始匹配点集中明显的误匹配点对并将之剔除,达到只剔除误匹配而不会误剔除正确匹配的效果。实验结果表明,在保证正确率不降低的前提下,该算法获取的匹配点对数量比原算法多3成以上,并且该算法对图像旋转、尺度缩放具有较好通用性。     

双损失估计下强化学习型图像匹配方法

学习型特征检测器利用神经网络来检测和匹配图像特征点,其网络参数通常通过优化低层视觉的匹配准确率而训练得到,然而在高级视觉任务中,低层图像配准率的提升未必能带来更佳性能.针对该问题,提出一种双损失误差策略下的强化学习方法,一方面,将学习不变特征变换(LIFT)所得到的特征点和描述符以概率形式表示,估算出图像间的相对位姿,...     

一种改进的全视角人脸纹理图像生成方法

传统的全视角人脸纹理图像生成方法计算量大、鲁棒性差,不能很好地解决配准和接缝问题。为此,提出一种改进方法。对待拼接的人脸图像进行归一化处理,利用基于列特征向量的灰度值匹配算法实现图像的精确匹配,使用双重融合算法处理重叠区域,使图像平滑过渡。实验结果表明,该方法匹配速度较快、鲁棒性较强,能有效消除误匹配。     

A stereo vision technique using curve-segments and relaxationmatching

A multichannel feature-based stereo vision technique where curve segments are used as feature primitives in the matching process is described. The left image and the right image are filtered by using several Laplacian-of-Gaussian operators of different widths (channels). Curve segments are extracted by a tracking algorithm, and their centroids are obtained. At each channel, the generalized Hough transform of each curve segment in the left and the right image is evaluated. The epipolar constraint on the centroids of the curve segment and the channel size is used to limit the searching space in the right image. To resolve the ambiguity of the false targets (multiple matches), a relaxation technique is used where the initial scores of the node assignments are updated by the compatibility measures between the centroids of the curve segments. The node assignments with the highest score are chosen as the matching curve segments