Class-based feature matching across unrestricted transformations

We develop a novel method for class-based feature matching across large changes in viewing conditions. The method is based on the property that when objects share a similar part, the similarity is preserved across viewing conditions. Given a feature and a training set of object images, we first identify the subset of objects that share this feature. The transformation of the feature's appearance across viewing conditions is determined mainly by properties of the feature, rather than of the object in which it is embedded. Therefore, the transformed feature will be shared by approximately the same set of objects. Based on this consistency requirement, corresponding features can be reliably identified from a set of candidate matches. Unlike previous approaches, the proposed scheme compares feature appearances only in similar viewing conditions, rather than across different viewing conditions. As a result, the scheme is not restricted to locally planar objects or affine transformations. The approach also does not require examples of correct matches. We show that by using the proposed method, a dense set of accurate correspondences can be obtained. Experimental comparisons demonstrate that matching accuracy is significantly improved over previous schemes. Finally, we show that the scheme can be successfully used for invariant object recognition.     

Aspect graph construction with noisy feature detectors

Many three-dimensional (3D) object recognition strategies use aspect graphs to represent objects in the model base. A crucial factor in the success of these object recognition strategies is the accurate construction of the aspect graph, its ease of creation, and the extent to which it can represent all views of the object for a given setup. Factors such as noise and nonadaptive thresholds may introduce errors in the feature detection process. This paper presents a characterization of errors in aspect graphs, as well as an algorithm for estimating aspect graphs, given noisy sensor data. We present extensive results of our strategies applied on a reasonably complex experimental set, and demonstrate applications to a robust 3D object recognition problem.     

Unsupervised Learning for Graph Matching

Graph matching is an essential problem in computer vision that has been successfully applied to 2D and 3D feature matching and object recognition. Despite its importance, little has been published on learning the parameters that control graph matching, even though learning has been shown to be vital for improving the matching rate. In this paper we show how to perform parameter learning in an unsupervised fashion, that is when no correct correspondences between graphs are given during training. Our experiments reveal that unsupervised learning compares favorably to the supervised case, both in terms of efficiency and quality, while avoiding the tedious manual labeling of ground truth correspondences. We verify experimentally that our learning method can improve the performance of several state-of-the art graph matching algorithms. We also show that a similar method can be successfully applied to parameter learning for graphical models and demonstrate its effectiveness empirically.     

Matching point features under small nonrigid motion

This paper describes a method for matching point features between images of objects that have undergone small nonrigid motion. Feature points are assumed to be available and, given a properly extracted set of feature points, a robust matching is established under the condition that the local nonrigid motion of each point is restricted to a circle of radius δ, where δ is not too large. This is in contrast to other techniques for point matching which assume either rigid motion or nonrigid motion of a known kind. The point matching problem is viewed in terms of weighted bipartite graph matching. In order to account for the possibility that the feature selector can be imprecise, we incorporate a greedy matching strategy with the weighted graph matching algorithm. Our algorithm is robust and insensitive to noise and missing features. The resulting matching can be used with image warping or other techniques for nonrigid motion analysis, image subtraction, etc. We present our experimental results on sequences of mammograms, images of a deformable clay object and satellite cloud images. In the first two cases we provide quantitative comparison with known ground truth.     

基于骨架层次分解的目标的图表示

基于骨架的目标表示技术是模式识别和计算机视觉的重要研究内容,近年来人们提出了许多骨架化算法,但是有关利用骨架信息表示并识别目标的研究还非常有限。Ablameyko等1996年提出了通过分解由距离标号的骨架为有意义的结构基元从而获得目标的层次结构图的方法。该图可以准确地刻画基元之间的拓扑关系,但是它对于骨架中的噪声比较敏感。主要表现为噪声基元破坏其它基元的完整性和图的稳定性。该文采用将分支编组为分支链以及构造多尺度结构图的改进策略来克服这些缺点,最终获得了目标的节点数更小、节点显著度更高、节点间连接关系更稳定的多尺度图,从而显著地提高后续利用不精确图匹配技术进行目标识别的效率。这项技术已经被应用于一个基于形状特征的图像数据库检索系统中。     

图匹配技术研究

图(Graph)在众多的科学领域和工程领域(如模式识别和计算机视觉)中具有广泛的应用 ,其具备 强大的信息表达能力。当图被用来表示物体结构时,衡量物体的相似程度将会被转化成计算两个图的相似度,这就是图匹配(Graph Matching)。近几十年来,对图匹配相关技术和算法的研究已经成为了研究领域内的一个重要课题,尤其是随着大数据时代的来临,图作为数据之间关系的一种表示形式,将会受到越来越多的关注。文中对图匹配技术的发展现状进行了综述,详细介绍了该技术的理论基础,梳理了解决图匹配问题的几种主流思路。最后,结合图匹配技术的一种具体应用对几种算法的性能进行了对比分析。     

Self-tuned Evolution-COnstructed features for general object recognition

Object recognition is a well studied but extremely challenging field. We present a novel approach to feature construction for object detection called Evolution-COnstructed Features (ECO features). Most current approaches rely on human experts to construct features for object recognition. ECO features are automatically constructed by uniquely employing a standard genetic algorithm to discover multiple series of transforms that are highly discriminative. Using ECO features provides several advantages over other object detection algorithms including: no need for a human expert to build feature sets or tune their parameters, ability to generate specialized feature sets for different objects, no limitations to certain types of image sources, and ability to find both global and local feature types. We show in our experiments that the ECO features compete well against state-of-the-art object recognition algorithms.     

人脸识别技术综述

首先对计算机人脸自动识别技术的研究背景及发展历程做了简单回顾,然后对人脸正面像的识别方法,按照识别特征的不同进行了分类综述,主要介绍了特征脸（Ｅｉｇｅｎｆａｃｅ）方法、基于小波特征的弹性匹配（Ｅｌａｓｔｉｃ Ｍａｔｃｈｉｎｇ）的方法、形状和灰度模型分离的可变形模型（Ｆｌｅｘｉｂｌ Ｍｏｄｅｌ）以及传统的部件建模等分析方法。通过对各种识别方法的分析与比较,总结了影响人脸识别技术实用化的几个因素,并提出了研究和开发成功的人脸识别技术所需要考虑的几个重要方面,进而展望了人脸识别技术今后的发展方向。     

Genetic object recognition using combinations of views

Investigates the application of genetic algorithms (GAs) for recognizing real 2D or 3D objects from 2D intensity images, assuming that the viewpoint is arbitrary. Our approach is model-based (i.e. we assume a pre-defined set of models), while our recognition strategy relies on the theory of algebraic functions of views. According to this theory, the variety of 2D views depicting an object can be expressed as a combination of a small number of 2D views of the object. This implies a simple and powerful strategy for object recognition: novel 2D views of an object (2D or 3D) can be recognized by simply matching them to combinations of known 2D views of the object. In other words, objects in a scene are recognized by "predicting" their appearance through the combination of known views of the objects. This is an important idea, which is also supported by psychophysical findings indicating that the human visual system works in a similar way. The main difficulty in implementing this idea is determining the parameters of the combination of views. This problem can be solved either in the space of feature matches among the views ("image space") or the space of parameters ("transformation space"). In general, both of these spaces are very large, making the search very time-consuming. In this paper, we propose using GAs to search these spaces efficiently. To improve the efficiency of genetic searching in the transformation space, we use singular value decomposition and interval arithmetic to restrict the genetic search to the most feasible regions of the transformation space. The effectiveness of the GA approaches is shown on a set of increasingly complex real scenes where exact and near-exact matches are found reliably and quickly     

Incremental feature selection based on rough set in dynamic incomplete data

Feature selection plays a vital role in many areas of pattern recognition and data mining. The effective computation of feature selection is important for improving the classification performance. In rough set theory, many feature selection algorithms have been proposed to process static incomplete data. However, feature values in an incomplete data set may vary dynamically in real-world applications. For such dynamic incomplete data, a classic (non-incremental) approach of feature selection is usually computationally time-consuming. To overcome this disadvantage, we propose an incremental approach for feature selection, which can accelerate the feature selection process in dynamic incomplete data. We firstly employ an incremental manner to compute the new positive region when feature values with respect to an object set vary dynamically. Based on the calculated positive region, two efficient incremental feature selection algorithms are developed respectively for single object and multiple objects with varying feature values. Then we conduct a series of experiments with 12 UCI real data sets to evaluate the efficiency and effectiveness of our proposed algorithms. The experimental results show that the proposed algorithms compare favorably with that of applying the existing non-incremental methods.     

Feature space trajectory methods for active computer vision

We advance new active object recognition algorithms that classify rigid objects and estimate their pose from intensity images. Our algorithms automatically detect if the class or pose of an object is ambiguous in a given image, reposition the sensor as needed, and incorporate data from multiple object views in determining the final object class and pose estimate. A probabilistic feature space trajectory (FST) in a global eigenspace is used to represent 3D distorted views of an object and to estimate the class and pose of an input object. Confidence measures for the class and pose estimates, derived using the probabilistic FST object representation, determine when additional observations are required as well as where the sensor should be positioned to provide the most useful information. We demonstrate the ability to use FSTs constructed from images rendered from computer-aided design models to recognize real objects in real images and present test results for a set of metal machined parts.     

Recognition of shapes by attributed skeletal graphs

In this paper, we propose a framework to address the problem of generic 2-D shape recognition. The aim is mainly on using the potential strength of skeleton of discrete objects in computer vision and pattern recognition where features of objects are needed for classification. We propose to represent the medial axis characteristic points as an attributed skeletal graph to model the shape. The information about the object shape and its topology is totally embedded in them and this allows the comparison of different objects by graph matching algorithms. The experimental results demonstrate the correctness in detecting its characteristic points and in computing a more regular and effective representation for a perceptual indexing. The matching process, based on a revised graduated assignment algorithm, has produced encouraging results, showing the potential of the developed method in a variety of computer vision and pattern recognition domains. The results demonstrate its robustness in the presence of scale, reflection and rotation transformations and prove the ability to handle noise and occlusions.     

Vision-based global localization for mobile robots with hybrid maps of objects and spatial layouts

This paper presents a novel vision-based global localization that uses hybrid maps of objects and spatial layouts. We model indoor environments with a stereo camera using the following visual cues: local invariant features for object recognition and their 3D positions for object pose estimation. We also use the depth information at the horizontal centerline of image where the optical axis passes through, which is similar to the data from a 2D laser range finder. This allows us to build our topological node that is composed of a horizontal depth map and an object location map. The horizontal depth map describes the explicit spatial layout of each local space and provides metric information to compute the spatial relationships between adjacent spaces, while the object location map contains the pose information of objects found in each local space and the visual features for object recognition. Based on this map representation, we suggest a coarse-to-fine strategy for global localization. The coarse pose is estimated by means of object recognition and SVD-based point cloud fitting, and then is refined by stochastic scan matching. Experimental results show that our approaches can be used for an effective vision-based map representation as well as for global localization methods.     

三维图匹配算法

目的 现有的图匹配算法大多应用于二维图像,对三维图像的特征点匹配存在匹配准确率低和计算速度慢等问题。为解决这些问题,本文将分解图匹配算法扩展应用在了三维图像上。方法 首先将需要匹配的两个三维图像的特征点作为图的节点集;再通过Delaunay三角剖分算法,将三维特征点相连,则相连得到的边就作为图的边集,从而建立有向图;然后,根据三维图像的特征点构建相应的三维有向图及其邻接矩阵;再根据有向图中的节点特征和边特征分别构建节点特征相似矩阵和边特征相似矩阵;最后根据这两个特征矩阵将节点匹配问题转化为求极值问题并求解。结果 实验表明,在手工选取特征点的情况下,本文算法对相同三维图像的特征点匹配有97.56%的平均准确率;对不同三维图像特征点匹配有76.39%的平均准确率;在三维图像有旋转的情况下,有90%以上的平均准确率;在特征点部分缺失的情况下,平均匹配准确率也能达到80%。在通过三维尺度不变特征变换（SIFT）算法得到特征点的情况下,本文算法对9个三维模型的特征点的平均匹配准确率为98.78%。结论 本文提出的基于图论的三维图像特征点匹配算法,经实验结果验证,可以取得较好的匹配效果。     

An algorithm for optimal free-form object matching

A novel method of matching for 3-D free-form objects (points vs. surface and surface vs. surface) is proposed. The method formulates the problem in terms of solution of a non-linear polynomial equation system, which can be solved robustly by the Interval Projected Polyhedron (IPP) algorithm. Two intrinsic surface properties, the Gaussian and the mean curvatures, are used as object features for matching. The related iso-curvature lines are used to establish the correspondence between two objects. The intersection points of these iso-curvature lines are calculated and sorted out to satisfy the Euclidean constraints from which the translation and rotation transformations are estimated. The performance of the proposed algorithm is also analyzed. This approach can cover global and partial matching, and be applied to automated inspection, copyright protection of NURBS models, and object recognition. Examples illustrate our technique.     

关系图文法及其应用

字符串文法不适于描述二维以上事物的特征，无法定义事物之间的复杂关系．本文提出了关系图的概念，对关系图的性质进行了研究．在此基础上提出了一种新的文法——关系图文法．该文法能够方便地抽象和概括二维以上复杂对象的特征，为分析和识别这些对象提供工具和方法，可以广泛应用于模式识别、高维文本分析和描述图示语言的语法等领域．为了使关系图文法实用化，本文还提出了相应的识别和匹配算法.