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。     

Benchmarking shape signatures against human perceptions of geometric similarity

Manual indexing of large databases of geometric information is both costly and difficult. Because of this, research into automated retrieval and indexing schemes has focused on the development of methods for characterising 3D shapes with a relatively small number of parameters (e.g. histograms) that allow ill-defined properties such as “geometric similarity” to be computed. However although many methods of generating these so called shape signatures have been proposed, little work on assessing how closely these measures match human perceptions of geometric similarity has been reported. This paper details the results of a trial that compared the part families identified by both human subjects and three published shape signatures.To do this a similarity matrix for the Drexel benchmark datasets was created by averaging the results of twelve manual inspections. Three different shape signatures (D2 shape distribution, spherical harmonics and surface portioning spectrum) were computed for each component in the dataset, and then used as input to a competitive neural network that sorted the objects into numbers of “similar” clusters. Comparison of human and machine generated clusters (i.e. families) of similar components allows the effectiveness of the signatures at duplicating human perceptions of shapes to be quantified.The work reported makes two contributions. Firstly the results of the human perception test suggest that the Drexel dataset contains objects whose perceived similarity levels ranged across the recorded spectrum (i.e. 0.1 to 0.9); Secondly the results obtained from benchmarking the three shape signatures against human perception demonstrate a low rate of false positives for all three signatures and a false negative rate that varied almost linearly with the amount of perceived similarity. In other words the shape signatures studied were reasonably effective at matching human perception in that they returned few wrong results and excluded parts in direct proportion to the level of similarity demanded by the user.     

Methods of spatial indexing of dynamic scenes based on regular octrees

The paper is devoted to study and development of spatial indexing methods as applied to three dimensional scenes arising in computer graphics, CAD/CAM systems, robotics, virtual and augmented reality applications, nD-modeling systems, and in project planning. Such scenes are compositions of a great number of extended geometrical objects exhibiting individual dynamic behaviors. The main focus is placed on algorithms for executing typical spatial queries with the use of regular dynamic octrees. In particular, algorithms for determining collisions, region search and nearest neighbor search are studied. For the model datasets introduced, average complexity estimates of index construction and execution of typical queries are derived based on probabilistic analysis. The estimates obtained significantly improve known pessimistic results and justify the suitability of regular octrees to spatial indexing of large-scale dynamic scenes. Results of computational experiments substantiate theoretical results and demonstrate possibilities of creating efficient computer graphics applications under the condition of permanently growing complexity of visual models.     

Emergent faces in crystal etching

The time development of emergent faces in crystal etching is investigated. We present and discuss a novel computational approach, based on an intuitive geometrical derivation, for predicting an etched shape given an initial polygonal (mask) shape and a diagram of etch rate as a function of orientation. A two-dimensional geometric model is derived which determines the etched shape as a function of time. The model is both intuitive and easy to implement manually or by computer. Because the model is intuitive in nature, some results can be obtained from only partial information. In addition, the model is a first step in the transition from analysis to design. Rather than predicting the etched shape for a given original shape, often what is desired is the original mask shape needed to produce a particular etched shape. This inversion process is carried out for some special cases. The concepts of equilibrium or eigen shapes (Eshapes), limit shapes, and time scaling are introduced. Model predictions are compared with experimental results. The extension from two dimensions to three is also introduced     

The Geometry of Visual Space: About the Incompatibility between Science and Mathematics

We address the problem of a geometrical model of vision. This problem is interesting for at least two reasons. First, any theory of vision (human or computer) must decide which geometry should be used to represent perceived objects (e.g., Euclidean vs projective). We believe that this representation should be compatible with geometrical properties of the imaging device (eye or camera). Second, the analysis of geometrical properties of vision will examine the usefulness of standard geometries and can lead to progress in mathematics itself. We analyze the geometry of image formation and show that human vision appears to involve a new branch of geometry whose properties are quite different from the properties of traditional geometries. We formulate these properties and use them to derive models of shape perception. Finally, we provide perceptual interpretations for our theoretical analyses.     

一种用区域直方图表示与描述形状的方法

众所周知，形状的表示与描述是模式识别的中心内容．然而，大多数简单类型的二维形状描述算法，无论是基于边界特性还是基于区域特性的，都有一定的应用范围或者在性能上存在某些不足．针对这样的情况，基于区域边界上当前像素与前后两个相邻像素的坐标关系，提出了一种称之为区域直方图的用于区域形状表示与描述的通用方法．该区域直方图是按照一定的分类与计算规则将区域沿边界序列化而得到的水平间距形式，它在像素意义上表示了区域的边界长度与面积．利用Rosen与Gleason推荐的标准二维形状进行了形状描述能力的定量测试以及同类型算法的对比试验，结果表明，该方法在区域形状描述方面显得很有效，能满足复杂区域形状的表示与描述要求，并且表现出较好的鲁棒性．它为区域形状的表示与描述提供了一种新的有效手段，从而在模式识别等机器视觉方面表现出一定的应用价值。     

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.     

Monocular Human Pose and Shape Reconstruction using Part Differentiable Rendering

Superior human pose and shape reconstruction from monocular images depends on removing the ambiguities caused by occlusions and shape variance. Recent works succeed in regression-based methods which estimate parametric models directly through a deep neural network supervised by 3D ground truth. However, 3D ground truth is neither in abundance nor can efficiently be obtained. In this paper, we introduce body part segmentation as critical supervision. Part segmentation not only indicates the shape of each body part but helps to infer the occlusions among parts as well. To improve the reconstruction with part segmentation, we propose a part-level differentiable renderer that enables part-based models to be supervised by part segmentation in neural networks or optimization loops. We also introduce a general parametric model engaged in the rendering pipeline as an intermediate representation between skeletons and detailed shapes, which consists of primitive geometries for better interpretability. The proposed approach combines parameter regression, body model optimization, and detailed model registration altogether. Experimental results demonstrate that the proposed method achieves balanced evaluation on pose and shape, and outperforms the state-of-the-art approaches on Human3.6M, UP-3D and LSP datasets.     

Adaptive indexing for content-based search in P2P systems

One of the major challenges in Peer-to-Peer (P2P) file sharing systems is to support content-based search. Although there have been some proposals to address this challenge, they share the same weakness of using either servers or super-peers to keep global knowledge, which is required to identify importance of terms to avoid popular terms in query processing. As a result, they are not scalable and are prone to the bottleneck problem, which is caused by the high visiting load at the global knowledge maintainers. To that end, in this paper, we propose a novel adaptive indexing approach for content-based search in P2P systems, which can identify importance of terms without keeping global knowledge. Our method is based on an adaptive indexing structure that combines a Chord ring and a balanced tree. The tree is used to aggregate and classify terms adaptively, while the Chord ring is used to index terms of nodes in the tree. Specifically, at each node of the tree, the system classifies terms as either important or unimportant. Important terms, which can distinguish the node from its neighbor nodes, are indexed in the Chord ring. On the other hand, unimportant terms, which are either popular or rare terms, are aggregated to higher level nodes. Such classification enables the system to process queries on the fly without the need for global knowledge. Besides, compared to the methods that index terms separately, term aggregation reduces the indexing cost significantly. Taking advantage of the tree structure, we also develop an efficient search algorithm to tackle the bottleneck problem near the root. Finally, our extensive experiments on both benchmark and Wikipedia datasets validated the effectiveness and efficiency of the proposed method.     

Representation and self-similarity of shapes

Representing shapes in a compact and informative form is a significant problem for vision systems that must recognize or classify objects. We describe a compact representation model for two-dimensional (2D) shapes by investigating their self-similarities and constructing their shape axis trees (SA-trees). Our approach can be formulated as a variational one (or, equivalently, as MAP estimation of a Markov random field). We start with a 2D shape, its boundary contour, and two different parameterizations for the contour (one parameterization is oriented counterclockwise and the other clockwise). To measure its self-similarity, the two parameterizations are matched to derive the best set of one-to-one point-to-point correspondences along the contour. The cost functional used in the matching may vary and is determined by the adopted self-similarity criteria, e.g., cocircularity, distance variation, parallelism, and region homogeneity. The loci of middle points of the pairing contour points yield the shape axis and they can be grouped into a unique free tree structure, the SA-tree. By implicitly encoding the (local and global) shape information into an SA-tree, a variety of vision tasks, e.g., shape recognition, comparison, and retrieval, can be performed in a more robust and efficient way via various tree-based algorithms. A dynamic programming algorithm gives the optimal solution in O(N/sup 1/), where N is the size of the contour.     

Computer vision based on a hypothesization and verification scheme by parallel relaxation

Shape recovery from a monocular image is addressed. It is often said that the information conveyed by an image is insufficient to reconstruct 3D shapes of objects in the image. This implies that shape recovery from an image necessitates the use of additional plausible constraints on typical structures and features of the objects in an ordinary scene. We propose a hypothesization and verification method for 3D shape recovery based on geometrical constraints peculiar to man-made objects. The objective is to increase the robustness of computer vision systems. One difficulty with this method lies in the mutual dependency between proper assignment of constraints to the regions in a given image and recovery of a consistent 3D shape. A concurrent mechanism has been implemented which is based on energy minimization using a parallel network for relaxation. This mechanism is capable of maintaining consistency between constraint assignment and shape recovery.     

基于两步策略的形状检索

提出一种将全局特征与局部特征相结合的形状检索的两步检索策略，首先由简单的全局特征过滤掉大部分非相关形状，并利用矢量近似方法对所属类别进行快速定位，类别内部，在对轮廓坐标进行平移、比例缩放和旋转等归一化处理的基础上，使用小波变换描述形状的局部特征，其相似性是直接用两个轮廓的小波变换系数的差来计算的，仿真试验表明，该结构能够高效准确地对高分辨遥感图像和航片中的对象进行检索。     

Multi-View Stereo Reconstruction and Scene Flow Estimation with a Global Image-Based Matching Score

We present a new variational method for multi-view stereovision and non-rigid three-dimensional motion estimation from multiple video sequences. Our method minimizes the prediction error of the shape and motion estimates. Both problems then translate into a generic image registration task. The latter is entrusted to a global measure of image similarity, chosen depending on imaging conditions and scene properties. Rather than integrating a matching measure computed independently at each surface point, our approach computes a global image-based matching score between the input images and the predicted images. The matching process fully handles projective distortion and partial occlusions. Neighborhood as well as global intensity information can be exploited to improve the robustness to appearance changes due to non-Lambertian materials and illumination changes, without any approximation of shape, motion or visibility. Moreover, our approach results in a simpler, more flexible, and more efficient implementation than in existing methods. The computation time on large datasets does not exceed thirty minutes on a standard workstation. Finally, our method is compliant with a hardware implementation with graphics processor units. Our stereovision algorithm yields very good results on a variety of datasets including specularities and translucency. We have successfully tested our motion estimation algorithm on a very challenging multi-view video sequence of a non-rigid scene. Electronic supplementary material Electronic supplementary material is available for this article at and accessible for authorised users.     

Arithmetic operations among shapes using shape numbers

In this work, a notation is given called the Discrete Geometry of Shapes, which describes the forms or shapes of flat regions limited by simply connected curves. A procedure is given that deduces from every region a unique number (its shape number) independent of translation and rotation, and optionally, of size and origin.All the integer numbers contain all the universe of discrete shapes (of course with different precision). In this universe there are shapes such as straight lines, circumferences, ellipses, parabolas, trigonometric functions, graphics of time, absorption waves, etc.The Discrete Geometry of Shapes is one-dimensional. It does not use the definition of equation and function to define shapes in a rectangular co-ordinate plane. With this notation it is possible to generate shapes with any characteristics by generating numerical sequences; also it is possible to do arithmetic operations among shapes. For example, the addition of a square and a circle, the average of a triangle and a circle, the square root of a pentagon, the numerical relations between given shapes, etc.Section V of this work describes the third dimension in the Discrete Geometry of Shapes for surfaces and volumes by means of a vector of shape numbers. It is possible to add surfaces, to divide volumes, to obtain the square root of a volume, etc.The main objective of this notation is the simplification of some mathematical and geometrical processes in this analysis of shapes and surfaces.     

Instance-based object recognition in 3D point clouds using discriminative shape primitives

3D local shapes are a critical cue for object recognition in 3D point clouds. This paper presents an instance-based 3D object recognition method via informative and discriminative shape primitives. We propose a shape primitive model that measures geometrical informativity and discriminativity of 3D local shapes of an object. Discriminative shape primitives of the object are extracted automatically by model parameter optimization. We achieve object recognition from 2.5/3D scenes via shape primitive classification and recover the 3D poses of the identified objects simultaneously. The effectiveness and the robustness of the proposed method were verified on popular instance-based 3D object recognition datasets. The experimental results show that the proposed method outperforms some existing instance-based 3D object recognition pipelines in the presence of noise, varying resolutions, clutter and occlusion.     

The lip as a biometric

In many cases human identification biometric systems are motivated by real-life criminal and forensic applications. One of the most interesting emerging method of human identification, which originates from the criminal and forensic practice, is human lips recognition. In this paper we consider lips shape and color features in order to determine human identity. We present standard and original geometrical parameters used in lips biometric system. Moreover Zernike and Hu moments as well as color features have been used. The presented results are yet not as good as these achieved in other known biometric systems. However, we believe that both lips biometrics as well as our approach and results, are worth to be presented to a wide research community.     

Embedding Gestalt laws in Markov random fields

The goal of this paper is to study a mathematical framework of 2D object shape modeling and learning for middle level vision problems, such as image segmentation and perceptual organization. For this purpose, we pursue generic shape models which characterize the most common features of 2D object shapes. In this paper, shape models are learned from observed natural shapes based on a minimax entropy learning theory. The learned shape models are Gibbs distributions defined on Markov random fields (MRFs). The neighborhood structures of these MRFs correspond to Gestalt laws-colinearity, cocircularity, proximity, parallelism, and symmetry. Thus, both contour-based and region-based features are accounted for. Stochastic Markov chain Monte Carlo (MCMC) algorithms are proposed for learning and model verification. Furthermore, this paper provides a quantitative measure for the so-called nonaccidental statistics and, thus, justifies some empirical observations of Gestalt psychology by information theory. Our experiments also demonstrate that global shape properties can arise from interactions of local features