Representation plurality and fusion for 3-D face recognition

In this paper, we present an extensive study of 3-D face recognition algorithms and examine the benefits of various score-, rank-, and decision-level fusion rules. We investigate face recognizers from two perspectives: the data representation techniques used and the feature extraction algorithms that match best each representation type. We also consider novel applications of various feature extraction techniques such as discrete Fourier transform, discrete cosine transform, nonnegative matrix factorization, and principal curvature directions to the shape modality. We discuss and compare various classifier combination methods such as fixed rules voting- and rank-based fusion schemes. We also present a dynamic confidence estimation algorithm to boost fusion performance. In identification experiments performed on FRGC v1.0 and FRGC v2.0 face databases, we tried to find the answers to the following questions: 1) the relative importance of the face representation technique vis-à-vis the types of features extracted; 2) the impact of the gallery size; 3) the conditions, under which subspace methods are preferable, and the compression factor; 4) the most advantageous fusion level and fusion methods; 5) the role confidence votes in improving fusion and the style of selecting experts in the fusion; and 6) the consistency of the conclusions across different databases.     

3-D face recognition for unattended access control

Biometric data have been integrated in all new European passports, since the Member States of the European Union started to implement the EU Council Regulation No 2252/2004 on standards for security features and biometrics in passports. The additional integration of three-dimensional models promises significant performance enhancements for border controls. By combining the geometry-and texture-channel information of the face, 3-D face recognition systems provide an improved robustness while processing variations in poses and problematic lighting conditions when taking the photo.     

Evidence-based recognition of 3-D objects

An evidence-based recognition technique is defined that identifies 3-D objects by looking for their notable features. This technique makes use of an evidence rule base, which is a set of salient or evidence conditions with corresponding evidence weights for various objects in the database. A measure of similarity between the set of observed features and the set of evidence conditions for a given object in the database is used to determine the identity of an object in the scene or reject the object(s) in the scene as unknown. This procedure has polynomial time complexity and correctly identifies a variety of objects in both synthetic and real range images. A technique for automatically deriving the evidence rule base from training views of objects is shown to generate evidence conditions that successfully identify new views of those objects     

3-D multiview object representations for model-based object recognition

3-D multiview object representations are presented as an alternative approach to traditional 3-D volumetric object representations. 3-D multiview models store features in a viewer-centered representation and thus can be immediately used to match features derived from 2-D images. Algorithms are presented that construct, search and perform region growing on 3-D multiview object models.     

Rectification and recognition of text in 3-D scenes

Real-world text on street signs, nameplates, etc. often lies in an oblique plane and hence cannot be recognized by traditional OCR systems due to perspective distortion. Furthermore, such text often comprises only one or two lines, preventing the use of existing perspective rectification methods that were primarily designed for images of document pages. We propose an approach that reliably rectifies and subsequently recognizes individual lines of text. Our system, which includes novel algorithms for extraction of text from real-world scenery, perspective rectification, and binarization, has been rigorously tested on still imagery as well as on MPEG-2 video clips in real time.Received: 15 December 2003, Published online: 14 December 2004Gregory K. Myers: Correspondence to     

一种融合PCA 和KFDA 的人脸识别方法

提出一种融合PCA和KFDA的人脸识别方法，即在进行非线性映射之前，首先利用经典的主分量分析(C—PCA)进行降维，然后执行KFDA．为进一步降低整个算法的计算时问，又提出一种I—PCA KFDA方法，它直接基于图像矩阵的主分量分析(I—PCA)．ORL标准人脸库的试验结果表明，与现有的核Fisher鉴别分析方法相比，两种方法可将特征抽取的速度分别提高3倍和7倍，其识别精度没有丝毫的降低．     

Human posture recognition with a time-of-flight 3D sensor for in-home applications

A non-invasive system for human posture recognition suitable to be used in several in-home scenarios is proposed and validation results presented. 3D point cloud sequences were acquired by using a time-of-flight sensor in a privacy preserving modality and near real-time processed with a low power embedded PC. To satisfy different application requirements in terms of discrimination capabilities, covered distance range and processing speed, a twofold discrimination approach was investigated in which features were hierarchical arranged from coarse to fine exploiting both topological and volumetric spatial representations. The topological representation encoded the intrinsic topology of the body’s shape in a skeleton-based structure, guarantying invariance to scale, rotations and postural changes, and achieving a high level of detail with a moderate computational cost. In the volumetric representation, on the other hand, postures were described in terms of 3D cylindrical histograms working within a wider range of distances in a faster way and also guarantying good invariance properties. The discrimination capabilities of the approach were evaluated in four different real-home scenarios especially related with ambient assisted living and homecare fields, namely dangerous event detection, anomalous behavior detection, activities recognition, natural human-ambient interaction, and also in terms of invariance to viewpoint changes, representation capabilities and classification performance, achieving promising results. The two approaches exhibited complementary characteristics showing high reliability with classification rates greater than 97% in four application scenarios for which the posture recognition is a fundamental function.     

Recursive 3-D road and relative ego-state recognition

The general problem of recognizing both horizontal and vertical road curvature parameters while driving along the road has been solved recursively. A differential geometry representation decoupled for the two curvature components has been selected. Based on the planar solution of E.D. Dickmanns and A. Zapp (1986) and its refinements, a simple spatio-temporal model of the driving process makes it possible to take both spatial and temporal constraints into account effectively. The estimation process determines nine road and vehicle state parameters recursively at 25 Hz (40 ms) using four Intel 80286 and one 386 microprocessors. Results with the test vehicle (VaMoRs), which is a 5-ton van, are given for a hilly country road     

FEG structures for representation and recognition of 3-D polyhedral objects

The paper proposes a fast O(n ^2.5) recognition algorithm for partially occluded 3D polyhedral objects, where n is the number of the polyhedron vertices.Our approach is based on the generate and test mechanism using the alignment approach as its basic recognition tool. The first stage is to align one face of the unknown polyhedron with one face of one library model (generate). The second stage is a recursive test procedure that checks the matching of the remaining faces. A new structure called FEG—Face Edge Graph is introduced. This structure stores information about the 2D coordinates of each face and the identity of its adjacent faces.A very low complexity is achieved by using a divide and conquer strategy. Instead of trying to recognize the whole object at once, we divide it and conquer (recognize) it face by face. This is done by reducing the recognition problem to generalized subgraph matching problem in which two subgraphs are equal not only when they are isomorphic, but also when they represent the same part of the same object. A special mechanism handles false splitting and false merging of adjacent faces as a result of wrong segmentation.The process lends itself to hierarchical parallel processing in that the matching with each library model may be carried out independently, and also for each model—processing at the pixel level may also be done in parallel.We evaluated our approach with several real range data images as well as some synthetic objects. Four of these cases are reported here.     

3-D face recognition method based on optimum 3-D image measurement technology

Most face recognition systems employ 2-D color or gray-scale images. However, face recognition based on 2-D images is adversely affected by 3-D movement, variable lighting, and the use of cosmetics. 3-D image measurement technology has the potential to overcome these limitations of face recognition based on 2-D images since it can perform geometric analysis. We propose a method that is capable of recognizing a person from a 3-D facial image obtained using a 3-D shape measurement system by employing a technique that optimizes the intensity-modulation pattern projection. This face recognition method is based on the iterative closest point algorithm. It is robust to changes in reflectivity and color. Since the 3-D facial information can be registered, this method can estimate rotations and translations to compensate for different positions or directions. In order to prove the validity of the proposed technique, a verification experiment was conducted which used 105 sample 3-D images obtained from 15 subjects. It achieved a detection rate of 96% when heads were turned at an angle of 20° or less relative to the camera.     

Evaluation of a hypothesizer for silhouette-based 3-D object recognition

Shape retrieval and shape-based object recognition are closely related problems; however, they have different task contexts, performance criteria, and database characteristics. In previous work, we proposed a method for similarity-based 2-D shape retrieval using scale-space part decompositions, part-frequency distributions, and structural indexing. In this paper, we evaluate the use of that shape retrieval method as the hypothesis generation component of silhouette-based 3-D object recognition systems, using a performance criterion and test database appropriate for the new application.     

Discriminative common vectors for face recognition

In face recognition tasks, the dimension of the sample space is typically larger than the number of the samples in the training set. As a consequence, the within-class scatter matrix is singular and the linear discriminant analysis (LDA) method cannot be applied directly. This problem is known as the "small sample size" problem. In this paper, we propose a new face recognition method called the discriminative common vector method based on a variation of Fisher's linear discriminant analysis for the small sample size case. Two different algorithms are given to extract the discriminative common vectors representing each person in the training set of the face database. One algorithm uses the within-class scatter matrix of the samples in the training set while the other uses the subspace methods and the Gram-Schmidt orthogonalization procedure to obtain the discriminative common vectors. Then, the discriminative common vectors are used for classification of new faces. The proposed method yields an optimal solution for maximizing the modified Fisher's linear discriminant criterion given in the paper. Our test results show that the discriminative common vector method is superior to other methods in terms of recognition accuracy, efficiency, and numerical stability.     

基于PCA技术的神经网络说话人识别研究

针对当提取以整段语音的多维语音特征参数为BP 神经网络输入而带来的说话人识别率和网络训练稳定性的问题,提出了一种用于BP 网络的基于主分量分析的PCA新方法。将该方法得到的降维语音特征参数用于BP 网络中,其识别率和训练速度都得到较大提高,使得基于BP 神经网络的说话人识别得到更好效果。     

一种局部加权的二维主成分分析算法及其在人脸识别中的应用

提出了一种将局部特征加权与二维主成分分析相结合的局部加权的二维主成分分析方法．引入了二维局部加权特征子空间的概念，将各类样本映射到这个局部加权特征子空间，再通过计算测试样本到加权子空间的距离进行样本的分类．使用这种方法在ORL人脸库上进行测试，结果表明，经过局部特征加权的二维主成分分析方法比普通的二维主成分分析方法具有更优的性能，并且在提高识别率的同时算法的复杂程度并没有明显增加．     

基于图像识别的建筑物三维重建

为从彩色高分辨率的图像中提取出主要建筑物的位置信息并进行三维重建,提出一种结合2D和3-D信息识别建筑物,通过纹理集技术进行大规模3-D重建的方法.进行边缘检测,提取可用的短直线以及相应的2-D特征,对这些短直线进行逐级聚类得到候选屋顶集合;通过朴素贝叶斯分类器在候选屋顶集合中区分出不同的3D屋顶特征,以识别全局优秀的屋顶;根据屋顶的位置信息,在大规模的3-D场景中绘制出相应尺寸的模型,通过动态分配算法将建筑物纹理合并,减少纹理数量,从而减少纹理状态的切换.以航拍和卫星遥感彩色高分辨率图像进行实验,实验结果表明,该方法有优秀的识别正确率和3-D重建效果.     

A linguistic approach to 3-D object recognition

The principles of a 3-D object recognition system for combined intensity-image and depth-map understanding are discussed. The goal of such system is to be an inversion of image synthesis performed by 3-D computer graphics. A linguistic model for two system elements, the knowledge base and recognition strategy, being an extension of pattern recognition approaches, is outlined. It consists of a powerful object specification language and a simultaneous syntactic-semantic analysis in this language. The syntax is based on a node-controlled parallel structure grammar. Particular attention is paid to elements shared in common by several parts and to hidden line/surface problems. Both are embedded into the grammars derivation. The semantics is well-defined due to the attribution of the grammar.     

Adaptive 3-D object recognition from multiple views

The authors address the problem of generating representations of 3-D objects automatically from exploratory view sequences of unoccluded objects. In building the models, processed frames of a video sequence are clustered into view categories called aspects, which represent characteristic views of an object invariant to its apparent position, size, 2-D orientation, and limited foreshortening deformation. The aspects as well as the aspect transitions of a view sequence are used to build (and refine) the 3-D object representations online in the form of aspect-transition matrices. Recognition emerges as the hypothesis that has accumulated the maximum evidence at each moment. The `winning' object continues to refine its representation until either the camera is redirected or another hypothesis accumulates greater evidence. This work concentrates on 3-D appearance modeling and succeeds under favorable viewing conditions by using simplified processes to segment objects from the scene and derive the spatial agreement of object features