An experimental study of one- and two-level classifier fusion for different sample sizes

Due to the wide variety of fusion techniques available for combining multiple classifiers into a more accurate classifier, a number of good studies have been devoted to determining in what situations some fusion methods should be preferred over other ones. However, the sample size behavior of the various fusion methods has hitherto received little attention in the literature of multiple classifier systems. The main contribution of this paper is thus to investigate the effect of training sample size on their relative performance and to gain more insight into the conditions for the superiority of some combination rules.A large experiment is conducted to study the performance of some fixed and trainable combination rules for executing one- and two-level classifier fusion for different training sample sizes. The experimental results yield the following conclusions: when implementing one-level fusion to combine homogeneous or heterogeneous base classifiers, fixed rules outperform trainable ones in nearly all cases, with only one exception of merging heterogeneous classifiers for large sample size. Moreover, the best classification for any considered sample size is generally achieved by a second level of combination (namely, utilizing one fusion rule to further combine a set of ensemble classifiers with each of them constructed by fusing base classifiers). Under these circumstances, it seems that adopting different types of fusion rules (fixed or trainable) as the combiners for two levels of fusion is appropriate.     

Personal identity verification by serial fusion of fingerprint and face matchers

The use of personal identity verification systems with multi-modal biometrics has been proposed in order to increase the performance and robustness against environmental variations and fraudulent attacks. Usually multi-modal fusion of biometrics is performed in parallel at the score-level by combining the individual matching scores. This parallel strategy exhibits some drawbacks: (i) all available biometrics are necessary to perform fusion, thus the verification time depends on the slowest system; (ii) some users could be easily recognizable using a certain biometric instead of another one and (iii) the system invasiveness increases. A system characterized by the serial combination of multiple biometrics can be a good trade-off between verification time, performance and acceptability. However, these systems have been poorly investigated, and no support for designing the processing chain has been given so far. In this paper, we propose a novel serial scheme and a simple mathematical model able to predict the performance of two serially combined matchers as function of the selected processing chain. Our model helps the designer in finding the processing chain allowing a trade-off, in particular, between performance and matching time. Experiments carried out on well-known benchmark data sets made up of face and fingerprint images support the usefulness of the proposed methodology and compare it with standard parallel fusion.     

Evolutionary algorithm-based face verification

This paper proposes a novel face verification method using principal components analysis (PCA) and evolutionary algorithm (EA). Although PCA related algorithms have shown outstanding performance, the problem lies in making decision rules or distance measures. To solve this problem, quantum-inspired evolutionary algorithm (QEA) is employed to find out the optimal weight factors in the distance measure for a predetermined threshold value which distinguishes between face images and non-face images. Experimental results show the effectiveness of the proposed method through the improved verification rate and false alarm rate.     

Particle swarm optimization based fusion of near infrared and visible images for improved face verification

This paper presents two novel image fusion schemes for combining visible and near infrared face images (NIR), aiming at improving the verification performance. Sub-band decomposition is first performed on the visible and NIR images separately. In both cases, we further employ particle swarm optimization (PSO) to find an optimal strategy for performing fusion of the visible and NIR sub-band coefficients. In the first scheme, PSO is used to calculate the optimum weights of a weighted linear combination of the coefficients. In the second scheme, PSO is used to select an optimal subset of features from visible and near infrared face images. To evaluate and compare the efficacy of the proposed schemes, we have performed extensive verification experiments on the IRVI database. This database was acquired in our laboratory using a new sensor that is capable of acquiring visible and near infrared face images simultaneously thereby avoiding the need for image calibration. The experiments show the strong superiority of our first scheme compared to NIR and score fusion performance, which already showed a good stability to illumination variations.     

Classifier combination based on confidence transformation

This paper investigates the effects of confidence transformation in combining multiple classifiers using various combination rules. The combination methods were tested in handwritten digit recognition by combining varying classifier sets. The classifier outputs are transformed to confidence measures by combining three scaling functions (global normalization, Gaussian density modeling, and logistic regression) and three confidence types (linear, sigmoid, and evidence). The combination rules include fixed rules (sum-rule, product-rule, median-rule, etc.) and trained rules (linear discriminants and weighted combination with various parameter estimation techniques). The experimental results justify that confidence transformation benefits the combination performance of either fixed rules or trained rules. Trained rules mostly outperform fixed rules, especially when the classifier set contains weak classifiers. Among the trained rules, the support vector machine with linear kernel (linear SVM) performs best while the weighted combination with optimized weights performs comparably well. I have also attempted the joint optimization of confidence parameters and combination weights but its performance was inferior to that of cascaded confidence transformation-combination. This justifies that the cascaded strategy is a right way of multiple classifier combination.     

Designing a smart-card-based face verification system: empirical investigation

To design a smart card face verification system many key factors have to be considered. In this study we discuss the implementation of such a system and investigate the trade-off between performance and computational complexity. Two optimisation strategies are considered. The studies are performed on the XM2VTS, BANCA and FERET databases demonstrating that the judicial choice of spatial and grey level resolution as well as JPEG compression settings for face representation can optimise verification error. We show that the use of a fixed precision data type does not affect system performance very much but can speed up the verification process. Since the optimisation framework of such a system is very complicated, the search space is simplified by applying some heuristics to the problem. In the adopted suboptimal search strategy one or two parameters are optimised at a time. The system was evaluated using half total error rate (HTER) as the performance criterion. The conclusions reached on different databases indicate that the selection of the optimum parameters may call for different optimum operating points.

A Viewpoint Invariant,Sparsely Registered,Patch Based,Face Verifier

Sparsely registering a face (i.e., locating 2–3 fiducial points) is considered a much easier task than densely registering one; especially with varying viewpoints. Unfortunately, the converse tends to be true for the task of viewpoint-invariant face verification; the more registration points one has the better the performance. In this paper we present a novel approach to viewpoint invariant face verification which we refer to as the “patch-whole” algorithm. The algorithm is able to obtain good verification performance with sparsely registered faces. Good performance is achieved by not assuming any alignment between gallery and probe view faces, but instead trying to learn the joint likelihood functions for faces of similar and dissimilar identities. Generalization is encouraged by factorizing the joint gallery and probe appearance likelihood, for each class, into an ensemble of “patch-whole” likelihoods. We make an additional contribution in this paper by reviewing existing approaches to viewpoint-invariant face verification and demonstrating how most of them fall into one of two categories; namely viewpoint-generative or viewpoint-discriminative. This categorization is instructive as it enables us to compare our “patch-whole” algorithm to other paradigms in viewpoint-invariant face verification and also gives deeper insights into why the algorithm performs so well.     

Fusion of appearance-based face recognition algorithms

Although many algorithms have been proposed, face recognition and verification systems can guarantee a good level of performances only for controlled environments. In order to improve the performance and robustness of face recognition and verification systems, multi-modal and mono-modal systems based on the fusion of multiple recognisers using different or similar biometrics have been proposed, especially for verification purposes. In this paper, a recognition and verification system based on the combination of two well-known appearance-based representations of the face, namely, principal component analysis (PCA) and linear discriminant analysis (LDA), is proposed. Both PCA and LDA are used as feature extractors from frontal view images. The benefits of such a fusion are shown for different environmental conditions, namely, ideal conditions, characterised by a very limited variability of environmental parameters, and real conditions with a large variability of lighting, scale and facial expression.     

基于Adaboost算法的人脸检测

该文提出了一种基于改进的Adaboost算法的人脸检测方法.Adaboost是一种构建准确分类器的学习算法,它将一族弱学习算法通过一定规则结合成为一个强学习算法,从而通过样本训练得到一个识别准确率理想的分类器.但是,Adaboost在有高噪音样本的情况下,有可能发生过配现象,该文在Adaboost算法的基础上,对其权值更新规则做了改进,并结合PCA进行人脸检测.仿真试验表明,该方法具有良好的性能,同时可以在一定程度上有效防止过配现象的发生.     

一种基于个人身份认证的正面人脸识别算法

利用小波分解提取人脸特征技术和支持向量机 (SVM)分类模型 ,提出了一种基于个人身份认证的正面人脸识别算法 (或称为人脸认证方法 ) .针对 M个用户的人脸认证算法包括二个阶段 :(1)训练阶段 :使用小波分解方法对脸像训练集中的人脸图象进行特征提取 ,并用所提取的人脸特征向量训练 M个 SVM(对应 M个用户 ) ;(2 )认证阶段 :先由待认证者所声称的用户身份 (姓名或密码等 )确定对应的一训练好的 SVM,然后用这一 SVM对小波分解方法提取的待认证人的脸像特征向量进行分类 ,分类结果将显示待认证人所声称的身份是否真实 .利用 ORL人脸图象库对该算法的实验测试结果 ,以及与径向基函数神经网络作为分类器时的实验结果比较表明了该算法性能的优越性     

Structurally noise resistant classifier for multi-modal person verification

In this letter we propose a piece-wise linear (PL) classifier for use as the decision stage in a two-modal verification system, comprised of a face and a speech expert. The classifier utilizes a fixed decision boundary that has been specifically designed to account for the effects of noisy audio conditions. Experimental results on the VidTIMIT database show that in clean conditions, the proposed classifier is outperformed by a traditional weighted summation decision stage (using both fixed and adaptive weights). Using white Gaussian noise to corrupt the audio data resulted in the PL classifier obtaining better performance than the fixed approach and similar performance to the adaptive approach. Using a more realistic noise type, namely “operations room” noise from the NOISEX-92 corpus, resulted in the PL classifier obtaining better performance than both the fixed and adaptive approaches. The better results in this case stem from the PL classifier not making a direct assumption about the type of noise that causes the mismatch between training and testing conditions (unlike the adaptive approach). Moreover, the PL classifier has the advantage of having a fixed (non-adaptive, thus simpler) structure.     

XYZ／SE程序的验证

ＸＹＺ／Ｅ的好处之一在于高级和低级的说明能够在同一框架下表示，因而使得软件的说明和实现变得容易一些．在这同时，开发验证工具以验证不同层次的说明是否满足所期望的关系是很重要的．谢洪亮等同志曾研究过ＸＹＺ／ＳＥ程序的验证规则．本篇文章增加了有关使用数组、过程说明和过程调用的规则．同时着重说明ＸＹＺ／ＳＥ程序验证的自动化方面的问题，且实现了一些化简验证条件的规则．     

融合LeNet-5和Siamese神经网络模型的人脸认证算法研究

基于人脸信息的身份认证对于个人安全和社会稳定都具有非常重要的意义。传统的人脸认证方法依赖人工构造视觉特征,易受外界条件影响,识别精度不高。深度学习模型以自主学习方式进行特征提取,能从复杂的数据中提取到人脸的隐性特征。然而大部分深度学习人脸认证方法需大量带有身份标记的训练样本,额外增加了标记数据的成本。针对以上问题,提出了融合LeNet-5和Siamese神经网络模型的人脸认证算法。该算法在Siamese神经网络框架基础上,引入LeNet-5卷积神经网络,将单分支LeNet-5卷积网络扩充为结构相同且参数共享的双分支LeNet-5卷积网络,通过缩小卷积核、增加卷积层来调整网络结构,使用Contrastive Loss函数对融合网络进行训练。实验结果表明,该算法在不同的人脸数据集上,均获取较高的识别精度。     

基于曲波变换和余弦测度的人脸识别方法

人脸识别是一种常用的生物特征识别技术,广泛应用于门禁考勤、公安司法等领域。光照、人脸表情与姿态、遮挡等采集条件的变化对 现有人脸识别方法 影响较大,限制了其应用。提出了一种基于曲波变换和余弦测度的人脸识别方法,以提高人脸识别对采集条件的鲁棒性。首先,对待识别人脸图像进行曲波变换,依据曲波系数检测人脸区域的关键点;然后,提取各关键点在不同尺度和方向上的曲波特征,构建人脸特征描述子;最后,依据余弦测度、累加和运算和极值运算求取人脸的最优匹配结果。仿真实验表明,所提方法对光照、姿态、表情和遮挡等变化的鲁棒性强,且识别性能好。     

一种弹性的软件过程模型验证工具

过程模型验证是保证软件过程定义正确性的重要手段.针对目前过程模型验证中的一些问题,首先提出了一种以活动为中心的软件过程元模型,并以XML对其进行描述.在此基础上,从行为、资源、组织视图结合的角度,提出了保证软件过程模型正确性的语义约束规则.最后,提出了一种弹性的用于验证XML描述的过程模型的机制,并基于此实现了过程模型验证工具,来验证过程模型的正确性.     

多距离分类器组合试验在人脸识别中的应用

先通过PCA特征脸或插值降维,并利用Fisher鉴别矢量集,获得人脸鉴别特征;然后采用常见距离分类器及其组合形式进行识别分析,分类器组合使用多数投票规则和最大值规则等;最后对计算结果进行分析。该文研究思路和方法简洁,结果令人满意,对基于生物特征鉴别分析的工程应用具有较大价值。     

Face recognition approach based on rank correlation of Gabor-filtered images

Face recognition is challenging because variations can be introduced to the pattern of a face by varying pose, lighting, scale, and expression. A new face recognition approach using rank correlation of Gabor-filtered images is presented. Using this technique, Gabor filters of different sizes and orientations are applied on images before using rank correlation for matching the face representation. The representation used for each face is computed from the Gabor-filtered images and the original image. Although training requires a fairly substantial length of time, the computation time required for recognition is very short. Recognition rates ranging between 83.5% and 96% are obtained using the AT&T (formerly ORL) database using different permutations of 5 and 9 training images per subject. In addition, the effect of pose variation on the recognition system is systematically determined using images from the UMIST database.     

证件照片的一种混合人脸识别方法

在仔细分析证件照片中人脸特点的基础上，提出了一种把人脸的几何特征矢量匹配和人脸的分块加权匹配相结合的思想。该方法针对一般人脸识别方法不能有效消除人脸表情影响的特点，首先对人脸进行快速准确的眼睛定位、图像控正以及标准化处理，然后一方面抽取能够避免人脸表情影响的几何特征向量，另一方面对标准人脸进行分块加权匹配，最后进行综合识别。对JAFFE人脸库的试验结果表明，该方法识别准确率高，能够有效地消除人脸表情在识别中的影响，结果令人满意。