Multimodal biometric user-identification system for network-based applications

The authors describe the design and development of a prototype of a multimodal biometric system for the automatic identification of an individual. Unlike in other proposed multimodal biometric systems, biometric features are acquired from the same image, using a low-cost scanner, at the same time. It makes the system suitable for home and for many network-based applications. After the pre-processing phase, the hand-geometry, finger and palm-print features invariant to hand translation and rotation on the scanner are extracted. Fusion at the matching-score level is obtained by means of the total similarity measure. In the decision module, three rules are used to establish identity. The system was tested on a database of 130 persons. The test performance, FAR=0% and FRR=0.2%, suggests that the system can be used in medium/high-security Internet environments.     

Finger-based personal authentication: a comparison of feature-extraction methods based on principal component analysis, most discriminant features and regularised-direct linear discriminant analysis

In this study, feature-extraction methods based on principal component analysis, most discriminant features, and regularised-direct linear discriminant analysis (RD-LDA) are tested and compared in an experimental finger-based personal authentication system. The system is multimodal and based on features extracted from eight regions of the hand: four fingerprints (the prints of the finger tips) and four digitprints (the prints of the fingers between the first and third phalanges). All of the regions are extracted from one-shot grey-level images of the palmar surface of four fingers of the right hand. The identification and verification experiments were conducted on a database consisting of 1840 finger images (184 people). The experiments showed that the best results were obtained with the RD-LDA-based feature-extraction method 2 99.98% correct identification for 920 tests and an equal error rate of 0.01% for 64170 verification tests.     

基于伪Zernike矩和Hough变换的脱机中文签名鉴别

利用伪Zernike矩和Hough变换提取了脱机中文签名图像的静态特征和动态特征,采用加权欧氏距离分类器完成签名鉴别。在690个真伪签名的较大规模样本库上进行测试,系统最高正确识别率为87.0%。利用签名图像不同特征能提供信息互补的特点,在决策层上进行了特征融合识别。系统在保持对伪样本拒绝率为71%的情况下,对真实签名的正确识别率仍可达80.4%。实验结果表明,多特征信息融合方法能较好地提高签名鉴别系统的识别性能。     

On the use of genuine-impostor statistical information for score fusion in multimodal biometrics/sur l’usage de l’information statistioue client-imposteur pour la fusion des scores en biométrie multimodale

Matching score level fusion techniques in multimodal person verification conventionally use global score statistics in the normalization and fusion stages. In this paper, novel normalization and fusion methods are presented to take advantage of the separate statistics of the monomodal scores in order to reduce the genuine and impostor pdf lobe overlapping and improve the verification rate. Joint mean normalization is an affine transformation that normalizes the mean of the monomodal biometrics scores separately for the genuine and impostor individuals. Histogram equalization is used to align the statistical distribution of the monomodal scores and make the whole separate statistics comparable. The presented weighting fusion methods have been designed to minimize the variances of the separate multimodal statistics and reduce the multimodal pdf lobe overlapping. The results obtained in speech and face scores fusion upon polycost and xm2vts databases show that the proposed techniques provide better results than the conventional methods.     

Shape-based hand recognition

The problem of person recognition and verification based on their hand images has been addressed. The system is based on the images of the right hands of the subjects, captured by a flatbed scanner in an unconstrained pose at 45 dpi. In a preprocessing stage of the algorithm, the silhouettes of hand images are registered to a fixed pose, which involves both rotation and translation of the hand and, separately, of the individual fingers. Two feature sets have been comparatively assessed, Hausdorff distance of the hand contours and independent component features of the hand silhouette images. Both the classification and the verification performances are found to be very satisfactory as it was shown that, at least for groups of about five hundred subjects, hand-based recognition is a viable secure access control scheme.     

似然得分归一化及其在与文本无关说话人确认中的应用

该文研究了似然得分归一化方法的原理,建立了基于自适应GMM模型的说话人确认系统,并将非特定人的背景模型与特定人的cohort模型相结合,提出了混合归一化的方法。在电话语音条件下,该文比较了不同得分归一化方法对确认系统性能的影响。实验表明,在自适应GMM模型似然比得分的基础上,T-cohort与通用背景模型混合归一化能获得最佳识别效果。当错误拒绝率为5%时,该方法可以获得0.5%的错误接受率,远远低于采用通用背景模型归一化方法的2%。     

Cooperative Transmissions in 5G Large-scale Relay Systems: How to Keep a Balance Between Performance and Complexity?

This paper presents a generalized i-vector representation framework with phonetic tokenization and tandem features for text independent as well as text dependent speaker verification. In the conventional i-vector framework, the tokens for calculating the zero-order and first-order Baum-Welch statistics are Gaussian Mixture Model (GMM) components trained from acoustic level MFCC features. Yet besides MFCC, we believe that phonetic information makes another direction that can benefit the system performance. Our contribution in this paper lies in integrating phonetic information into the i-vector representation by several extensions, forming a more generalized i-vector framework. First, the tokens for calculating the zero-order statistics is extended from the MFCC trained GMM components to phonetic phonemes, trigrams and tandem feature trained GMM components, using phoneme posterior probabilities. Second, given the zero-order statistics (posterior probabilities on tokens), the feature used to calculate the first-order statistics is also extended from MFCC to tandem feature, and is not necessarily the same feature employed by the tokenizer. Third, the zero-order and first-order statistics vectors are then concatenated and represented by the simplified supervised i-vector approach followed by the standard Probabilistic Linear Discriminant Analysis (PLDA) back-end. We study different token and feature combinations, and we show that the feature level fusion of acoustic level MFCC features and phonetic level tandem features with GMM based i-vector representation achieves the best performance for text independent speaker verification. Furthermore, we demonstrate that the phonetic level phoneme constraints introduced by the tandem features help the text dependent speaker verification system to reject wrong password trials and improve the performance dramatically. Experimental results are reported on the NIST SRE 2010 common condition 5 female part task and the RSR 2015 part 1 female part task for text independent and text dependent speaker verification, respectively. For the text independent speaker verification task, the proposed generalized i-vector representation outperforms the i-vector baseline by relatively 53 % in terms of equal error rate (EER) and norm minDCF values. For the text dependent speaker verification task, our proposed approach also reduced the EER significantly from 23 % to 90 % relatively for different types of trials.     

Verification system robust to occlusion using low-order Zernike moments of palmprint sub-images

This paper proposes a palmprint based verification system which uses low-order Zernike moments of palmprint sub-images. Euclidean distance is used to match the Zernike moments of corresponding sub-images of query and enrolled palmprints. These matching scores of sub-images are fused using a weighted fusion strategy. The proposed system can also classify the sub-image of palmprint into non-occluded or occluded region and verify user with the help of non-occluded regions. So it is robust to occlusion. The palmprint is extracted from the acquired hand image using a low cost flat bed scanner. A palmprint extraction procedure which is robust to hand translation and rotation on the scanner has been proposed. The system is tested on IITK, PolyU and CASIA databases of size 549, 5239 and 7752 hand images respectively. It performs with accuracy of more than 98%, and FAR, FRR less than 2% for all the databases.     

基于二代curvelet与wavelet变换的自适应图像融合

针对同一场景红外图像与可见光图像的融合问题,提出了一种基于二代curvelet与wavelet变换的自适应图像融合算法。首先对源图像进行快速离散curvelet变换,得到不同尺度与方向下的粗尺度系数和细尺度系数;根据红外图像与可见光图像的不同物理特性以及人类视觉系统特性,对不同尺度与方向下的粗尺度系数和细尺度系数采用基于离散小波变换的图像融合方法,在小波域中,对低频系数采用基于红外图像与可见光图像的不同物理特性的自适应融合规则,对高频系数采用基于邻域方向对比度与局部区域匹配度相结合的自适应融合规则,然后进行小波逆变换得到融合的curvelet系数;最后,进行快速离散curvelet逆变换得到融合图像。实验结果表明,该方法能够更加有效、准确地提取图像中的特征,是一种有效可行的图像融合算法。     

Framework for Content‐Based Image Identification with Standardized Multiview Features

Information identification with image data by means of low‐level visual features has evolved as a challenging research domain. Conventional text‐based mapping of image data has been gradually replaced by content‐based techniques of image identification. Feature extraction from image content plays a crucial role in facilitating content‐based detection processes. In this paper, the authors have proposed four different techniques for multiview feature extraction from images. The efficiency of extracted feature vectors for content‐based image classification and retrieval is evaluated by means of fusion‐based and data standardization–based techniques. It is observed that the latter surpasses the former. The proposed methods outclass state‐of‐the‐art techniques for content‐based image identification and show an average increase in precision of 17.71% and 22.78% for classification and retrieval, respectively. Three public datasets — Wang; Oliva and Torralba (OT‐Scene); and Corel — are used for verification purposes. The research findings are statistically validated by conducting a paired t‐test.     

Target dependent score normalization techniques and their application to signature verification

Score normalization methods in biometric verification, which encompass the more traditional user-dependent decision thresholding techniques, are reviewed from a test hypotheses point of view. These are classified into test dependent and target dependent methods. The focus of the paper is on target dependent score normalization techniques, which are further classified into impostor-centric, target-centric, and target-impostor methods. These are applied to an on-line signature verification system on signature data from the First International Signature Verification Competition (SVC 2004). In particular, a target-centric technique based on the cross-validation procedure provides the best relative performance improvement testing both with skilled (19%) and random forgeries (53%) as compared to the raw verification performance without score normalization (7.14% and 1.06% Equal Error Rate for skilled and random forgeries, respectively).     

文本无关说话人确认中的一种新的评分规整方法

对于采用统一阈值的,基于高斯混合模型(GMM)的文本无关说话人确认系统,由于不同的话者模型的输出评分分布的不同,会影响到系统的确认性能,为此,需对输出评分进行规整。本文提出了一种新的评分规整方法-整体规整。整体规整同时考虑了不同测试语音和不同话者模型的差异,并在评分域做出调整,使得所有语音的输出评分具有相似的分布,从而使系统整体分类能力得以保证。在NIST’03电话语音库上进行的实验表明,采用了整体规整后的系统性能和传统的评分规整方法比较,有了明显提高。     

Score bi-Gaussian equalisation for multimodal person verification

Multimodal biometric fusion at score level can be performed by means of combinatory or classificatory techniques. In the first case, it is straightforward that the normalisation of the scores is a very important issue for the success of the fusion process. In the classificatory approach as, for instance, in support vector machine (SVM)- based systems, only simple normalisation methods are usually applied. In this work, histogram equalisation of biometric score distribution is successfully applied in a multimodal person verification system composed by prosodic, speech spectrum and face information. Furthermore, a new bi-Gaussian equalisation (BGEQ) is introduced, which takes into account the separate statistics of the genuine and impostor scores by using as a reference a sum of two Gaussian functions, whose standard deviations model the overlap between the genuine and impostor lobes of the original distributions. Multimodal verification experiments are shown, where prosodic and speech spectrum scores are provided by speech experts using the Switchboard-I database, and face scores are obtained by a face recognition expert using XM2VTS database. BGEQ in combination with an SVM fusion system with a polynomial kernel has obtained the best results and has outperformed in more than a 21.29% the results obtained by min?max normalisation.     

Face anti-spoofing based on multi-modal and multi-scale features fusion

Face anti-spoofing is used to assist face recognition system to judge whether the detected face is real face or fake face. In the traditional face anti-spoofing methods, features extracted by hand are used to describe the difference between living face and fraudulent face. But these handmade features do not apply to different variations in an unconstrained environment. The convolutional neural network (CNN) for face deceptions achieves considerable results. However, most existing neural network-based methods simply use neural networks to extract single-scale features from single-modal data, while ignoring multi-scale and multi-modal information. To address this problem, a novel face anti-spoofing method based on multi-modal and multi-scale features fusion ( MMFF) is proposed. Specifically, first residual network ( Resnet )-34 is adopted to extract features of different scales from each modality, then these features of different scales are fused by feature pyramid network (FPN), finally squeeze-and-excitation fusion ( SEF) module and self-attention network ( SAN) are combined to fuse features from different modalities for classification. Experiments on the CASIA-SURF dataset show that the new method based on MMFF achieves better performance compared with most existing methods.     

Personal Authentication Using Hand Vein Triangulation and Knuckle Shape

This paper presents a new approach to authenticate individuals using triangulation of hand vein images and simultaneous extraction of knuckle shape information. The proposed method is fully automated and employs palm dorsal hand vein images acquired from the low-cost, near infrared, contactless imaging. The knuckle tips are used as key points for the image normalization and extraction of region of interest. The matching scores are generated in two parallel stages: (i) hierarchical matching score from the four topologies of triangulation in the binarized vein structures and (ii) from the geometrical features consisting of knuckle point perimeter distances in the acquired images. The weighted score level combination from these two matching scores are used to authenticate the individuals. The achieved experimental results from the proposed system using contactless palm dorsal-hand vein images are promising (equal error rate of 1.14%) and suggest more user friendly alternative for user identification.      

基于特征不变矩的签名鉴别方案

脱机手写签名鉴别的主要困难在于有效特征的提取,因此本文主要围绕提取能反映签名本质的特征进行了相关研究。在具体解决签名鉴别时,一方面要考虑签名的静态特征,另一方面寻找动态特征。重点研究了静态特征。提取静态特征时,利用伪Zernike矩的尺度及位移不变性,计算签名图像的0~10阶伪Zernike矩来组成特征向量。在此基础上,对基于上述两种不同特征的加权欧氏距离分类器进行性能比较,并找到了一个有效的数据融合方案。     

微光图像与激光助视图像的对比度调制融合

图像融合可以对同一景物不同频谱或其他不同物理效应产生的图像进行处理，改善图像质量。把微光图像作为重要的夜视图像具有对比度小、视觉效果模糊的特点。在双谱图像触合理论的基础上，针对光阴极的光谱响应曲线特点，运用瞬态激光助视的方法，获得了景物在近红外波段的图像。因为近红外激光助视图像与微光图像响应的光谱波段不同，所以两类图像有各自的信息特征。将两种图像用基于小波变换的对比度调制的算法进行触合处理，得到了效果较好的融合图像。该技术对提高投光电视系统的视距与目标识别能力具有重要意义。