Exploring biometric identification in FinTech applications based on the modified TAM

In recent years,biometric technologies have been widely embedded in mobile devices;these technologies were originally employed to enhance the security of mobile devices.With the rise of financial technology(FinTech),which uses mobile devices and applications as promotional platforms,biometrics has the important role of strengthening the identification of such applications for security.However,users still have privacy and trust concerns about biometrics.Previous studies have demonstrated that the technology acceptance model(TAM)can rigorously explain and predict user acceptance of new technologies.This study therefore modifies the TAM as a basic research architecture.Based on a literature review,we add two new variables,namely,“perceived privacy”and“perceived trust,”to extend the traditional TAM to examine user acceptance of biometric identification in FinTech applications.First,we apply the analytic hierarchy process(AHP)to evaluate the defined objects and relevant criteria of the research framework.Second,we use the AHP results in the scenario analysis to explore biometric identification methods that correspond to objects and criteria.The results indicate that face and voice recognition are the two most preferred identification methods in FinTech applications.In addition,there are significant changes in the results of the perceived trust and perceived privacy dominant scenarios.

Optical Ciphering Scheme for Cancellable Speaker Identification System

Most current security and authentication systems are based on personal biometrics.The security problem is a major issue in the field of biometric systems.This is due to the use in databases of the original biometrics.Then biometrics will forever be lost if these databases are attacked.Protecting privacy is the most important goal of cancelable biometrics.In order to protect privacy,therefore,cancelable biometrics should be non-invertible in such a way that no information can be inverted from the cancelable biometric templates stored in personal identification/verification databases.One methodology to achieve non-invertibility is the employment of non-invertible transforms.This work suggests an encryption process for cancellable speaker identification using a hybrid encryption system.This system includes the 3D Jigsaw transforms and Fractional Fourier Transform(FrFT).The proposed scheme is compared with the optical Double Random Phase Encoding(DRPE)encryption process.The evaluation of simulation results of cancellable biometrics shows that the algorithm proposed is secure,authoritative,and feasible.The encryption and cancelability effects are good and reveal good performance.Also,it introduces recommended security and robustness levels for its utilization for achieving efficient cancellable biometrics systems.

Using Head Patch Pattern as a Reliable Biometric Character for Noninvasive Individual Recognition of an Endangered Pitviper Protobothrops mangshanensis

Mangshan pitviper, Protobothrops mangshanensis （formerly Zhaoermia mangshanensis） is endemic to China. Unfortunately, due to the decreasing size of its wild populations, this snake has been listed as critically endangered. Re- search carried out on the Mangshan pitviper＇s population ecology and captive reproduction has revealed that the unique head patch patterns of different individuals may potentially be used as a noninvasive recognition biometric character. We collected head patch pattern images of 40 individuals of P. mangshanensis between 1994 and 2011. By comparing each pitviper＇s head patch pattern, we found that the head patch pattern of individual snakes was different and unique. Additionally, we observed and recorded the head patch pattern characters of four adults and five juveniles before and af- ter ecdysis. Our findings confirmed that head patch patterns of Mangshan pitvipers are unique and stable, remaining un- changed after ecdysis. Thus, individuals can be quickly identified by examining the head patch pattern within a specific recognition area on the head. This method may be useful for noninvasive individual recognition in many other species that display color patch pattern variations, especially in studies of endangered species where the use of invasive marking techniques is undesirable.

Dynamic Audio-Visual Biometric Fusion for Person Recognition

Biometric recognition refers to the process of recognizing a person’s identity using physiological or behavioral modalities,such as face,voice,fingerprint,gait,etc.Such biometric modalities are mostly used in recognition tasks separately as in unimodal systems,or jointly with two or more as in multimodal systems.However,multimodal systems can usually enhance the recognition performance over unimodal systems by integrating the biometric data of multiple modalities at different fusion levels.Despite this enhancement,in real-life applications some factors degrade multimodal systems’performance,such as occlusion,face poses,and noise in voice data.In this paper,we propose two algorithms that effectively apply dynamic fusion at feature level based on the data quality of multimodal biometrics.The proposed algorithms attempt to minimize the negative influence of confusing and low-quality features by either exclusion or weight reduction to achieve better recognition performance.The proposed dynamic fusion was achieved using face and voice biometrics,where face features were extracted using principal component analysis(PCA),and Gabor filters separately,whilst voice features were extracted using Mel-Frequency Cepstral Coefficients(MFCCs).Here,the facial data quality assessment of face images is mainly based on the existence of occlusion,whereas the assessment of voice data quality is substantially based on the calculation of signal to noise ratio(SNR)as per the existence of noise.To evaluate the performance of the proposed algorithms,several experiments were conducted using two combinations of three different databases,AR database,and the extended Yale Face Database B for face images,in addition to VOiCES database for voice data.The obtained results show that both proposed dynamic fusion algorithms attain improved performance and offer more advantages in identification and verification over not only the standard unimodal algorithms but also the multimodal algorithms using standard fusion methods.

Biometrics:Standing Throughout Emerging Technologies

Biometrics technologies have been around for quite some time and many have been deployed for different applications all around the world, ranging from small companies' time and attendance systems to access control systems for nuclear facilities. Biometrics offer a reliable solution for the establishment of the distinctiveness of identity based on 'who an individual is', rather than what he or she knows or carries. Biometric Systems automatically verify a person's identity based on his/her anatomical and behavioral characteristics. Biometric traits represent a strong and undeviating link between a person and his/her identity, these traits cannot be easily lost or forgotten or faked, since biometric systems require the user to be present at the time of authentication. Some biometric systems are more reliable than others, yet they are neither secure nor accurate, all biometrics have their strengths and weaknesses. Although some of these systems have shown reliability and solidarity, work still has to be done to improve the quality of service they provide. Presented is the available standing biometric systems showing their strengths and weaknesses and also emerging technologies which may have great benefits for security applications in the near future.

Orientation Field Code Hashing:A Novel Method for Fast Palmprint Identification

For a large-scale palmprint identification system,it is necessary to speed up the identification process to reduce the response time and also to have a high rate of identification accuracy.In this paper,we propose a novel hashing-based technique called orientation field code hashing for fast palmprint identification.By investigating hashing-based algorithms,we first propose a double-orientation encoding method to eliminate the instability of orientation codes and make the orientation codes more reasonable.Secondly,we propose a window-based feature measurement for rapid searching of the target.We explore the influence of parameters related to hashing-based palmprint identification.We have carried out a number of experiments on the Hong Kong Poly U large-scale database and the CASIA palmprint database plus a synthetic database.The results show that on the Hong Kong Poly U large-scale database,the proposed method is about 1.5 times faster than the state-of-the-art ones,while achieves the comparable identification accuracy.On the CASIA database plus the synthetic database,the proposed method also achieves a better performance on identification speed.

Identification of Fusarium Species Associated with Onion(Allium cepa L.)Plants in Field in Burkina Faso

Many fungi limit onion production in Burkina Faso. This study aims to identify the main Fusarium species associated with onion plant in field in order to determine those involved in seedling damping-off and bulb rot, and develop adequate management strategies of these diseases. For this purpose, 36 isolates of Fusarium were isolated from onion plants in 17 sites and subjected to molecular analysis and biometric characterization. The results revealed that the isolates belong to five Fusarium species: Fusarium oxysporum (44.44% of the isolates), Fusarium proliferatum (41.66%), Fusarium solani (5.55%), Fusarium fujikuroi (5.55%) and Fusarium thapsinum (2.77%). Fusarium oxysporum, F. proliferatum, F. solani and F. fujikuroi had faster mycelial development, with a growth rate of 7.72 - 8.27 mm/d, than F. thapsinum (6.52 mm/d). Conidia of F. oxysporum, F. proliferatum and F. solani were longer (4.74 - 5.96 μm) than those of F. fujikuroi and F. thapsinum (3.20 - 4.04 μm). Fusarium solani and F. oxysporum, respectively, had the largest and most partitioned conidia.

基于PCA-LSR双约束的多光谱掌脉图像识别方法

为实现高安全性、用户接受度好的生物特征识别系统,设计了一种开放环境下基于多光谱的掌脉图像采集设备,并研究了一种基于主成分分析(Principal Component Analysis,PCA)和最小二乘回归(Least Squares Regression,LSR)双约束的掌脉识别算法。算法在最小二乘回归投影的过程中对主成分提取的主元信息进行约束,共同驱动数据,削弱了光散射对识别性能的不良影响,解决了非接触式图像采集造成的类内间距增大的问题。在中科院自动化所、同济大学、香港理工大学以及自建的掌脉图库上进行了实验,算法最低等误率分别为0.72%、0.50%、0.18%和0.03%,正确识别率分别为99.80%、99.77%、99.90%、99.95%。相比其他典型方法具有优势,系统具有实用价值。

基于多模态生物特征识别的高校门禁系统设计与实现

为解决传统门禁系统对实体校园卡的过度依赖、数据应用能力差、无法形成精细化管理等问题,在已有门禁系统架构基础上,基于一卡通专网,采用分布式架构设计了一种基于多模态生物特征识别的高校智慧门禁系统。该系统集采集管理、生物数据库、算法服务、校门口出入管理、访客出入管理、公寓管理、设备管理和出入权限管理等功能于一体,实现了校园出入口的智慧化管理,提升了校园安全管理效率,为下一步的智慧校园建设奠定了应用基础。

基于注意力网络的长时牦牛个体识别研究

为推动精准畜牧业的发展及探讨长时间跨度下的动物个体识别,构建间隔6个月和12个月的同一批牦牛个体图像数据集。试验采用引入注意力机制的PCB+SE-ResNet50识别模型,实现短时和长时牦牛个体识别,从而分析影响长时牦牛个体识别的因素,并在该长时数据集上与ViT和PGCFL模型识别结果进行比较。结果表明:该模型在间隔6个月和12个月的数据集上识别平均精度均值达到60.37%、41.56%。相较于ViT,分别提高1.64%、5.82%;相较于PGCFL,分别提高12.40%、11.22%。该研究可为长时牦牛个体识别、养殖信息化及牲畜精准管理等提供理论依据和方法指导。

联合局部多尺度和全局上下文特征的步态识别

现有步态识别方法在空间上能提取丰富的步态信息,但是在时间上通常忽略局部区域内的细粒度时间特征和不同子区域间的时间上下文信息。考虑到步态识别为细粒度识别问题同时每个人行走的时间上下文信息具有独特性,提出一种联合局部多尺度和全局上下文时间特征的步态识别方法。将整个步态序列按多个时间分辨率划分并提取局部子序列内的多分辨率细粒度时间特征。在子序列之间基于Transformer提取时间上下文信息,并基于上下文信息融合所有子序列形成全局特征。在2个公开数据集上进行大量的实验,在CASIA-B数据集的3种行走状态下取得98.0%、95.4%和87.0%的rank-1准确率,在OU-MVLP数据集上取得90.7%的rank-1准确率。本文提出的方法得到的结果可为其他步态识别方法提供参考。

人脸识别系统在学生管理工作中的应用

通过人脸识别系统,学校能够实时监控校园内的学生活动,及时发现异常情况,提高安全管理水平。同时,也可以将人脸识别系统用于课堂考勤管理,自动记录学生的出勤情况,有效防止逃课和代签等问题。在宿舍管理方面,人脸识别系统能够核实学生归寝情况,提高夜间巡查的效率。人脸识别技术能够在学生管理工作中发挥重要作用。

生物识别系统中的对抗攻击研究综述

生物识别系统是当下一个备受关注的研究方向,其安全性也得到了公众的广泛关注。基于深度学习的生物识别系统容易受到对抗攻击,添加对抗扰动的图像会让深度学习模型做出错误的输出预测,从而破坏生物识别系统的安全性,达到非法攻击的目的。文章对针对生物识别系统的对抗攻击进行了调查,并研究了对抗攻击防御方法及对抗攻击在隐私保护方面的应用。最后,本文讨论了未来生物识别系统中的对抗攻击的发展方向,为未来的对抗攻击方式提供了可实现的解决方案。

Contact-free and pose-invariant hand-biometric-based personal identification system using RGB and depth data

Hand-biometric-based personal identification is considered to be an effective method for automatic recognition. However, existing systems require strict constraints during data acquisition, such as costly devices,specified postures, simple background, and stable illumination. In this paper, a contactless personal identification system is proposed based on matching hand geometry features and color features. An inexpensive Kinect sensor is used to acquire depth and color images of the hand. During image acquisition, no pegs or surfaces are used to constrain hand position or posture. We segment the hand from the background through depth images through a process which is insensitive to illumination and background. Then finger orientations and landmark points, like finger tips or finger valleys, are obtained by geodesic hand contour analysis. Geometric features are extracted from depth images and palmprint features from intensity images. In previous systems, hand features like finger length and width are normalized, which results in the loss of the original geometric features. In our system, we transform 2D image points into real world coordinates, so that the geometric features remain invariant to distance and perspective effects. Extensive experiments demonstrate that the proposed hand-biometric-based personal identification system is effective and robust in various practical situations.

Gram Matrix-Based Convolutional Neural Network for Biometric Identification Using Photoplethysmography Signal

As a kind of physical signals that could be easily acquired in daily life,photoplethysmography(PPG)signal becomes a promising solution to biometric identification for daily access management system(AMS).State-of-the-art PPG-based identification systems are susceptible to the form of motions and physical conditions of the subjects.In this work,to exploit the advantage of deep learning,we developed an improved deep convolutional neural network(CNN)architecture by using the Gram matrix(GM)technique to convert time-serial PPG signals to two-dimensional images with a temporal dependency to improve accuracy under different forms of motions.To ensure a fair evaluation,we have adopted cross-validation method and“training and testing”dataset splitting method on the TROIKA dataset collected in ambulatory conditions.As a result,the proposed GM-CNN method achieved accuracy improvement from 69.5%to 92.4%,which is the best result in terms of multi-class classification compared with state-of-the-art models.Based on average five-fold cross-validation,we achieved an accuracy of 99.2%,improved the accuracy by 3.3%compared with the best existing method for the binary-class.

水产养殖中智能识别技术的研究进展

智能识别技术是水产养殖由粗放型向集约型转变的关键技术。水产养殖中的智能识别是通过研究并利用机器视觉和机器学习技术实现水下生物和环境的监测,并对生产管理中出现的问题进行判断、分析和预测,以实现自动化养殖为目的。本文从生物的物种识别与分类、年龄识别、性别识别和行为识别4个方面分析了水产养殖中智能识别技术的研究和发展现状,阐述了水产养殖中采用的主要智能识别技术和原理,并对今后水产养殖中智能识别技术的发展进行了展望,以期为中国渔业现代化、智慧化发展提供参考和新思路。

面向新型电力系统的人机交互统一安全认证技术

新型电力系统采用“物理分布、逻辑统一”的全新体系架构重构了电网调控支撑体系。在新架构下,人机云终端(以下简称“云终端”)实现了本地、异地无差别浏览功能,但同时也面临了新的安全挑战。首先,对新架构和人机访问过程进行分析,指出其存在的安全问题。然后,提出了一种基于硬件指纹对云终端进行设备统一安全认证的方法;结合电力调度数字证书和生物特征识别技术,对用户进行多因子身份认证;对服务进行启动认证和服务调用验证,并对服务通信数据进行加密传输,保证服务启动和访问安全。最后,对服务认证加密的性能进行测试,并给出针对不同服务请求大小的认证加密策略;测试结果表明,通过对云终端、用户身份、服务的认证及通信数据加密,实现了人机访问的全链路安全。

基于注意力机制的人脸虹膜双特征融合识别

针对单一生物识别方法存在的固有局限性,利用人脸和虹膜双生物模态信息,提出一种基于注意力机制和低秩多模态融合的身份识别模型(attention mechanism and low-rank multimodal fusion,ALMF)。在模型的人脸和虹膜特征提取网络中均嵌入改进的混合注意力机制(I_CBAM),增强有用特征的提取。利用模态特定低秩因子完成低秩多模态特征级融合(low-rank multimodal fusion,LMF),解决传统特征拼接方式无法充分实现各模态特征的互补、容易造成冗余信息和维度灾难等问题。使用简单高效的余弦距离完成特征模板的比对实现身份识别。实验结果表明,ALMF模型相比单一生物特征识别和传统融合识别算法具有更强的鲁棒性和准确率。

从人工到智能:牛个体识别技术研究进展

牛个体识别技术是实现牛的智能测重、体况评分、体型鉴定、行为监测等自动化技术的先决条件,各种用于牛个体识别的设备和方法在不同的时间段被提出。作者首先对不同牛个体识别方法进行分类阐述,介绍了传统识别方法、生物特征识别方法和深度学习方法在牛个体识别中的研究进展,特别是当前深度学习方法在实际应用中的难点,然后详细分析了不同识别方法的优缺点。传统识别方法如耳切、耳纹、热烙等方法,依靠人工对牛进行识别,识别准确率和识别效率低,忽视了动物福利和标记持久性;无线射频识别技术将牛个体识别由人工识别转向了自动识别,提高了识别效率,但数据安全无法得到保障。随着图像识别技术的发展和深度学习方法的崛起,基于生物特征识别方法和深度学习方法的牛个体识别技术实现了非接触、安全高效的牛智能识别,但基于鼻纹印、视网膜血管和虹膜的生物特征识别方法因理想图像获取难度较大,实用性较差。深度学习方法通过深度神经网络学习图像特征,更适用于复杂条件下的图像应用,在真实的牛场养殖环境中具有广泛的应用前景和潜在价值。作者还对比了不同识别方法在各方面的差异,并在此基础上对牛个体识别技术的研究前景进行了展望。

基于同态加密的人脸识别隐私保护方法

随着大数据的发展与应用,生物特征识别技术得到了快速发展,并在新型认证技术中开始得到广泛应用.由于传统的基于生物特征的身份认证多是在明文状态下进行,对用户的隐私无法给与充分保障,因此基于以上缺陷提出并设计了一种基于同态加密技术的人脸识别隐私保护方法.该方法首先利用当前热门身份认证模型FaceNet对用户生物特征信息进行提取,然后借助基于RLWE的同态加密技术对提取的特征信息进行加密,保证生物特征信息在外包给服务器进行距离计算时不会泄露用户的隐私数据,防止服务器窥探用户的行为.同时,在身份认证过程中引入随机数概念,防止非法用户对服务器的重放攻击.实验证明,该方法在密文状态下仍能保证较高的准确率与可行性.