Unconstrained Hand Dorsal Veins Image Database and Recognition System

Hand veins can be used effectively in biometric recognition since they are internal organs that,in contrast to fingerprints,are robust under external environment effects such as dirt and paper cuts.Moreover,they form a complex rich shape that is unique,even in identical twins,and allows a high degree of freedom.However,most currently employed hand-based biometric systems rely on hand-touch devices to capture images with the desired quality.Since the start of the COVID-19 pandemic,most handbased biometric systems have become undesirable due to their possible impact on the spread of the pandemic.Consequently,new contactless hand-based biometric recognition systems and databases are desired to keep up with the rising hygiene awareness.One contribution of this research is the creation of a database for hand dorsal veins images obtained contact-free with a variation in capturing distance and rotation angle.This database consists of 1548 images collected from 86 participants whose ages ranged from 19 to 84 years.For the other research contribution,a novel geometrical feature extraction method has been developed based on the Curvelet Transform.This method is useful for extracting robust rotation invariance features from vein images.The database attributes and the veins recognition results are analyzed to demonstrate their efficacy.

People Recognition by RGB and NIR Analysis from Digital Image Database Using Cross-Correlation and Wavelets

This document presents a framework for recognizing people by palm vein distribution analysis using cross-correlation based signatures to obtain descriptors. Haar wavelets are useful in reducing the number of features while maintaining high recognition rates. This experiment achieved 97.5% of individuals classified correctly with two levels of Haar wavelets. This study used twelve-version of RGB and NIR (near infrared) wavelength images per individual. One hundred people were studied;therefore 4,800 instances compose the complete database. A Multilayer Perceptron (MLP) was trained to improve the recognition rate in a k-fold cross-validation test with k = 10. Classification results using MLP neural network were obtained using Weka (open source machine learning software).

Biometric Finger Vein Recognition Using Evolutionary Algorithm with Deep Learning

In recent years,the demand for biometric-based human recog-nition methods has drastically increased to meet the privacy and security requirements.Palm prints,palm veins,finger veins,fingerprints,hand veins and other anatomic and behavioral features are utilized in the development of different biometric recognition techniques.Amongst the available biometric recognition techniques,Finger Vein Recognition(FVR)is a general technique that analyzes the patterns of finger veins to authenticate the individuals.Deep Learning(DL)-based techniques have gained immense attention in the recent years,since it accomplishes excellent outcomes in various challenging domains such as computer vision,speech detection and Natural Language Processing(NLP).This technique is a natural fit to overcome the ever-increasing biomet-ric detection problems and cell phone authentication issues in airport security techniques.The current study presents an Automated Biometric Finger Vein Recognition using Evolutionary Algorithm with Deep Learning(ABFVR-EADL)model.The presented ABFVR-EADL model aims to accomplish bio-metric recognition using the patterns of the finger veins.Initially,the presented ABFVR-EADL model employs the histogram equalization technique to pre-process the input images.For feature extraction,the Salp Swarm Algorithm(SSA)with Densely-connected Networks(DenseNet-201)model is exploited,showing the proposed method’s novelty.Finally,the Deep-Stacked Denoising Autoencoder(DSAE)is utilized for biometric recognition.The proposed ABFVR-EADL method was experimentally validated using the benchmark databases,and the outcomes confirmed the productive performance of the proposed ABFVR-EADL model over other DL models.

Extraction of intersecting palm-vein and palmprint features for cancellable identity verification

A novel method based on the cross-modality intersecting features of the palm-vein and the palmprint is proposed for identity verification.Capitalising on the unique geometrical relationship between the two biometric modalities,the cross-modality intersecting points provides a stable set of features for identity verification.To facilitate flexibility in template changes,a template transformation is proposed.While maintaining non-invertibility,the template transformation allows transformation sizes beyond that offered by the con-ventional means.Extensive experiments using three public palm databases are conducted to verify the effectiveness the proposed system for identity recognition.

Artificial intelligence can assist with diagnosing retinal vein occlusion

AIM:To assist with retinal vein occlusion(RVO)screening,artificial intelligence(AI)methods based on deep learning(DL)have been developed to alleviate the pressure experienced by ophthalmologists and discover and treat RVO as early as possible.METHODS:A total of 8600 color fundus photographs(CFPs)were included for training,validation,and testing of disease recognition models and lesion segmentation models.Four disease recognition and four lesion segmentation models were established and compared.Finally,one disease recognition model and one lesion segmentation model were selected as superior.Additionally,224 CFPs from 130 patients were included as an external test set to determine the abilities of the two selected models.RESULTS:Using the Inception-v3 model for disease identification,the mean sensitivity,specificity,and F1 for the three disease types and normal CFPs were 0.93,0.99,and 0.95,respectively,and the mean area under the curve(AUC)was 0.99.Using the DeepLab-v3 model for lesion segmentation,the mean sensitivity,specificity,and F1 for four lesion types(abnormally dilated and tortuous blood vessels,cotton-wool spots,flame-shaped hemorrhages,and hard exudates)were 0.74,0.97,and 0.83,respectively.CONCLUSION:DL models show good performance when recognizing RVO and identifying lesions using CFPs.Because of the increasing number of RVO patients and increasing demand for trained ophthalmologists,DL models will be helpful for diagnosing RVO early in life and reducing vision impairment.

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。

轻量级Transformer的双向交互近红外手指静脉图像识别

针对现有手指静脉识别算法速度慢、复杂度高以及Transformer架构在小数据集上效果不佳的问题,提出轻量级Transformer的双向交互识别方法 .利用轻量级卷积神经网络与改进的Transformer架构组成并行主干网络,用于近红外手指静脉图像的局部和全局特征提取;设计交互结构,在并行结构的基础上,以交互方式融合两条分支上不同尺度的特征.为最大程度地保留近红外图像的局部特征和全局表示,将两条分支提取的信息拼接融合,通过输出层得出识别结果 .结果表明,该算法在多个数据集上的最高识别率可达99.77%,参数量仅1.33 MB.相较于其他指静脉算法,以及改进的Transformer架构,在保持高准确率的同时进一步降低了算法的复杂度.

基于手指静脉识别的艺术实验教学智慧监管系统

当前艺术实验教学中缺乏兼顾安全监管和智慧决策的信息化管理手段。在主流的信息安全技术中,手指静脉识别技术具有活体识别、准确率高、使用方便等优势,适应艺术实验教学监管应用场景。该文提出结合软特征的手指静脉识别算法,进一步提升了识别性能。在此基础上,研究实现艺术实验教学智能监管系统,在实现实验教学监管的同时辅助管理决策,有效解决了监管中普遍存在的问题,全面提升了监管水平。

一种基于改进多任务学习的手背静脉识别方法与系统

针对当前手背静脉识别产品较为缺乏的问题,为了促进深度学习技术在手背静脉识别领域的落地应用,提出一种基于改进多任务学习的手背静脉识别方法,同时开发一套基于软硬件协同的手背静脉识别系统。来自采集手背静脉数据集上的实验结果显示,改进算法在嵌入式设备上能够取得99.59%的准确率、0.437%的等误率、小于1 s的识别时间,足以满足大多数常见应用场景对识别性能的需求,为手背静脉识别方法的落地应用提供了一种有效的解决方案。

采用轻量化神经网络的高安全手指静脉识别系统

针对特殊材料能伪造手指静脉从而欺骗识别系统,以及利用卷积神经网络进行手指静脉识别计算量大的问题,设计了具有活体检测功能和轻量化卷积神经网络结构的手指静脉识别系统。采用光容积法检测手指脉搏波的变化,从而判断被采集对象是否为活体;利用剪枝及通道恢复方法改进了ResNet-18卷积神经网络,并结合L_(1)正则化增加卷积神经网络的特征选择能力,在提升算法准确率的基础上,能有效地降低计算资源的消耗。实验表明,使用改进的剪枝及通道恢复优化结构,参数量降低了75.6%,计算量降低了25.6%,在山东大学和香港理工大学手指静脉数据库上得到的等误率分别为0.025%、0.085%,远低于ResNet-18得到的等误率(0.117%、0.213%)。

基于深度学习的K近邻图迭代静脉识别算法研究

深度学习在计算机视觉中具有强大的特征表达能力,近年来广泛应用于静脉特征的提取与识别。通常,基于深度学习的静脉识别模型在训练阶段,每次仅输入1幅图像及其对应的标签,学习图像与标签之间的映射关系,然而,这种每次只处理单幅图像的方法,难以捕捉不同类别多幅静脉图像之间的关系。为了解决该问题,提出一种基于深度学习的K近邻图迭代静脉识别算法。用较优的深度学习模型提取掌静脉图像特征;利用K近邻算法通过特征距离在训练集中选出最近的K幅图像及其标签,通过这些特征向量生成标签传播矩阵和标签矩阵;利用图迭代算法预测待分类图像的标签,完成分类。在香港理工大学和同济大学提供的掌静脉数据集上进行实验,最高识别精度分别为99.67%和92.72%。

掌静脉识别的深度学习方法综述

掌静脉识别作为一种新兴的红外生物识别技术,因其高安全性、活体检测性等优势已成为当前生物特征识别领域中的研究热点之一。近年来,该领域的大量研究通过引入深度学习方法推动了掌静脉识别技术的发展。为了掌握掌静脉识别领域最新研究现状及发展方向,对数据采集和数据预处理的主流算法进行了分类和总结,并针对基于深度学习的掌静脉识别的最新进展按照掌脉特征表征、网络设计与优化、轻量级网络进行了分类和详细阐述。针对当前单模态识别达到瓶颈等问题,分析并对比了多模态和多特征融合识别相关算法;探讨了当前掌静脉识别的研究难点挑战,并对未来的发展趋势进行了展望与总结。

基于静脉关键特征和AdaFace损失的轻量级指静脉识别算法

基于深度学习的指静脉识别方法通常需要大量的计算资源,限制了其在嵌入设备上的推广和普及,采用轻量级网络又面临模型参数减少导致准确率下降的问题,为此提出一种基于指静脉关键特征和AdaFace损失的轻量级识别算法。在MicroNet框架中,首先提出一种FMixconv卷积来替代原网络中的深度卷积,减少参数的同时可以获得静脉特征的多尺度信息;其次引入轻量级注意力模块CA模块,从空间和通道上聚焦于静脉特征的关键信息;最后在损失函数中加入AdaFace损失,通过特征范数对图像质量进行评价,以减少图像质量下降对训练的影响。该算法在SDUMLA-HMT、FV-USM和自建数据集上的识别准确率达到99.84%、99.39%和99.42%,而参数量仅有0.82 M。实验结果表明,该算法在准确率和参数量大小上均领先于其他方法。

Finger vein recognition using weighted local binary pattern code based on a support vector machine

Finger vein recognition is a biometric technique which identifies individuals using their unique finger vein patterns. It is reported to have a high accuracy and rapid processing speed. In addition, it is impossible to steal a vein pattern located inside the finger. We propose a new identification method of finger vascular patterns using a weighted local binary pattern (LBP) and support vector machine (SVM). This research is novel in the following three ways. First, holistic codes are extracted through the LBP method without using a vein detection procedure. This reduces the processing time and the complexities in detecting finger vein patterns. Second, we classify the local areas from which the LBP codes are extracted into three categories based on the SVM classifier: local areas that include a large amount (LA), a medium amount (MA), and a small amount (SA) of vein patterns. Third, different weights are assigned to the extracted LBP code according to the local area type (LA, MA, and SA) from which the LBP codes were extracted. The optimal weights are determined empirically in terms of the accuracy of the finger vein recognition. Experimental results show that our equal error rate (EER) is significantly lower compared to that without the proposed method or using a conventional method.

一种轻量级掌静脉识别算法NEPVR

信息技术的进步催生了生物特征识别逐渐替代传统身份验证方法,尤其关注卫生、安全的掌静脉识别,然而在计算资源受限的情况下保持识别性能仍然是一项挑战。近年来,虽然深度学习架构Vision Transformer在模型性能上取得显著进展并在掌静脉识别领域逐渐得到应用,但是也因参数量问题限制了其适用范围。该文提出了一种手掌静脉识别算法(NAM-EfficientViT Based Palm Vein Recognition, NEPVR),采用了EfficientViT作为深度学习的高效轻量化网络以减少参数量的规模,并结合归一化注意力机制加强图像在通道和空间维度上对重要细节特征的提取,进而保持良好的识别性能。此外,NEPVR还融合了交叉熵和三元组损失函数作为在网络训练中的综合损失函数,以提高识别性能和模型收敛的稳定性。实验结果表明:将掌静脉信息编码为512维特征向量的方法识别性能最佳;在PolyU、CASIA与TongjiU数据集上进行的评估中,等误差率(EER)分别达到了0.067%、0.150%与0.085%,充分证明了该算法的有效性。

基于改进MobileNet的指静脉识别算法

指静脉处于手指皮肤里层不易改变,利用指静脉进行身份识别与验证已经成为生物识别领域的一个研究热点。基于CNN的指静脉识别参数量大、计算量大、运行时间长。针对这些问题,论文提出一种基于改进轻量级网络(MobileNet)的指静脉识别算法。改进后的网络融入粒子群算法(PSO)对MobileNet参数进行优化。实验结果表明,该识别算法在保持高精度的前提下,减少了参数量和运算时间。

基于掌静脉识别技术的城市轨道交通乘车管理系统设计与实现

针对城市轨道交通传统自动售检票系统应用过程中面临的操作复杂度高、运营效率低等问题,基于掌静脉识别技术原理,构建基于掌静脉识别技术的城市轨道交通乘车管理系统,设计了系统架构和功能。通过掌静脉识别的注册认证、算法匹配、电子交互、多元融合等关键技术,实现了该系统与传统自动售检票系统的集成融合,达到了通过掌静脉识别快速乘车注册、识别、支付等通行目标。应用表明,该系统具备更高识别准确率、更低故障率等特点,具有无接触式进出站、掌码合一、实名制出行、多元化出行等优点,对城市轨道交通乘车管理系统进一步提高安全性和稳定性等具有一定的参考价值。

面向掌纹掌静脉识别网络轻量化的非对称双模态融合方法

深度学习已在掌纹掌静脉领域广泛应用,但随着任务使用场景的不断微型化、终端化,现有的深度学习模型往往难以在算力匮乏、内存有限的边缘设备上顺利部署。本文基于知识蒸馏方法提出了轻量化的掌纹掌静脉识别网络。根据模态特征提取复杂程度,为掌纹与掌静脉模态分别选用不同的网络深度。在常规知识蒸馏方法中引入新设计的模态特征损失函数,强化教师模型对各模态特征提取的指导作用。实验结果表明,该方法有效协调了模型大小与性能,为边缘计算环境下的生物特征识别技术提供了一种有效的解决方案。

Palm vein recognition method based on fusion of local Gabor histograms

Gabor features have been shown to be effective for palm vein recognition. This paper presents a novel feature representation method, implementing the fusion of local Gabor histograms （FLGH）, in order to improve the accuracy of palm vein recognition systems. A new local descriptor called local Gabor principal differences patterns （LGPDP） encodes the Gabor magnitude using the local maximum difference （LMD） operator. The corresponding Gabor phase patterns are encoded by local Gabor exclusive OR （XOR） patterns （LGXP）. Fisher＇s linear discriminant （FLD） method is then implemented to reduce the dimensionality of the feature representation. Low-dimensional Gabor magnitude and phase feature vectors are finally fused to enhance accuracy. Experimental results from Institute of Automation, Chinese Academy of sciences （CASIA） database show that the proposed FLGH method achieves better performance by utilizing score-level fusion. The equal error rate （EER） is 0.08%, which outperforms other conventional palm vein recognition methods （EER range from 2.87% to 0.16%）, e.g., the Laplacian palm, minutiae feature, Hessian phase, Eigenvein, local invariant features, mutual foreground local binary patterns （LBP）, and multi-sampling feature fusion methods.

基于SURF算子的快速手背静脉识别

提出基于加速鲁棒性特征(speeded-up robust features,SURF)的手背静脉识别算法。首先对手背静脉图像进行预处理,提取手背静脉感兴趣区域(ROI),然后提取手背静脉的局部SURF特征,基于欧式距离实现测试样本和注册样本特征点的匹配,并剔除错误匹配对,最后计算匹配率作为待识别样本和注册样本之间的相似度测试实现身份识别。利用TJU手背静脉图像数据库对算法性能进行测试,在认证模式下等错率为0.07%,平均识别时间0.153 s。实验结果证明该算法可以快速有效地实现手背静脉识别。