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.

Orbital decompression surgery and horse chestnut seed extract improved superior orbital vein blood flow in patients with thyroid-associated ophthalmopathy

AIM： To evaluate the efficacy and safety of orbital decomposition （OD） surgery in combination with horse chestnut seed extract （HCSE）, as compared to OD atone, in patients with thyroid-associated ophthalmopathy （TAO）. METHODS： Sixty-two orbits from 62 TAO patients were randomly assigned to OD or OD＋HCSE at 1：1 ratio （31 received OD alone, 31 received OD ＋HCSE）. Forty-two orbits from 21 healthy subjects were used as controls. Complete ophthalmic examination and color Doppler flow imaging （CDFI） were performed before surgery and 3mo post-surgery on all 62 orbits from the TAO patients. CDFI were also performed on the 42 control orbits, The effect of OD ＋HCSE and OD alone on TAO orbits was compared on several endpoints, including superior ophthalmic vein blood flow （SOVBF） parameters, subjective assessment, soft tissue involvement, lid retraction, diplopia, eye movement restriction, degree of exophthalmos, and intraocular pressure. The control orbits were used as reference for the SOVBF parameters. RESULTS： OD surgery with or without HCSE improved SOVBF, symptoms and soft tissue involvement, decreased degree of exophthalmos and intraocular pressure in orbits of TAO patients. The OD ＋HCSE combination led to significantly better improvement of SOVBF than OD alone. The differences between the reductions of SOVBF in the two groups are 1.26 cmls in max-volecity and 0.52 cm/s in min-voiecity （P〈0.0001）. CONCLUSION： SOVBF is significantly reduced in the orbits affected with TAO, indicating that congestion may be an important factor contributing to TAO pathogenesis. OD surgery improves the SOVBF, and combination of HCSE medication and OD surgery further improved venous return than OD surgery alone.

Finger-vein image recognition combining modified hausdorff distance with minutiae feature matching

In this paper, we propose a novel method for finger-vein recognition. We extract the features of the vein patterns for recognition. Then, the minutiae features included bifurcation points and ending points are extracted from these vein patterns. These feature points are used as a geometric representation of the vein patterns shape. Finally, the modified Hausdorff distance algorithm is provided to evaluate the identifica-tion ability among all possible relative positions of the vein patterns shape. This algorithm has been widely used for comparing point sets or edge maps since it does not require point cor-respondence. Experimental results show these minutiae feature points can be used to perform personal verification tasks as a geometric rep-resentation of the vein patterns shape. Fur-thermore, in this developed method. we can achieve robust image matching under different lighting conditions.

Finger Vein Authentication Based on Wavelet Scattering Networks

Biometric-based authentication systems have attracted more attention than traditional authentication techniques such as passwords in the last two decades.Multiple biometrics such as fingerprint,palm,iris,palm vein and finger vein and other biometrics have been introduced.One of the challenges in biometrics is physical injury.Biometric of finger vein is of the biometrics least exposed to physical damage.Numerous methods have been proposed for authentication with the help of this biometric that suffer from weaknesses such as high computational complexity and low identification rate.This paper presents a novel method of scattering wavelet-based identity identification.Scattering wavelet extracts image features from Gabor wavelet filters in a structure similar to convolutional neural networks.What distinguishes this algorithm from other popular feature extraction methods such as deep learning methods,filter-based methods,statistical methods,etc.,is that this algorithm has very high skill and accuracy in differentiating similar images but belongs to different classes,even when the image is subject to serious damage such as noise,angle changes or pixel location,this descriptor still generates feature vectors in away thatminimizes classifier error.This improves classification and authentication.The proposed method has been evaluated using two databases Finger Vein USM(FV-USM)and Homologous Multimodal biometrics Traits(SDUMLA-HMT).In addition to having reasonable computational complexity,it has recorded excellent identification rates in noise,rotation,and transmission challenges.At best,it has a 98.2%identification rate for the SDUMLA-HMT database and a 96.1%identification rate for the FV-USM database.

Application of free vein skin flap on the anterior aspect of wrist in the case of finger injury with vessel and skin defect

Objective To introduce an effective reconstruction method for the finger injured with vessel and skin defect. Methods Free skin flap with skin vein was transplanted on the site of tissue defect, connecting by anastomosis the vein with artery or vein of the finger. Results Seven cases were treated with this method,among which 5 cases have sikin defect on the palm aspect of fingers, the rest have skin defect on the dorsal aspect skin of finger. All fingers survived with good shape and function. Conclusion This is a simple and effective method of finger reconstruction for the patients with defect of vessels and skin. 6 refs.

舌下络脉的客观识别与颜色分类研究

目的探讨中医舌下络脉诊的颜色信息客观识别方法。方法结合计算机视觉,尝试利用紧凑型全卷积网络(CFCNs)和19种深度学习分类模型等算法进行研究,并设计双络脉矩形算法,作为舌下络脉分割识别和颜色信息提取的手段。结果应用“去除反光点+数据扩充+数据后处理”方法获取的舌底分割的精确率为0.9559,F1值为0.9473、mIoU值为0.9000,应用“去除反光点+语义分割舌体结果作为输入+数据扩充+后处理边缘膨胀腐蚀”方法获取的舌下络脉分割结果精确率为0.7784、F1值为0.7383、mIoU值为0.5851,均明显优于目前经典的或改进的U-net模型。舌下络脉颜色分类上,DenseNet161-bc-early_stopping分类模型的效果最佳,准确率达0.8037。结论深度学习方法对于识别中医舌下络脉颜色信息具有一定作用,可为中医舌下络脉诊的颜色量化检测技术研究提供新方法。

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.

指背静脉移植在血管缺损的断指再植术中的临床应用

目的探讨指背静脉移植在血管缺损的断指再植术中的应用效果。方法收集2021年4月至2022年8月于秦皇岛市第一医院进行断指再植术的35例手指离断患者(40指)的临床资料,术中均采用指背静脉移植桥接术。观察术中镜下挫伤血管内膜挫伤分布情况,记录血管移植的时间。比较同水平面指背静脉与缺损血管的管径,观察术后再植手指的成活情况、并发症发生情况和成活手指的功能恢复情况。结果术后手指成活率为95.0%(38/40)。自切取静脉至完成两处吻合口的时间一般约为40分钟,吻合质量良好。同水平面指背静脉与缺损血管的管径相当或略粗。术后6个月,在成活的38个再植手指中,手指功能优10指,良25指,差3指,优良率为92.1%(35/38)。结论在血管缺损的断指再植术中,指背静脉移植可在避免再植时过多缩短指骨、关节融合或截指的情况下获得满意的外形和优良的功能。

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。

MCFNet:融合上下文信息的多尺度视网膜动静脉分类网络

针对由于血管类间具有强相似性造成的动静脉错误分类问题,提出了一种新的融合上下文信息的多尺度视网膜动静脉分类网络(multi-scale retinal artery and vein classification network,MCFNet),该网络使用多尺度特征(multi-scale feature,MSF)提取模块及高效的全局上下文信息融合(efficient global contextual information aggregation,EGCA)模块结合U型分割网络进行动静脉分类,抑制了倾向于背景的特征并增强了血管的边缘、交点和末端特征,解决了段内动静脉错误分类问题。此外,在U型网络的解码器部分加入3层深度监督,使浅层信息得到充分训练,避免梯度消失,优化训练过程。在2个公开的眼底图像数据集(DRIVE-AV,LES-AV)上,与3种现有网络进行方法对比,该模型的F1评分分别提高了2.86、1.92、0.81个百分点,灵敏度分别提高了4.27、2.43、1.21个百分点,结果表明所提出的模型能够很好地解决动静脉分类错误的问题。

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。

指蹼逆行指背静脉岛状皮瓣修复手指中远节皮肤缺损

2020年1月~2021年10月,我科采用指蹼逆行指背静脉岛状皮瓣修复20例手指中远节皮肤缺损患者,疗效满意,报道如下。1材料与方法1.1病例资料本组20例(20指),男15例,女5例,年龄18~64岁。拇指8例,示指6例,中指3例,环指1例,小指2例。创面面积2.0 cm×1.5 cm~2.5 cm×2.0 cm。受伤原因:机器撕脱伤14例,切割伤3例,压砸伤3例。19例急诊手术,伤后至手术时间2~4 h.

轻量级空间移位MLP用于指静脉分割

基于CNN和Transformer架构图像分割网络模型参数繁多、计算复杂,需要消耗大量的内存资源,这使得它们无法满足快速、有效的指静脉图像分割需求,并且在算力有限的嵌入式平台部署非常困难。因此,提出一种基于MLP的轻量级手指静脉分割算法。首先,通过不同轴向移动特征图获取信息流来捕获局部依赖性,提高局部信息提取能力;其次,使用标记MLP块对特征图进行标记和投影卷积特征;然后,在下采样和上采样之前都添加一个轻量级注意力模块来提升分割性能,在输入到MLP的同时转移输入的通道,使网络模型更专注于学习本地依赖性。在SDU-FV、HKPU和UTFVP三个公开的手指静脉数据集中进行实验,结果表明:该方法仅使用了346.949K Params、1.835G Flops和11.023M的计算复杂度,分割性能指标Dice、AUC、Acc分别达到0.515 6、0.895 9、91.68%。在三种NVIDIA嵌入式平台上,该算法的Dice和AUC指标均取得了最优性能。

Line Patterns Segmentation in Blurred Images Using Contrast Enhancement and Local Entropy Thresholding

Finger vein extraction and recognition hold significance in various applications due to the unique and reliable nature of finger vein patterns. While recently finger vein recognition has gained popularity, there are still challenges associated with extracting and processing finger vein patterns related to image quality, positioning and alignment, skin conditions, security concerns and processing techniques applied. In this paper, a method for robust segmentation of line patterns in strongly blurred images is presented and evaluated in vessel network extraction from infrared images of human fingers. In a four-step process: local normalization of brightness, image enhancement, segmentation and cleaning were involved. A novel image enhancement method was used to re-establish the line patterns from the brightness sum of the independent close-form solutions of the adopted optimization criterion derived in small windows. In the proposed method, the computational resources were reduced significantly compared to the solution derived when the whole image was processed. In the enhanced image, where the concave structures have been sufficiently emphasized, accurate detection of line patterns was obtained by local entropy thresholding. Typical segmentation errors appearing in the binary image were removed using morphological dilation with a line structuring element and morphological filtering with a majority filter to eliminate isolated blobs. The proposed method performs accurate detection of the vessel network in human finger infrared images, as the experimental results show, applied both in real and artificial images and can readily be applied in many image enhancement and segmentation applications.

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。

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.

面向人机协作系统的上肢姿态精准识别算法研究

在基于姿态识别协同控制灵巧手机械臂的任务中,会出现身体部位相互遮挡以及非操作人员身体干扰的问题。因此本文提出了一种面向人机协作系统的上肢姿态精准识别算法,能够有效排除遮挡和干扰问题。该算法首先基于Finger-YOLOv4算法框选出人体上肢区域;其次通过稀疏性目标提取算法排除非操作人员身体干扰;然后在设计的双特征条件随机场网络中进行深度学习,解决遮挡导致的类内模糊问题,精准定位人体上肢的48个关键点坐标;最后,根据关键点坐标进行人体上肢的姿态预测,将人体上肢的姿态与灵巧手机械臂的姿态进行映射,完成人机协作。实验表明,本算法平均检测速度33 FPS,关键点平均检测精度75.2%,协同操作完成度98%。满足实际需求。

深度学习在手指静脉识别中的应用研究综述

手指静脉识别技术由于其非接触、高防伪性以及活体检测等优点,成为新一代生物识别技术中的研究热点。随着深度学习的发展,基于深度神经网络的手指静脉识别技术取得了显著的成果。首先对手指静脉识别领域的常用公开数据集进行了介绍,然后根据神经网络学习任务的不同,对近几年深度学习方法在手指静脉识别中的应用进行了分类,分析了每种类型的技术特点和适用场景。从轻量化网络、数据增广、注意力机制等方面对手指静脉识别中的深度学习设计技巧进行了介绍。从分类损失和度量学习损失两方面,对模型中常用的损失函数进行了阐述。最后介绍了手指静脉识别系统的评价指标并汇总了部分研究在准确率和等错误率方面的成果。此外,还提出了手指静脉识别面临的挑战和潜在的发展方向。

“和伤散”熏洗联合刘氏“三指按摩”手法对预防髋部骨折术后下肢深静脉血栓的效果

目的观察“和伤散”熏洗联合刘氏“三指按摩”手法护理预防髋部骨折患者术后下肢深静脉血栓的效果。方法选择符合纳入标准的116例髋部骨折患者为研究对象,采用随机数字表法将其分为对照组和观察组,对照组患者术后实施常规护理,观察组在对照组常规护理基础上予以“和伤散”熏洗联合刘氏“三指按摩”手法护理,2组患者均护理10 d。比较2组患者凝血指标以及下肢深静脉血栓发生率。结果观察组D-二聚体、纤维蛋白原均低于对照组,活化凝血活酶时间、凝血酶原时间均长于对照组,差异有统计学意义(P<0.05)。观察组下肢深静脉血栓发生率(1.72%)与对照组(13.79%)比较,差异有统计学意义(P<0.05)。结论对于髋部骨折术后患者,运用“和伤散”熏洗联合刘氏“三指按摩”手法护理能够降低下肢深静脉血栓发生率。