浏览全部资源
扫码关注微信
Received：29 October 2018，
Revised：2019-1-21，
Published：16 August 2019
移动端阅览
目的
2
掌纹识别技术作为一种新兴的生物特征识别技术越来越受到广泛重视。深度学习是近10年来人工智能领域取得的重要突破。但是，基于深度学习的掌纹识别相关研究还比较初步，尤其缺乏深入的分析和讨论，且已有的工作使用的都是比较简单的神经网络模型。为此，本文使用多种卷积神经网络对掌纹识别进行性能评估。
方法
2
选取比较典型的8种卷积神经网络模型，在5个掌纹数据库上针对不同网络模型、学习率、网络层数、训练数据量等进行性能评估，展开实验，并与经典的传统掌纹识别方法进行比较。
结果
2
在不同卷积神经网络识别性能评估方面，ResNet和DenseNet超越了其他网络，并在PolyU M_B库上实现了100%的识别率。针对不同学习率、网络层数、训练数据量的实验发现，5×10
-5
为比较合适的识别率；网络层数并非越深越好，VGG-16与VGG-19的识别率相当，ResNet层数由18层逐渐增加到50层，识别率则逐渐降低；参与网络训练的数据量总体来说越多越好。对比传统的非深度学习方法，卷积神经网络在识别效果方面还存在一定差距。
结论
2
实验结果表明，对于掌纹识别，卷积神经网络也能获得较好的识别效果，但由于训练数据量不充分等原因，与传统算法的识别性能还有差距。基于卷积神经网络的掌纹识别研究还需要进一步深入开展。
Objective
2
In recent years
as an emerging biometrics technology
low-resolution palmprint recognition has attracted attention due to its potential for civilian applications. Many effective palmprint recognition methods have been proposed. These traditional methods can be roughly divided into categories
such as texture-based
line-based
subspace learning-based
correlation filter-based
local descriptor-based
and orientation coding-based. In the past decade
deep learning was the most important technique in the field of artificial intelligence
introducing performance breakthroughs in many fields such as speech recognition
natural language processing
computer vision
image and video analysis
and multimedia. In the field of biometrics
especially in face recognition
deep learning has become the most mainstream technology. However
research on deep learning-based palmprint recognition remains at the preliminary stage. Research on deep learning-based palmprint recognition is relatively rare
and in-depth analysis and discussion on deep learning-based palmprint recognition is scarce. In addition
most existing work on deep learning-based palmprint recognition exploited simple networks only. In palmprint databases
the palmprint images were usually captured in two different sessions. In traditional palmprint recognition work
the images captured in the first session were usually treated as the training data
and the images captured in the second session were typically used as the test data. However
in existing work on deep learning-based palmprint recognition
the images captured in the first and second sessions are exploited as the training data
which leads to a high recognition accuracy. In this study
we evaluate the performance of various convolutional neural networks (CNNs) in palmprint recognition to thoroughly investigate the problem of deep learning-based palmprint recognition.
Method
2
We systematically review the classic CNNs in recent years and analyze the structure of various networks and their underlying connections. Then
we perform a large-scale performance evaluation for palmprint recognition. First
we select eight typical CNN networks
namely
AlexNet
VGG
Inception_v3
ResNet
Inception_v4
Inception_ResNet_v2
DenseNet
and Xception
and evaluate these networks on five palmprint databases to determine the best network. We choose the pretrained model in ImageNet Large Scale Visual Recognition Challenge for training because training the CNN model in the case of insufficient data (the scale of the dataset is small) is time consuming and may lead to poor results. Second
we conduct evaluations by using six learning rates from large to small to analyze the impact on performance and obtain the suitable learning rate. Third
we compare the performance of VGG-16 and VGG-19 and ResNet18
ResNet34
and ResNet50 in the evaluation on different layer numbers of the network. Fourth
starting from a single training data
we gradually increase the data amount until the training data contains all the data of the first session to analyze the influence of different training data quantities on performance. Finally
the performance of CNNs is compared with that of several traditional methods
such as competitive code
ordinal code
RLOC
and LLDP.
Result
2
Experimental results on eight CNNs with different structures show that ResNet18 outperforms other networks and can achieve 100% recognition rate on the PolyU M_B database. The performance of DenseNet121 is similar to that of ResNe18
and the performance of AlexNet is poor. To evaluate the learning rate
results show that 5×10
-5
is suitable for the palmprint dataset used in this study. If the learning rate is too large
then the performance of these CNNs will be poor. In addition
the appropriate learning rate of the VGG network is 10
-5
. The performance evaluation of different numbers of network layers indicated that the recognition rate of VGG-16 and VGG-19 is similar. As the layer number of ResNet increases from 18 to 34 and to 50
the recognition rate gradually decreases. Generally speaking
more data involved in network training results in improved performance. In the early stage of the increase in the amount of data
the performance is significantly improved. A comparison of the performance of CNNs with that of traditional non-deep learning methods shows that the performance of CNNs is equivalent to that of non-deep learning methods on the PolyU M_B database. On other databases
the performance of CNNs is worse than that of traditional non-deep learning methods.
Conclusion
2
This paper reviews the CNNs proposed in the literature and conducts a large-scale performance evaluation of palmprint recognition on five different palmprint databases under different network structures
learning rates
network layers
and training data amounts. Results show that ResNet is suitable for palmprint recognition and that 5×10
-5
is an appropriate learning rate
which can help researchers engaged in deep learning and palmprint recognition. We also compared the performance of CNNs with that of four traditional methods. The overall performance of CNN is slightly worse than that of traditional methods
but we can still see the great potential of deep learning methods.
Lecun Y, Bottou L, Bengio Y, et al.Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.[DOI:10.1109/5.726791]
Krizhevsky A, Sutskever I, Hinton G E.ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6):84-90.[DOI:10.1145/3065386]
Simonyan K, Zisserman A.Very deep convolutional networks for large-scale image recognition[EB/OL].[2018-10-14] https://arxiv.org/pdf/1409.1556.pdf https://arxiv.org/pdf/1409.1556.pdf .
He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016.[ DOI: 10.1109/CVPR.2016.90 http://dx.doi.org/10.1109/CVPR.2016.90 ]
Szegedy C, Vanhoucke V, Ioffe S, et al. Rethinking the inception architecture for computer vision[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016.[ DOI: 10.1109/CVPR.2016.308 http://dx.doi.org/10.1109/CVPR.2016.308 ]
Szegedy C, Ioffe S, Vanhoucke V.Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence. Mountain View, CA: AAAI, 2017: #12.
Huang G, Liu Z, van der Maaten L, et al. Denselyconnected convolutional networks[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017.[ DOI: 10.1109/CVPR.2017.243 http://dx.doi.org/10.1109/CVPR.2017.243 ]
Chollet F. Xception: deep learning with depthwise separable convolutions[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017.[ DOI: 10.1109/CVPR.2017.195 http://dx.doi.org/10.1109/CVPR.2017.195 ]
Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: IEEE, 2015.[ DOI: 10.1109/CVPR.2015.7298594 http://dx.doi.org/10.1109/CVPR.2015.7298594 ]
Ioffe S, Szegedy C.Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on International Conference on Machine Learning. Lille, France: JMLR.org, 2015: 448-456.
Kong A, Zhang D, Kamel M.A survey of palmprint recognition[J]. Pattern Recognition, 2009, 42(7):1408-1418.[DOI:10.1016/j.patcog.2009.01.018]
Zhang D, Zuo W M, Yue F.A comparative study of palmprint recognition algorithms[J]. ACM Computing Surveys, 2012, 44(1):#2.[DOI:10.1145/2071389.2071391]
Fei L K, Lu G M, Jia W, et al.Feature extraction methods for palmprint recognition:a survey and evaluation[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2019, 49(2):346-363.[DOI:10.1109/TSMC.2018.2795609]
Yue F, Zuo W M, Zhang D P.Survey of palmprint recognition algorithms[J]. Acta Automatica Sinica, 2010, 36(3):353-365.
岳峰, 左旺孟, 张大鹏.掌纹识别算法综述[J].自动化学报, 2010, 36(3):353-365. [DOI:10.3724/SP.J.1004.2010.00353]
Wu X Q, Zhang D, Wang K Q.Palm line extraction and matching for personal authentication[J]. IEEE Transactions on Systems, Man, and Cybernetics-Part A:Systems and Humans, 2006, 36(5):978-987.[DOI:10.1109/TSMCA.2006.871797]
Liu L, Zhang D, You J.Detecting wide lines using isotropic nonlinear filtering[J]. IEEE Transactions on Image Processing, 2007, 16(6):1584-1595.[DOI:10.1109/TIP.2007.894288]
Huang D S, Jia W, Zhang D.Palmprint verification based on principal lines[J]. Pattern Recognition, 2008, 41(4):1316-1328.[DOI:10.1016/j.patcog.2007.08.016]
Jing X Y, Zhang D.A face and palmprint recognition approach based on discriminant DCT feature extraction[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2004, 34(6):2405-2415.[DOI:10.1109/TSMCB.2004.837586]
Lu J, Zhao Y, Hu J.Enhanced Gabor-based region covariance matrices for palmprint recognition[J]. Electronics Letters, 2009, 45(17):880-881.[DOI:10.1049/el.2009.0871]
Kong A W K, Zhang D. Competitive coding scheme for palmprint verification[C]//Proceedings of the 17th International Conference on Pattern Recognition.Cambridge, UK: IEEE, 2004.[ DOI: 10.1109/ICPR.2004.1334184 http://dx.doi.org/10.1109/ICPR.2004.1334184 ]
Sun Z N, Tan T N, Wang Y H, et al. Ordinal palmprint represention for personal identification[C]//Proceedings of 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA, USA: IEEE, 2005.[ DOI: 10.1109/CVPR.2005.267 http://dx.doi.org/10.1109/CVPR.2005.267 ]
Jia W, Huang D S, Zhang D.Palmprint verification based on robust line orientation code[J]. Pattern Recognition, 2008, 41(5):1504-1513.[DOI:10.1016/j.patcog.2007.10.011]
Zuo W M, Yue F, Wang K Q, et al. Multiscale competitive code for efficient palmprint recognition[C]//Proceedings of the 19th International Conference on Pattern Recognition. Tampa, FL, USA: IEEE, 2008.[ DOI: 10.1109/ICPR.2008.4761868 http://dx.doi.org/10.1109/ICPR.2008.4761868 ]
Fei L K, Xu Y, Tang W L, et al.Double-orientation code and nonlinear matching scheme for palmprint recognition[J]. Pattern Recognition, 2016, 49:89-101.[DOI:10.1016/j.patcog.2015.08.001]
Fei L K, Zhang B, Zhang W, et al.Local apparent and latent direction extraction for palmprint recognition[J]. Information Sciences, 2019, 473:59-72.[DOI:10.1016/j.ins.2018.09.032]
Zheng Q, Kumar A, Pan G.Suspecting less and doing better:new insights on palmprint identification for faster and more accurate matching[J]. IEEE Transactions on Information Forensics and Security, 2016, 11(3):633-641.[DOI:10.1109/TIFS.2015.2503265]
Jia W, Hu R X, Lei Y K, et al.Histogram of oriented lines for palmprint recognition[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2014, 44(3):385-395.[DOI:10.1109/TSMC.2013.2258010]
Luo Y T, Zhao L Y, Zhang B, et al.Local line directional pattern for palmprint recognition[J]. Pattern Recognition, 2016, 50:26-44.[DOI:10.1016/j.patcog.2015.08.025]
Wu X Q, Zhao Q S.Deformed palmprint matching based on stable regions[J]. IEEE Transactions on Image Processing, 2015, 24(12):4978-4989.[DOI:10.1109/TIP.2015.2478386]
Zhang L, Shen Y, Li H Y, et al.3D palmprint identification using block-wise features and collaborative representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(8):1730-1736.[DOI:10.1109/TPAMI.2014.2372764]
Hennings-Yeomans P H, Vijaya Kumar B V K, SavvidesM.Palmprint classification using multiple advanced correlation filters and palm-specific segmentation[J]. IEEE Transactions on Information Forensics and Security, 2007, 2(3):613-622.[DOI:10.1109/TIFS.2007.902039]
Jia W, Zhang B, Lu J T, et al.Palmprint recognition based on complete direction representation[J]. IEEE Transactions on Image Processing, 2017, 26(9):4483-4498.[DOI:10.1109/TIP.2017.2705424]
Sundararajan K, Woodard D L.Deep learning for biometrics:a survey[J]. ACM Computing Surveys, 2018, 51(3):#65.[DOI:10.1145/3190618]
CDATA[Sun Y, Wang X G, Tang X O.Deep learning face representation by joint identification-verification[EB/OL].[2018-10-14] . https:/arxiv.org/pdf/1406.4773.pdf https:/arxiv.org/pdf/1406.4773.pdf .
Sun Y, Wang X G, Tang X O.Deep learning face representation from predicting 10000 classes[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA: IEEE, 2014: 1891-1898.[ DOI: 10.1109/CVPR.2014.244 http://dx.doi.org/10.1109/CVPR.2014.244 ]
Sun Y, Wang X G, Tang X O. Deeply learned face representations are sparse, selective, and robust[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: IEEE, 2015.[ DOI: 10.1109/CVPR.2015.7298907 http://dx.doi.org/10.1109/CVPR.2015.7298907 ]
Taigman Y, Yang M, Ranzato M A, et al. DeepFace: closing the gap to human-level performance in face verification[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA: IEEE, 2014.[ DOI: 10.1109/CVPR.2014.220 http://dx.doi.org/10.1109/CVPR.2014.220 ]
Schroff F, Kalenichenko D, Philbin J. FaceNet: a unified embedding for face recognition and clustering[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: IEEE, 2015.[ DOI: 10.1109/CVPR.2015.7298682 http://dx.doi.org/10.1109/CVPR.2015.7298682 ]
Zhu Z Y, Luo P, Wang X G, et al. Deep learning identity-preserving face space[C]//Proceedings of 2013 IEEE International Conference on Computer Vision. Sydney, NSW, Australia: IEEE, 2013.[ DOI: 10.1109/ICCV.2013.21 http://dx.doi.org/10.1109/ICCV.2013.21 ]
Ramaiah N P, Ijjina E P, Mohan C K.Illumination invariant face recognition using convolutional neural networks[C]//Proceedings of 2015 IEEE International Conference on Signal Processing, Informatics, Communication and Energy Systems. Kozhikode, India: IEEE, 2015.[ DOI: 10.1109/SPICES.2015.7091490 http://dx.doi.org/10.1109/SPICES.2015.7091490 ]
Chiachia G, FalcãoAX, Pinto N, et al.Learning person-specific representations from faces in the wild[J]. IEEE Transactions on Information Forensics and Security, 2014, 9(12):2089-2099.[DOI:10.1109/TIFS.2014.2359543]
Wen Y D, Zhang K P, Li Z F, et al.A discriminative feature learning approach for deep face recognition[C]//Proceedings of the 14th European Conference on Computer Vision.Amsterdam, The Netherlands: Springer, 2016: 499-515.[ DOI: 10.1007/978-3-319-46478-7_31 http://dx.doi.org/10.1007/978-3-319-46478-7_31 ]
AbdAlmageed W, Wu Y, Rawls S, et al.Face recognition using deep multi-pose representations[C]//Proceedings of 2016 IEEE Winter Conference on Applications of Computer Vision. Lake Placid, NY, USA: IEEE, 2016: 1-9.[ DOI: 10.1109/WACV.2016.7477555 http://dx.doi.org/10.1109/WACV.2016.7477555 ]
Masi I, Rawls S, Medioni G, et al. Pose-aware face recognition in the wild[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016.[ DOI: 10.1109/CVPR.2016.523 http://dx.doi.org/10.1109/CVPR.2016.523 ]
Minaee S, Abdolrashidi A, Wang Y.An experimental study of deep convolutional features for iris recognition[C]//Proceedings of 2016 IEEE Signal Processing in Medicine and Biology Symposium. Philadelphia, PA, USA: IEEE, 2016.[ DOI: 10.1109/SPMB.2016.7846859 http://dx.doi.org/10.1109/SPMB.2016.7846859 ]
Liu N F, Zhang M, Li H Q, et al.DeepIris:learning pairwise filter bank for heterogeneous iris verification[J]. Pattern Recognition Letters, 2016, 82:154-161.[DOI:10.1016/j.patrec.2015.09.016]
Gangwar A, Joshi A. DeepIrisNet: deep iris representation with applications in iris recognition and cross-sensor iris recognition[C]//Proceedings of 2016 IEEE International Conference on Image Processing. Phoenix, AZ, USA: IEEE, 2016.[ DOI: 10.1109/ICIP.2016.7532769 http://dx.doi.org/10.1109/ICIP.2016.7532769 ]
Raja K B, Raghavendra R, Vemuri V K, et al.Smartphone based visible iris recognition using deep sparse filtering[J]. Pattern Recognition Letters, 2015, 57:33-42.[DOI:10.1016/j.patrec.2014.09.006]
Zhang Q, Li H Q, Sun Z N, et al. Exploringcomplementary features for iris recognition on mobile devices[C]//Proceedings of 2016International Conference on Biometrics. Halmstad, Sweden: IEEE, 2016.[ DOI: 10.1109/ICB.2016.7550079 http://dx.doi.org/10.1109/ICB.2016.7550079 ]
Jiang L, Zhao T, Bai C C, et al. A direct fingerprint minutiae extraction approach based on convolutional neural networks[C]//Proceedings of 2016 International Joint Conference on Neural Networks. Vancouver BC, Canada: IEEE, 2016.[ DOI: 10.1109/IJCNN.2016.7727251 http://dx.doi.org/10.1109/IJCNN.2016.7727251 ]
Su H R, Chen K Y, Wong W J, et al. A deep learning approach towards pore extraction for high-resolution fingerprint recognition[C]//Proceedings of 2017 IEEE International Conference on Acoustics, Speechand Signal Processing.New Orleans, LA, USA: IEEE, 2017.[ DOI: 10.1109/ICASSP.2017.7952518 http://dx.doi.org/10.1109/ICASSP.2017.7952518 ]
Cao K, Jain A K.Automated latent fingerprint recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 41(4):788-800.[DOI:10.1109/TPAMI.2018.2818162]
Jalali A, Mallipeddi R, Lee M. Deformation invariant and contactless palmprint recognition using convolutional neural network[C]//Proceedings of the 3rd International Conference on Human-Agent Interaction. Daegu, Kyungpook, Republic of Korea: ACM, 2015.[ DOI: 10.1145/2814940.2814977 http://dx.doi.org/10.1145/2814940.2814977 ]
Zhao D D, Pan X, Luo X L, et al.Palmprint recognition based on deep learning[C]//Proceedings of the 6th International Conference on Wireless, Mobile and Multi-Media. Beijing, China: IET, 2015: 214-216.[ DOI: 10.1049/cp.2015.0942 http://dx.doi.org/10.1049/cp.2015.0942 ]
Minaee S, Wang Y.Palmprint recognition using deep scattering convolutional network[EB/OL].[2018-10-14] . https://arxiv.org/pdf/1603.09027.pdf https://arxiv.org/pdf/1603.09027.pdf .
Liu D, Sun D M. Contactless palmprint recognition based on convolutional neural network[C]//Proceedings of the 13th IEEE International Conference on Signal Processing. Chengdu, China: IEEE, 2016.[ DOI: 10.1109/ICSP.2016.7878049 http://dx.doi.org/10.1109/ICSP.2016.7878049 ]
Svoboda J, Masci J, Bronstein M M, et al. Palmprint recognition via discriminative index learning[C]//Proceedings of the 23rd International Conference on Pattern Recognition. Cancun, Mexico: IEEE, 2016.[ DOI: 10.1109/ICPR.2016.7900298 http://dx.doi.org/10.1109/ICPR.2016.7900298 ]
Yang A Q, Zhang J X, Sun Q L, et al.Palmprint recognition based on CNN and local coding features[C]//Proceedings of the 6th International Conference on Computer Science and Network Technology. Dalian, China: IEEE, 2017: 482-487.[ DOI: 10.1109/ICCSNT.2017.8343744 http://dx.doi.org/10.1109/ICCSNT.2017.8343744 ]
Zhang L, Cheng Z X, Shen Y, et al.Palmprint and palmvein recognition based on DCNN and a new large-scale contactless palmvein dataset[J]. Symmetry, 2018, 10(4):#78.[DOI:10.3390/sym10040078]
Zhang D, Kong W K, You J, et al.Online palmprint identification[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(9):1041-1050.[DOI:10.1109/TPAMI.2003.1227981]
相关文章
相关作者
相关机构
京公网安备11010802024621
