轻量化多特征融合的指纹分类算法研究
|
摘要
快速准确的指纹分类在大型指纹识别系统中是加速目标指纹查找的关键技术。目前,指纹分类算法存在复杂度高、操作繁琐、参数较多、所需数据规模大、且无法充分利用指纹特征信息等问题。神经网络深层提取的特征更加关键,也更有代表性,但忽略了部分浅层信息。针对指纹分类存在的问题,本文提出一种轻量化多特征融合的指纹分类算法。该算法设计了轻量化Finger-SqueezeNet来训练指纹图像,采用查表法求得指纹的细化图之后,利用改进的分布求和梯度法求取相应细化图的感兴趣区域(Region Of Interest,ROI)图像;将指纹ROI图像输入网络深层与提取的特征图进行特征融合,使得深层网络也能获得浅层中纹线准确的走向信息,从而增强网络对于纹型的敏感度;采用Maxout激活函数对网络提取的特征进行激活。实验结果表明,本文算法不仅减少了训练参数量,而且通过指纹ROI图像补偿深层特征图,更加充分利用了指纹的纹型信息,轻量化算法也可为指纹分类模型拓展到移动端提供理论支撑。
It is the key technology for fast and accurate fingerprint classification to accelerate target fingerprint search in large fingerprint identification systems. There still exist some problems such as complex operation process, numerous parameters, large scale data and inadequate use of the fingerprint information. It's more critical and representative for the features to be extracted by the deep layer of neural networks, namely, some information in the shallow layer may be ignored. Therefore, in this paper, the lightweight multi-feature fusion fingerprint classification algorithm is presented. Firstly, the fingerprint images are trained by the lightweight Finger-SqueezeNet. Simultaneously, after the look-up-table method is used to obtain the refined map of the fingerprint, the improved distribution summation gradient method is used to get the Region Of Interest(ROI) image of the corresponding map, which is merged with the extracted feature map in the deep layer of the network. Since the deep network receives the accurate trend information of the fingerprint lines in the shallow layer, the sensitivity of the network to the pattern is enhanced. Finally, the Maxout activation function is used to activate the features extracted by the network. Experimental results show that the network structure of the five Finger-fire modules is optimal for fingerprint classification, and the network model after feature fusion can reach 96.81%. Moreover, the test result obtained by a single fingerprint test method reaches 94.57%. Compared with the same type and verification method, the fingerprint classification model in this paper can still obtain higher accuracy while greatly reducing network parameters. In addition, the classification of the whorl fingerprints has a good performance among the five categories, but the arch and the tented arch are relatively poor, which is because of the 17.5% fuzzy labels of these two classes fingerprint. It is worth mentioning that two kinds of fuzzy fingerprints haven't been mixed as one class to improve the result, nor any of them has been refused to be recognized, namely, it's 0 rejection rate. It can be seen from the final results that the model has strong generalization ability and high stability for the classification of fingerprint with different quality. The method can make full use of fingerprint information by compensation of the ROI image, and the lightweight algorithm provides theoretical support for the extension of the fingerprint classification model to the mobile end.
It is the key technology for fast and accurate fingerprint classification to accelerate target fingerprint search in large fingerprint identification systems. There still exist some problems such as complex operation process, numerous parameters, large scale data and inadequate use of the fingerprint information. It's more critical and representative for the features to be extracted by the deep layer of neural networks, namely, some information in the shallow layer may be ignored. Therefore, in this paper, the lightweight multi-feature fusion fingerprint classification algorithm is presented. Firstly, the fingerprint images are trained by the lightweight Finger-SqueezeNet. Simultaneously, after the look-up-table method is used to obtain the refined map of the fingerprint, the improved distribution summation gradient method is used to get the Region Of Interest(ROI) image of the corresponding map, which is merged with the extracted feature map in the deep layer of the network. Since the deep network receives the accurate trend information of the fingerprint lines in the shallow layer, the sensitivity of the network to the pattern is enhanced. Finally, the Maxout activation function is used to activate the features extracted by the network. Experimental results show that the network structure of the five Finger-fire modules is optimal for fingerprint classification, and the network model after feature fusion can reach 96.81%. Moreover, the test result obtained by a single fingerprint test method reaches 94.57%. Compared with the same type and verification method, the fingerprint classification model in this paper can still obtain higher accuracy while greatly reducing network parameters. In addition, the classification of the whorl fingerprints has a good performance among the five categories, but the arch and the tented arch are relatively poor, which is because of the 17.5% fuzzy labels of these two classes fingerprint. It is worth mentioning that two kinds of fuzzy fingerprints haven't been mixed as one class to improve the result, nor any of them has been refused to be recognized, namely, it's 0 rejection rate. It can be seen from the final results that the model has strong generalization ability and high stability for the classification of fingerprint with different quality. The method can make full use of fingerprint information by compensation of the ROI image, and the lightweight algorithm provides theoretical support for the extension of the fingerprint classification model to the mobile end.
引文
[1] Li Y K,Wu X J,Kittler J.L1-(2D) 2PCANet:A Deep Learning Network for Face Recognition[J].arXiv preprint arXiv:1805.10476,2018.
[2] Ren S,He K,Girshick R,et al.Faster r-cnn:Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems,2015:91-99.
[3] Peralta D,Triguero I,García,et al.On the use of convolutional neural networks for robust classification of multiple fingerprint captures[J].International Journal of Intelligent Systems,2018,33(1):213-230.
[4] Schuch P,Schulz S D,Busch C.Deep expectation for estimation of fingerprint orientation fields[C]//Biometrics(IJCB),IEEE International Joint Conference on.IEEE,2017:185-190.
[5] Ding S,Bian W,Liao H,et al.Combining gabor filtering and classification dictionaries learning for fingerprint enhancement[J].Iet Biometrics,2017,6(6):438- 447.
[6] Minaee S,Wang Y.Fingerprint recognition using translation invariant scattering network[C]//Signal Processing in Medicine and Biology Symposium(SPMB),IEEE,2015:1- 6.
[7] Shrein J M.Fingerprint classification using convolutional neural networks and ridge orientation images[C]//Computational Intelligence(SSCI),IEEE Symposium Series on.IEEE,2017:1- 8.
[8] Wang R,Han C,Guo T.A novel fingerprint classification method based on deep learning[C]//International Conference on Pattern Recognition.IEEE,2017:931-936.
[9] Nogueira R F,Lotufo R D A,Machado R C.Fingerprint Liveness Detection Using Convolutional Neural Networks[J].IEEE Transactions on Information Forensics & Security,2017,11(6):1206-1213.
[10] Michelsanti D,Ene A D,Guichi Y,et al.Fast Fingerprint Classification with Deep Neural Networks[C]//International Conference on Computer Vision Theory and Applications,2017:202-209.
[11] Sha L,Tang X.Combining exclusive and continuous fingerprint classification[C]//Image Processing.ICIP’04.International Conference on.IEEE,2004,2:1245-1248.
[12] Park C H,Park H.Fingerprint classification using fast Fourier transform and nonlinear discriminant analysis[J].Pattern Recognition,2005,38(4):495-503.
[13] Li J,Yau W Y,Wang H.Combining singular points and orientation image information for fingerprint classification[J].Pattern Recognition,2008,41(1):353-366.
[14] Iandola F N,Han S,Moskewicz M W,et al.Squeezenet:Alexnet-level accuracy with 50x fewer parameters and <0.5 MB model size[J].arXiv preprint arXiv:1602.07360,2016.
[15] Goodfellow I J,Warde-Farley D,Mirza M,et al.Maxout Networks[J].Computer Science,2013:1319-1327.
[16] Akram M U,Nasir S,Tariq A,et al.Improved fingerprint image segmentation using new modified gradient based technique[C]//Electrical and Computer Engineering,2008.CCECE 2008.Canadian Conference on.IEEE,2008:001967- 001972.
[17] Wilson C L,Candela G T,Watson C I.Neural network fingerprint classification[J].Journal of Artificial Neural Networks,1994,1(2):203-228.
[18] Holden D,Saito J,Komura T.A deep learning framework for character motion synthesis and editing[J].ACM Transactions on Graphics,2016,35(4):1-11.
[2] Ren S,He K,Girshick R,et al.Faster r-cnn:Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems,2015:91-99.
[3] Peralta D,Triguero I,García,et al.On the use of convolutional neural networks for robust classification of multiple fingerprint captures[J].International Journal of Intelligent Systems,2018,33(1):213-230.
[4] Schuch P,Schulz S D,Busch C.Deep expectation for estimation of fingerprint orientation fields[C]//Biometrics(IJCB),IEEE International Joint Conference on.IEEE,2017:185-190.
[5] Ding S,Bian W,Liao H,et al.Combining gabor filtering and classification dictionaries learning for fingerprint enhancement[J].Iet Biometrics,2017,6(6):438- 447.
[6] Minaee S,Wang Y.Fingerprint recognition using translation invariant scattering network[C]//Signal Processing in Medicine and Biology Symposium(SPMB),IEEE,2015:1- 6.
[7] Shrein J M.Fingerprint classification using convolutional neural networks and ridge orientation images[C]//Computational Intelligence(SSCI),IEEE Symposium Series on.IEEE,2017:1- 8.
[8] Wang R,Han C,Guo T.A novel fingerprint classification method based on deep learning[C]//International Conference on Pattern Recognition.IEEE,2017:931-936.
[9] Nogueira R F,Lotufo R D A,Machado R C.Fingerprint Liveness Detection Using Convolutional Neural Networks[J].IEEE Transactions on Information Forensics & Security,2017,11(6):1206-1213.
[10] Michelsanti D,Ene A D,Guichi Y,et al.Fast Fingerprint Classification with Deep Neural Networks[C]//International Conference on Computer Vision Theory and Applications,2017:202-209.
[11] Sha L,Tang X.Combining exclusive and continuous fingerprint classification[C]//Image Processing.ICIP’04.International Conference on.IEEE,2004,2:1245-1248.
[12] Park C H,Park H.Fingerprint classification using fast Fourier transform and nonlinear discriminant analysis[J].Pattern Recognition,2005,38(4):495-503.
[13] Li J,Yau W Y,Wang H.Combining singular points and orientation image information for fingerprint classification[J].Pattern Recognition,2008,41(1):353-366.
[14] Iandola F N,Han S,Moskewicz M W,et al.Squeezenet:Alexnet-level accuracy with 50x fewer parameters and <0.5 MB model size[J].arXiv preprint arXiv:1602.07360,2016.
[15] Goodfellow I J,Warde-Farley D,Mirza M,et al.Maxout Networks[J].Computer Science,2013:1319-1327.
[16] Akram M U,Nasir S,Tariq A,et al.Improved fingerprint image segmentation using new modified gradient based technique[C]//Electrical and Computer Engineering,2008.CCECE 2008.Canadian Conference on.IEEE,2008:001967- 001972.
[17] Wilson C L,Candela G T,Watson C I.Neural network fingerprint classification[J].Journal of Artificial Neural Networks,1994,1(2):203-228.
[18] Holden D,Saito J,Komura T.A deep learning framework for character motion synthesis and editing[J].ACM Transactions on Graphics,2016,35(4):1-11.