基于深度學(xué)習(xí)的污損指紋識別研究

吳震東; 王雅妮; 章堅武

doi:10.11999/JEIT161121

基于深度學(xué)習(xí)的污損指紋識別研究

doi: 10.11999/JEIT161121

1.
(杭州電子科技大學(xué)網(wǎng)絡(luò)空間安全學(xué)院杭州 310018) ②(杭州電子科技大學(xué)通信工程學(xué)院杭州 310018)

基金項目:

國家重點研發(fā)計劃(2016YFB0800201)，浙江省自然科學(xué)基金(LY16F020016)，浙江省重點科技創(chuàng)新團(tuán)隊項目(2013TD03)

計量
- 文章訪問數(shù): 2033
- HTML全文瀏覽量: 258
- PDF下載量: 1138
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-10-21
- 修回日期: 2017-04-01
- 刊出日期: 2017-07-19

Fouling and Damaged Fingerprint Recognition Based on Deep Learning

1.
(School of Cyberspace, Hangzhou Dianzi University, Hangzhou 310018, China)
2.
(School of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, China)

Funds:

The National Key Research and Development Program of China (2016YFB0800201), The Natural Science Fundation of Zhejiang Province (LY16F020016), Zhejiang Provincial Science and Technology Innovation Program (2013TD03)

摘要

摘要: 隨著社會信息化水平的提高及不穩(wěn)定因素的增加，人們迫切需要更加可靠的識別技術(shù)對身份進(jìn)行認(rèn)證。因此，利用生物特征進(jìn)行鑒定已成為時下熱潮。其中的指紋識別更是因其方便性和可靠性受到普遍認(rèn)同。傳統(tǒng)的指紋識別方法基于特征點比對尋求相似性，此種方法特征點尋找容易出錯，且隨著指紋的模糊、破壞、污損或是其他問題，均會使識別率明顯降低。針對這些問題，該文提出基于深度卷積神經(jīng)網(wǎng)絡(luò)(CNN)的CBF-FFPF(Central Block Fingerprint and Fuzzy Feature Points Fingerprint)算法對污損指紋圖像進(jìn)行分類識別。CBF-FFPF算法提取指紋中心點分塊圖像及特征點模糊化圖，合并后輸入CNN網(wǎng)絡(luò)，進(jìn)行指紋深層特征識別。將該算法與基于主成分分析(KPCA)，超限學(xué)習(xí)機(jī)(ELM)和k近鄰分類器(KNN)的指紋識別算法進(jìn)行比較，實驗結(jié)果表明，所提出的CBF-FFPF算法對污損指紋識別有更高的識別率和更好的魯棒性。
- 指紋識別 /
- 卷積神經(jīng)網(wǎng)絡(luò) /
- 分塊指紋 /
- 指紋深層特征
Abstract: With the development of information technology and the increasing demanding of information security, people are urgently in need of more reliable identification techniques for identity authentication. Therefore, the biometric recognition methods have become a compelling issue. Among the methods, the fingerprint identification technique attracts much interest due to its excellent feasibility and reliability performance. The traditional fingerprint recognition method is based on matching feature points. However, this method needs a long time to find the feature points, and suffering the blur, scaling, damage, and other problems, the recognition rate is decreased seriously. To solve these problems, a fouling and damaged fingerprint recognition algorithm named CBF-FFPF (Central Block Fingerprint and Fuzzy Feature Points Fingerprint) is proposed, it is based on Convolution Neural Network (CNN) of deep learning. Combining small sub block fingerprint, which takes the fingerprint core point as the center from the thinned image and fuzzy graph of fingerprint feature points, as original image input to obtain the recognition rate. The recognition rate based on CBF-FFPF is compared with the fingerprint identification algorithm based on Kernel Principal Component Analysis (KPCA), Extreme Learning Machine (ELM), and K-Nearest Neighbor (KNN). Experimental results show that fingerprint recognition algorithm CBF- FFPF has higher recognition rate and better robustness.
- Fingerprint identification /
- Convolution Neural Network (CNN) /
- Sub block fingerprint /
- Fingerprint deep character

HTML全文

參考文獻(xiàn)(18)

HAGHIGHAT M, ZONOUZ S, and ABDEL-MOTTALEB M. CloudID: Trustworthy cloud-based and cross-enterprise biometric identification[J]. Expert Systems with Applications, 2015, 42(21): 7905-7916. doi: 10.1016/j.eswa.2015.06.025.

JAIN A K, FENG J J, and NANDAKUMAR K. Fingerprint matching[J]. Computer, 2010, 43(2): 36-44. doi: 10.1109/MC. 2010.38.

LIU Eryun, ZHAO Heng, LIANG Jimin, et al. Random local region descriptor (RLRD): A new method for fixed-length feature representation of fingerprint image and its application to template protection[J]. Future Generation Computer Systems, 2012, 28(1): 236-243. doi: 10.1016/j.future.2011.01. 001.

PAULINO A A, FENG J J, and JAIN A K. Latent fingerprint matching using descriptor-based hough transform [J]. IEEE Transactions on Information Forensics and Security, 2011, 8(1): 31-45. doi: 10.1109/IJCB.2011.6117483.

FENG J J, ZHOU J, and JAIN A K. Orientation field estimation for latent fingerprint enhancement[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(4): 925-940.

KRISH R P, FIERREZ J, RAMOS D, et al. Pre-registration for improved latent fingerprint identification[C]. International Conference on Pattern Recognition, Stockholm, Sweden, 2014: 696-701. doi: 10.1109/ICPR.2014.130.

FANG B, WEN H, LIU R Z, et al. A new fingerprint thinning algorithm[C]. 2010 Chinese Conference on Pattern Recognition (CCPR), Changsha, China, 2010: 1-4. doi: 10.1109/CCPR.2010.5659273.

KRIZHEVSKY A, SUTSKEVER I, and HINTON G. ImageNet classification with deep convolutional neural networks[C]. Proceedings of the 25th International Conference on Neural Information Processing Systems, Lake Tahoe, Nevada, USA, 2012: 1097-1105.

HINTON G and OSINDERO S. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554. doi: 10.1162/neco.2006.18.7.1527.

SAINATH T N, KINGSBURY B, SAON G, et al. Deep convolutional neural networks for large-scale speech tasks[J]. Neural Networks, 2015, 64(4): 39-48. doi: 10.1016/j.neunet. 2014.08.005.

LAVIN A. maxDNN: An efficient convolution kernel for deep learning with maxwell GPUs[OL]. https://arxiv.org/abs/ 1501.06633, 2015.

ARPIT D and NAMBOODIRI A. Fingerprint feature extraction from gray scale images by ridge tracing[C]. International Joint Conference on Biometrics, Washington DC, USA, 2011: 1-8. doi: 10.1109/IJCB.2011.6117533.

CHANG C C, HWANG S M, and BUEHRER D J. A shape recognition scheme based on relative distances of feature points from the centroid[J]. Pattern Recognition, 1991, 24(11): 1053-1063. doi: 10.1016/0031-3203(91)90121-K.

IWASOKUN G B and AKINYOKUN O C. Fingerprint singular point detection based on modified poincare index method[J]. International Journal of Signal Processing Image Processing Pattern Recognition, 2014, 7(5): 259-272. doi: 10.14257/ijsip.2014.7.5.23.

KUMAR R, HANMANDLU M, and CHANDRA P. An empirical evaluation of rotation invariance of LDP feature for fingerprint matching using neural networks[J]. International Journal of Computational Vision Robotics, 2014, 4(4): 330-348. doi: 10.1504/IJCVR.2014.065569.

WANG R, HAN C, WU Y, et al. Fingerprint classification based on depth neural network[OL]. https:// arxiv.org/abs/ 1409.5188,2014.

KANAAN L, MERHEB D, KALLAS M, et al. PCA and KPCA of ECG signals with binary SVM classification[C]. IEEE Workshop on Signal Processing Systems, Beirut, Lebanon, 2011: 344-348. doi: 10.1109/SiPS.2011.6089000.

HUANG G B, ZHU Q Y, and SIEW C K. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501. doi: 10.1016/j.neucom.2005.12.126.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計