中文

Operations Research Transactions >

2023 , Vol. 27 >Issue 4: 1 - 19

DOI: https://doi.org/10.15960/j.cnki.issn.1007-6093.2023.04.001

Fingerprint orientation field estimation algorithm based on deep learning

Expand
  • 1. College of Big Data Statistics, Guizhou University of Finance and Economics, Guiyang 550025, Guizhou, China
    2. School of Mathematical Sciences, University of Chinese Academy of Sciences, Beijing 100049, China
    3. Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing 100190, China

Received date: 2023-04-25

  Online published: 2023-12-07

Fold

Abstract

As a very important feature in fingerprint images, fingerprint orientation field plays an important role in many aspects of Automatic Fingerprint Identification System (AFIS), such as fingerprint image enhancement, singular point detection, fingerprint classification, etc. Although existing orientation field estimation algorithms can achieve competitive extraction results, these algorithms are sensitive to image noise and often require prior knowledge for direction calculation, which consumes a lot of time. To address this issue, a fingerprint orientation field estimation algorithm based on fully convolutional network is proposed in this paper, which uses pixel-level classification tasks to estimate fingerprint orientation field. According to the characteristics of fingerprint image and attention mechanism, we design a fully convolutional network with attention mechanism (Attention FCN) for orientation field estimation. In addition, dilated convolution layers are added to the network to extract important discriminative features in different fingerprint images. At the same time, a new loss function is designed to train the network. According to the classification results of each pixel point, the orientation field is estimated. Experimental results show that the proposed algorithm achieves good performance and very fast estimation speed, and it is very robust to image noise.

Key words： fingerprint orientation field estimation; deep learning; attention mechanism; fully convolutional network

Cite this article

Yonghong LIU, Congying HAN, Tiande GUO . Fingerprint orientation field estimation algorithm based on deep learning[J]. Operations Research Transactions, 2023 , 27(4) : 1 -19 . DOI: 10.15960/j.cnki.issn.1007-6093.2023.04.001

References

1 郭田德, 韩丛英, 赵彤, 等. 大库容量指纹自动识别系统中的优化模型与算法[J]. 运筹学学报, 2017, 21 (4): 19- 33.
2 Jagannath A , Jagannath J , Kumar P . A comprehensive survey on radio frequency (RF) fingerprinting: Traditional approaches, deep learning, and open challenges[J]. Computer Networks, 2022, 219, 109455.
3 Oliveira M A , Leite N J . A multiscale directional operator and morphological tools for reconnecting broken ridges in fingerprint images[J]. Pattern Recognition, 2008, 41 (1): 367- 377.
4 Ji L , Yi Z . Fingerprint orientation field estimation using ridge projection[J]. Pattern Analysis and Machine Intelligence, 2008, 41 (5): 1491- 1503.
5 Jain A K , Feng J . Latent palmprint matching[J]. Pattern Analysis and Machine Intelligence, 2009, 31 (6): 1032- 1047.
6 Cao K, Liang J, Tian J. A div-curl regularization model for fingerprint orientation extraction [C]// Proceedings of the International Conference on Biometrics: Theory, Applications and Systems, 2012: 231-236.
7 Feng J , Zhou J , Jain A K . Orientation field estimation for latent fingerprint enhancement[J]. Pattern Analysis and Machine Intelligence, 2013, 35 (4): 925- 940.
8 Kass M , Witkin A . Analyzing oriented patterns[J]. Computer Vision, Graphics, and Image Processing, 1987, 37 (3): 362- 385.
9 Bazen A M , Gerez S H . Systematic methods for the computation of directonal fields and sigular points of fingerprin[J]. Pattern Analysis and Machine Intelligence, 2003, 24 (7): 905- 919.
10 Sherlock B G , Monro D M . A model for interpreting fingerprint topology[J]. Pattern Recognition, 1993, 26 (7): 1047- 1055.
11 Sun R Y . Optimization for deep learning: an overview[J]. Journal of the Operations Research Society of China, 2020, 8 (2): 249- 294.
12 Montemanni R , Smith D H , Chou X . Maximum independent sets and supervised learning[J]. Journal of the Operations Research Society of China, 2023, 11, 957- 972.
13 Guo T D , Liu Y , Han C Y . An overview of stochastic quasi-newton methods for large-scale machine learning[J]. Journal of the Operations Research Society of China, 2023, 11 (2): 245- 275.
14 Zhao C , Li J , Lin M , et al. Ultrasonic guided wave inversion based on deep learning restoration for fingerprint recognition[J]. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2022, 69 (10): 2965- 2974.
15 Minaee S , Abdolrashidi A , Su H , et al. Biometrics recognition using deep learning: A survey[J]. Artificial Intelligence Review, 2023, 56, 8647- 8695.
16 Trabelsi S , Samai D , Dornaika F , et al. Efficient palmprint biometric identification systems using deep learning and feature selection methods[J]. Neural Computing and Applications, 2022, 34 (14): 12119- 12141.
17 Qin J, Han C, Bai C, et al. Multi-scaling detection of singular points based?on fully convolutional networks in fingerprint images [C]// Proceedings of the Chinese Conference on Biometric Recognition, 2017: 221-230.
18 Liu Y , Zhou B , Han C , et al. A method for singular points detection based on faster-rcnn[J]. Applied Sciences, 2018, 8 (10): 1853.
19 Chen J, Zhao H, Cao Z, et al. Singular points detection with semantic segmentation networks [J]. 2019, arXiv: 1911.01106.
20 Tang Y, Gao F, Feng J, et al. FingerNet: An unified deep network for fingerprint minutiae extraction [C]// Proceedings of the International Joint Conference on Biometrics, 2017: 108-116.
21 Darlow L N, Rosman B. Fingerprint minutiae extraction using deep learning [C]// Proceedings of the International Joint Conference on Biometrics, 2017: 22-30.
22 Nguyen D L, Cao K, Jain A K. Robust minutiae extractor: Integrating deep networks and fingerprint domain knowledge [C]// Proceedings of the International Conference on Biometrics, 2018: 9-16.
23 Zhou B , Han C , Liu Y , et al. Fast minutiae extractor using neural network[J]. Pattern Recognition, 2020, 103, 107273.
24 Li J , Feng J , Kuo C -C J . Deep convolutional neural network for latent fingerprint enhancement[J]. Signal Processing: Image Communication, 2018, 60, 52- 63.
25 Wong W J , Lai S H . Multi-task CNN for restoring corrupted fingerprint images[J]. Pattern Recognition, 2020, 101, 107203.
26 Liu Y , Zhou B , Han C , et al. A novel method based on deep learning for aligned fingerprints matching[J]. Applied Intelligence, 2019, 50 (2): 397- 416.
27 Tang S, Han C, Li M, et al. An end-to-end algorithm based on spatial transformer for fingerprint matching [C]// Proceedings of the International Conference on Computer and Communication Systems, 2022: 320-325.
28 Nguyen L T , Nguyen H T , Afanasiev A D , et al. Automatic identification fingerprint based on machine learning method[J]. Journal of the Operations Research Society of China, 2022, 10 (4): 849- 860.
29 Cao K, Jain A K. Latent orientation field estimation via convolutional neural network [C]// Proceedings of the International Conference on Biometrics, 2015: 349-356.
30 Lin L , Liu E , Wang L , et al. Fingerprint orientation field regularisation via multi-target regression[J]. Electronics Letters, 2016, 52 (13): 1118- 1120.
31 Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation [C]// Proceedings of the Conference on Computer Vision and Pattern Recognition, 2015: 3431-3440.
32 Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks [C]// Proceedings of the Advances in Neural Information Processing Systems, 2012: 1097-1105.
33 Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition [J]. 2014, arXiv: 1409.1556.
34 Lin T, Goyal P, Girshick R, et al. Focal loss for dense object detection [C]// Proceedings of the International Conference on Computer Vision, 2017: 2980-2988.
35 Stollenga M F, Masci J, Gomez F, et al. Deep networks with internal selective attention through feedback connections [C]// Proceedings of the Advances in Neural Information Processing Systems, 2014: 3545-3553.
36 Wang, F, Jiang M, Qian C, et al. Residual attention network for image classification [C]// Proceedings of the Conference on Computer Vision and Pattern Recognition, 2017: 3156-3164.
37 Woo S, Park J, Lee J, et al. CBAM: Convolutional block attention module [C]// Proceedings of the European Conference on Computer Vision, 2018: 3-19.
38 Keys R G . Cubic convolution interpolation for digital image processing[J]. Acoustics, Speech, and Signal Processing, 1981, 29 (6): 1153- 1160.
39 Wen Y, Zhang K, Li Z, et al. A discriminative feature learning approach for deep face recognition [C]// Proceedings of the European Conference on Computer Vision, 2016: 499-515.
40 Maio D, Maltoni D, Cappelli R, et al. Fvc2002: Second fingerprint verification competition [C]// Proceedings of the International Conference on Pattern Recognition, 2002: 811-814.
41 Maio D , Maltoni D , Cappelli R , et al. Fvc2004: Third fingerprint verification competition[J]. Lecture Notes in Computer Science, 2004, 3072 (2): 1- 7.
42 Abadi M, Agarwal A, Barham P, et al. TensorFlow: Large-scale machine learning on heterogeneous systems [J]. 2016, arXiv: 1605.08695.
43 Turroni F , Maltoni D , Cappelli R , et al. Improving fingerprint orientation extraction[J]. Information Forensics and Security, 2011, 6 (3): 1002- 1013.
44 Cao K , Pang L , Liang J , et al. Fingerprint classification by a hierarchical classifier[J]. Pattern Recognition, 2013, 46 (12): 3186- 3197.
Options
Outlines

/

〈 〉