Enhancing the Latent Fingerprint Segmentation Accuracy Using Hybrid Techniques – WCO and BiLSTM

Enhancing the Latent Fingerprint Segmentation Accuracy Using Hybrid Techniques – WCO and BiLSTM

© 2021 by IJETT Journal
Volume-69 Issue-11
Year of Publication : 2021
Authors : Neha Chaudhary, Priti Dimri
DOI :  10.14445/22315381/IJETT-V69I11P221

How to Cite?

Neha Chaudhary, Priti Dimri, "Enhancing the Latent Fingerprint Segmentation Accuracy Using Hybrid Techniques – WCO and BiLSTM," International Journal of Engineering Trends and Technology, vol. 69, no. 11, pp. 161-169, 2021. Crossref, https://doi.org/10.14445/22315381/IJETT-V69I11P221

For more than a century, latent fingerprints have been effectively utilized to identify criminal defendants by matching the latent fingerprints to the rolled or plain fingerprints saved in the dataset. Background noise, overlapping patterns, unclear structures, partial impressions, and non-linear distortions of the finger are the key issues with latent fingerprints. Segmentation is one of the procedures that must be completed before identification. Traditional segmentation methods perform badly on latent fingerprints. The focus of this research has primarily been on the automatic segmentation of latent fingerprints. First, the latent fingerprint images are divided into local blocks. Then, feature vectors are constructed by extracting the features from the local blocks using the ridge, intensity, and gradient method. Extracted feature vectors are fed as input of bidirectional long short-term memory network (BiLSTM). The BiLSTM is utilized for segmentation with world cup optimization for weight update. The proposed algorithm`s performance is compared with the previously known results of the latent fingerprint segmentation techniques. The segmentation accuracy of latent fingerprints is 92.9% which has greatly been improved, and it is quite promising than the earlier algorithms.

Segmentation, latent fingerprint, ridge features, bidirectional long short-term memory network.

[1] Champod, C. Lennard, P. Margot, and M. Stoilovic, Fingerprints and Other Ridge Skin Impressions. CRC Press, (2004).
[2] S. A. Cole, Suspect Identities: A History of Fingerprinting and Criminal Identification. Harvard University Press, (2002).
[3] Jain, A. K., & Feng, J., Latent fingerprint matching. IEEE Transactions on pattern analysis and machine intelligence.33 (1) (2010) 88-100.222
[4] Mehtre, B. M., Murthy, N. N., Kapoor, S., & Chatterjee, B., Segmentation of fingerprint images using the directional image. Pattern recognition.20(4) (1987) 429-435.
[5] Mehtre, B. M., & Chatterjee, B., Segmentation of fingerprint images—a composite method. Pattern recognition, 22(4) (1989) 381-38
[6] Ratha, N. K., Chen, S., & Jain, A. K., Adaptive flow orientation-based feature extraction in fingerprint images. Pattern Recognition, 28(11) (1995) 1657-1672.
[7] Bazen, A. M., & Gerez, S. H., Segmentation of fingerprint images. In ProRISC 2001 Workshop on Circuits, Systems and Signal Processing (2001)276-280.
[8] Xue, J., & Li, H., Fingerprint image segmentation based on a combined method. In 2012 IEEE International Conference on Virtual Environments Human-Computer Interfaces and Measurement Systems (VECIMS) Proceedings IEEE. (2012) 207-208
[9] Zhang, J., Lai, R., & Kuo, C. C. J., Latent fingerprint segmentation with adaptive total variation model. In 2012 5th IAPR International Conference on Biometrics (ICB) IEEE. (2012)189-195
[10] Zhang, J., Lai, R., & Kuo, C. C. J. (2012, September). Latent fingerprint detection and segmentation with a directional total variation model. In 2012 19th IEEE International Conference on Image Processing IEEE.(2012)1145-1148
[11] Zhang, J., Lai, R., & Kuo, C. C. J., Adaptive directional total-variation model for latent fingerprint segmentation. IEEE Transactions on Information Forensics and Security. 8(8)(2013)1261-1273.
[12] Choi, H., Boaventura, M., Boaventura, I. A., & Jain, A. K., Automatic segmentation of latent fingerprints. In 2012 IEEE Fifth International Conference on Biometrics: Theory, Applications and Systems (BTAS) IEEE.(2012)303-310
[13] Short, N. J., Hsiao, M. S., Abbott, A. L., & Fox, E. A., Latent fingerprint segmentation using ridge template correlation. In 4th International Conference on Imaging for Crime Detection and Prevention IET.(2011)1-6
[14] Cao, K., Liu, E., & Jain, A. K., Segmentation and enhancement of latent fingerprints: A coarse to fine ridge structure dictionary. IEEE transactions on pattern analysis and machine intelligence.36(9)(2014)1847-1859.
[15] Sankaran, A., Jain, A., Vashisth, T., Vatsa, M., & Singh, R. (2017). Adaptive latent fingerprint segmentation using feature selection and random decision forest classification. Information Fusion.34 (2017) 1-15.
[16] Stojanovi?, B., & Marques, O., Machine Learning Based Overlapped Latent Fingerprints Segmentation and Separation. In 2018 26th Telecommunications Forum (TELFOR)IEEE.(2018)1-8
[17] Jain, A. K., & Feng, J., Latent fingerprint matching. IEEE Transactions on pattern analysis and machine intelligence, 33(1) (2010) 88-100.
[18] Bazen, A. M., & Gerez, S. H, Segmentation of fingerprint images. In ProRISC 2001 Workshop on Circuits, Systems and Signal Processing ,Veldhoven, The Netherlands.(2001) 276-280.
[19] Maltoni, D., Maio, D., Jain, A. K., & Prabhakar, S., Handbook of fingerprint recognition. Springer Science & Business Media. (2009)
[20] NIST, NFIQ 2.0, Quality features definition, http://biometrics.nist.gov/cs_links/quality/NFIQ_2/NFIQ-2_ Quality_Feature_Defin-Ver05.pdf.
[21] E. Zhu, J. Yin, C. Hu, G. Zhang, A systematic method for fingerprint ridge orientation estimation and image segmentation, Pattern Recognition.39(8)(2006)1452–1472.
[22] Chen, X., Tian, J., Cheng, J., & Yang, X., Segmentation of fingerprint images using a linear classifier. EURASIP Journal on Advances in Signal Processing.2(4)(2004)1-15.
[23] Chikkerur, S., Govindaraju, V., & Cartwright, A. N., Fingerprint image enhancement using STFT analysis. In International Conference on Pattern Recognition and Image Analysis Springer, Berlin, Heidelberg. (2005) 20-29.
[24] Chin, Y. J., Ong, T. S., Teoh, A. B. J., & Goh, K. O. M., Integrated biometrics template protection technique based on fingerprint and palmprint feature-level fusion. Information Fusion.18 (2014) 161-174.
[25] Elfaik, H. Deep Bidirectional LSTM Network Learning-Based Sentiment Analysis for Arabic Text. Journal of Intelligent Systems. 30(1)(2021) 395-412.
[26] Liu, Q., Zhou, F., Hang, R., & Yuan, X, Bidirectional-convolutional LSTM based spectral-spatial feature learning for hyperspectral image classification. Remote Sensing. 9(12)(2017)1330.
[27] Chaudhary, N., Singh, H. P., & Dimri, P., Comparative Study of Latent Fingerprint Image Segmentation Techniques Based on Literature Review. Ambient Communications and Computer Systems. (2020) 391-399.
[28] Khan, A. I., & Wani, M. A., Patch-based segmentation of latent fingerprint images using convolutional neural network. Applied Artificial Intelligence. 33(1) (2019) 87-100.
[29] Razmjooy, N., Estrela, V. V., & Loschi, H. J, Entropy-based breast cancer detection in digital mammograms using world cup optimization algorithm. International Journal of Swarm Intelligence Research (IJSIR).11(3)(2020) 1-18.
[30] Chaudhary, N., & Dimri, P., Singh, H. P., Segmentation of Latent Fingerprint using Neural Network. International Journal of Engineering and Advanced Technology. 9(1)(2019)3777-3780.
[31] Yildirim, Ö. A novel wavelet sequence based on a deep bidirectional LSTM network model for ECG signal classification. Computers in biology and medicine.96 (2018) 189-202.