An Overview of Live Detection Techniques to Secure Fingerprint Recognition System from Spoofing Attacks

London Journal of Research in Computer Science and Technology
Volume | Issue | Compilation
Authored by Munish Kumar , Dr. Priyanka
Classification: K.6.5
Keywords: FPR, BMR, Spoofing Attacks, live detect.
Language: English

Due to unique characteristics and permanence of fingerprints, Fingerprint Recognition (FPR) Systems has been extensively employed in security, identification, and verification of a person in forensic and commercial applications. External attacks or spoofing attacks are among the main challenges in using FPR systems. Spoofing means to make the system fool by producing fake finger as a real one to the fingerprint sensor. So, there is a need to develop efficient techniques to distinguish between fake and real fingers against these attacks, so that FPR systems can be secured. These types of attacks can be identified by measuring life signs and live detection techniques together with FPR techniques. This paper presents a brief review of work carried out in the field of live detection in FPR systems with various spoofing and anti-spoofing techniques. To make FPR systems more reliable, secure & efficient, it is necessary to detect and protect the system against any unpredictable spoofing attacks.

               

An Overview of Live Detection Techniques to Secure Fingerprint Recognition System from Spoofing Attacks

Munish Kumarα & Dr. Priyankaσ

____________________________________________

  1. ABSTRACT

Due to unique characteristics and permanence of fingerprints, Fingerprint Recognition (FPR) Systems has been extensively employed in security, identification, and verification of a person in forensic and commercial applications. External attacks or spoofing attacks are among the main challenges in using FPR systems. Spoofing means to make the system fool by producing fake finger as a real one to the fingerprint sensor. So, there is a need to develop efficient techniques to distinguish between fake and real fingers against these attacks, so that FPR systems can be secured. These types of attacks can be identified by measuring life signs and live detection techniques together with FPR techniques. This paper presents a brief review of work carried out in the field of live detection in FPR systems with various spoofing and anti-spoofing techniques. To make FPR systems more reliable, secure & efficient, it is necessary to detect and protect the system against any unpredictable spoofing attacks.

Author α σ: ECE Department, D.C.R. University of Sciences & Technology, Murthal.

Keywords:  FPR, BMR, Spoofing Attacks, live detect.

  1. INTRODUCTION

In the present scenario there are various applications in which protection of sensitive data, services or facilities from illegal access is required this is usually achieved by some type of security means like password, card, key, PIN (Personal Identification Number) and biometric identification. The objective of using any one of these security means that the system is accessed by an only legal person or user [1]. The password, card, key, and PIN can protect the system against fraudulent access, but they can be cracked or guessed by hackers. Sometimes the single password or PIN is employed for access to multiple resources. If one can crack or guess that password or PIN, then all the resources can be easily accessed by an unauthorized person. Thus there is a necessity of more secure and reliable techniques to protect resources from fraudulent access.

To overcome the limitations of these recognition techniques means Biometrics Recognition (BMR) System started to find applications in security systems [2]. BMR systems use human characteristics for authentication purpose to the system and they can’t be stolen easily and don’t require any password to remember by the user. Biometric systems work on the human unique characteristics that are a fingerprint, voice, palm geometry, face, signature, and iris etc [3-6].

Fingerprint Recognition (FPR) systems are preferred over all the BMR systems used for authentication in personal and commercial applications due to their reliability and uniqueness in nature. Though the biometrics information can’t be easily stolen, forget or lost; but due to advancement in technology one can access the system by fake identity made from a real one using various methods. BMR systems are more accurate and secure than all traditional security methods but also have various vulnerabilities that make the system less secure [7-8].

Biometrics systems are affected by various types of attacks at different levels. These attacks may be at the sensor level, replay attack, feature level, tempering stored template, matching process & matching score level, attacking the channel at a different level and overriding the final decision etc. [9]. Among all the vulnerabilities, spoofing or direct attacks have been considering for the present study. These types of attacks are also known as presentation attacks because in these attacks a fake identity of the genuine user is presented to the sensor for accessing the system. This paper focuses on the sensor level attacks, which affect the system easily without knowing the internal structure of the system.

These attacks are done by presenting fake fingerprints to the sensor for authentication purposes. An unauthorized person uses fake fingerprints are made from the impression of a real finger on artificial materials such as plastic, clay, play-doh, putty, paraffin wax, silicon, and gelatin material to access the system with this fake fingerprint. To avoid these types of attacks and to ensure right person at a right place one needs to use live detection techniques in the FPR system [10]. In this study, consideration of the different types of sensor level spoofing attacks and their detection techniques have been discussed and compared. In section II brief study about various types of attacks are discussed. Section III depicts different live detection techniques. Section IV gives a comparative study of work carried out by researchers in this area. In section V the study has been concluded.

  1. SPOOFING ATTACKS IN FRS

Researchers have shown that one can easily spoof the FPR system [11], which means a false acceptance of user by using fake evidence to the FPR or biometric system. By spoofing the FPR system an unauthorized person can access the system and manipulate the data or information without knowing to an authorized user. One can manipulate the data or information in FPR system by two form of attacks as shown in fig.1 [12]. Direct attacks are performed at first stage of FPR system i.e. at sensor by making a fake finger from real one and these attacks are also known as spoofing or presentation attacks. Hence these are found outside the digital limit of FPR systems. In indirect attacks manipulation of digital information i.e. features, database, channel & score etc. is done at various stages of FPR system by the specialized hackers to illegally access the system.

Fig. 1: Attacks in FPR System

Spoofing attacks are more popular because there is no need of any technical knowledge about the internal structure of the FPR system. These attacks are performed by making an artificial mold or fake finger of a real finger with cooperation or without the cooperation of user. There are two categories by which fake fingerprints are created [13]:

  1. With the cooperation of person – directly created from the real finger.
  2. Without the cooperation of person – created from dead fingerprints.

In ‘with cooperation’ the user itself provided his/ her finger for generating fake finger or impression so these prints are made with cooperation of user from live finger and in ‘without cooperation’ fake finger or impression are generated from dead finger, so these prints are made from without cooperation of user i.e. latent fingerprint, fingerprint reactivation, fingerprint synthesis, and cadaver.

The main attention is carried on fake finger attacks. These attacks have been implemented by employing fake finger to the sensor made from an impression of real one. There are several categories from which fake fingerprint can be produced. Various materials incorporated for fake fingerprint are plastic print, clay print, Play-Doh print, silicon mold, gelatin material, print photo, ink print and mikrosil mold etc. According to the input data, there is various process by which fake fingerprints are created as shown in fig.2.

Fig. 2: Various Spoofing Methods

In fig. 3 basic block diagram of FPR system is shown with different types of attacks at different stages/level by which one can affect the system or spoofing the system with a fake identity.

 

Fig. 3: Showing attacks in FPR system at different stages

Based on the literature survey any person can generate a fake fingerprint and easily spoof the FPR system. Thus, to avoid spoofing attacks, live detection techniques must be incorporated into the system [14-17].

  1. LIVE DETECTION TECHNIQUES IN FPR SYSTEM

Live detection in FPR system is imperative to ensure right person at the right place or refrain from unauthorized access to the system. There are two types of Live detection methods first is based on hardware used during acquisition stage and second is software based used during processing stages [18]. Table 1 shows live detection methods used in FPR system based these approaches [19-20].

Table 1: Live Detection Methods

S. No

Hardware-Based

Software-Based

1

Finger temperature, pulse

Skin deformation

2

Pulse oximetry

Image quality based

3

Blood pressure

Pore based

4

Electric resistance

Perspiration based

5

Odour

Combined based

In hardware-based approach interfacing of the extra device to the sensor is required to detect the real finger by acquiring life signs [21]. Biometrics sensor cannot compute life sign directly, so they require further hardware for detection. Biomedical sensors are employed for measuring life sign in hardware-based approaches [22]. Which in turn makes the system more bulky and expensive. In software- based approaches there is no need of additional hardware is required which make the system flexible for future changes/ adoption. Software-based approaches are inexpensive than a hardware based.

Table 2 shows the various spoofing detection methods used for distinguishes between real and fake fingerprint based on the extracted feature from the input.

These features are extracted from real and fake finger based on predefined attributes. A classifier is learned based on the training set. These methods give the output in the form of numerical values and depend on these values, classifier authenticates the input as real or fake [18].

Table 2: Spoofing detection methods based on the attributes and features extracted from the fingerprint [23-36].

In table 2 four attributes coarseness, perspiration, anatomical and textural are considered for detection of spoofing attacks. Serial no. 1to 3 is based on coarseness attribute with different feature extraction methods to detect input attacks in FPR system. In serial no. 4 to 5 perspiration analysis is done using wavelet and fusion of morphology on the input image to find the real and fake finger. In serial no. 6 to 8 pore and noise analysis are considered under anatomical attributes based on that system detect input finger is real or fake. At last textural attributes with feature extraction is used to detect spoofing attacks.

In recent years software-based approaches gain more attention due to various types of algorithms that can be applied to detect spoofing attacks. Existing FPR systems can be easily protected by simply upgrade the system with a new algorithm. Thus, by applying software-based techniques existing FPR systems are protected. These solutions are easy to use, fast, less costly, easily upgradeable, and more efficient.    

  1. COMPARATIVE STUDY OF WORK CARRIED OUT BY AUTHORS

In the last year, the researcher gave significant efforts in live detection techniques used in FPR systems. A comparison of different techniques used for live detection for FPR system is shown in Table 3.

Table 3 is divided into two tables i.e. (a)(b). Table 3 (a) provides a comparative study of work carried out by different researchers based on the rate of classification as a parameter to increase the performance of the system with different feature extraction techniques used for fingerprint images. And in table 3 (b) based on accuracy, error and novel material detection to find spoofing attacks with different feature extraction techniques used for fingerprint images is provided.

Table 3(a): Comparative study based on classification rate

Table 3(b): Comparative study based on accuracy and error

S. No.

Author (s)/Year

Feature Extraction Techniques used for Fingerprint images.

Remarks

1

 Emanuela et al., IEEE 2010 [45]

  Technique using multiple textural

features

  Reduce Average error rate to 12.47%.

2

 Ankita et al., IEEE     2012 [46]

  Histogram features.

  Error rate reduces to 7.58%.

3

 Akhtar et.al. 2015 [47]

 LUCID, CENTRIST, POEM features  based detection

 HTER - Iris: 0:01%, Face: 0:1%,  Fingerprint: 0:25%.

4

 Silva et al., IEEE 2015                                             [48]

 Pores, statistical features, and     quality

  Achieved 97.3% accuracy

5

 Rattani et al., IEEE 2015 [49]

 Weibull-calibrated SVM (W-SVM)

Improvement in novel material detection up to 44%.

6

 Dongju et al., IEEE 2015 [50]

 Adopting ridge tracing features.

 Show the improvement on spoof          finger detection.

7

 Marasco et al., IEEE 2015 [51]

  Convolutional Neural Networks

Improvement in accuracy- Caffe Net (96.5%), GoogLe Net (96.6%), Siamese (93.1%).

8

 Ding et al., IEEE 2016 [52]

 One Class Support Vector Machine (OC-SVM) approach.

Improvement in detection accuracy & easily detect unseen material.

V.    CONCLUSION

Recently the demand for biometrics systems has been increased for security and authentication purposes due to their unique characteristics. Among all biometrics, human fingerprints are most reliable and employed in large-scale applications. Biometrics systems are sometimes influenced by various attacks such as spoofing attacks. In last few years these types of attacks have become a challenge to the use of biometric systems. Hence researchers gave more attention to detect these types of attacks, that is to develop techniques to differentiate between fake and real finger and ensure the genuine user for the system. In this paper, an overview of various types of spoofing attacks and live detection techniques proposed by different researchers have been discussed. There is need to develop generalized live detection algorithm for unpredictable and unseen spoofing attacks. One way to predict or detect these types of attacks in FPR systems is to add more features to the system for recognition, so the system becomes more secure and efficient.

REFERENCES

  1. www.cedarbuffalo.edu/govind/presentations/Fingerprints Overview.
  2. Priyanka “Fingerprint Recognition Techniques and its Applications” IEEE International Conference on Advances in Engineering & Technology Research (ICAETR - 2014), August 01- 02, 2014.
  3. Daugman J (1994) Biometric personal identification system based on iris analysis. United States Patent, 5291560
  4. Singh D, Singh A (2010) A secure private key encryption technique for data security in a modern cryptosystem. In: BIJIT—BVICAM’s International Journal of Information Technology Bharati Vidyapeeth’s Institute of Computer Applications and Management BVICAM), New Delhi.
  5. Kumar, M. & Priyanka.: ‘Various image enhancement and matching techniques used for fingerprint recognition system’, Int. j. inf. tecnol. (Springer Singapore Print ISSN 2511-2104), 2017, https://doi.org/10.1007/ s41870-017- 0061-4.
  6. Panganiban A, Linsangan N, Caluyo F (2011) Wavelet- based feature extraction algorithm for an iris recognition system. J Inf Process Syst 5(3): pp.-425–434.
  7. A. Jain, A. Ross, and S. Pankati, “Biometrics: A tool for information security,” IEEE Trans. Inform. Forensics Security, vol. 1, no. 2, pp. 125–143, June 2006.
  8. Galbally, J. Fierrez, and 1. Ortega-Garcia, "Vulnerabilities in Biometric Systems: Attacks and Recent Advances in Liveness Detection," Proceedings of Spanish Workshop on Biometrics, SWB, Girona, Spain, June 2007.
  9. S. Marcel, M. Nixon, and S. Z. Li, Handbook of Biometric Anti-Spoofing. New York: Springer, 2014.
  10. D. Maltoni, D. Maio, A. Jain, and S. Prabhakar, Handbook of Fingerprint Recognition. New York, NY, USA: Springer- Verlag, 2009.
  11. B. Tan and S. Schuckers, "Liveness detection using an intensity-based approach in fingerprint scanner," Proceedings of Biometric Consortium Research Symposium, Crystal City, September 2005.
  12. Abdenour Hadid, Nicholas Evans, Sébastien Marcel, and Julian Fierrez, “Biometrics Systems Under Spoofing Attack,” IEEE SIGNAL PROCESSING MAGAZINE, pp. 20-30, 2015.
  13. T. Putte and 1. Keuning "Fingerprint recognition don't get your fingers burned," Fourth Working Conference on Smart Card Research and Advanced Applications, Kluwer Academic Publishers, pp. 289-303, 2000.
  14. H. Kang, B. Lee, H. Kim, D. Shin, and J. Kim, "A Study on Performance Evaluation of the Liveness Detection for Various Fingerprint Sensor Modules," Knowledge-Based Intelligent Information and Engineering Systems Lecture Notes in Computer Science, Springer Berlin Heidelberg, Vol. 2774, pp. 1245-1253, 2003.
  15. H. Kang, B. Lee, H. Kim, D. Shin, and J. Kim, "A Study on Performance Evaluation of the Liveness Detection for Various Fingerprint Sensor Modules," Knowledge-Based Intelligent Information and Engineering Systems Lecture Notes in Computer Science, Springer Berlin Heidelberg, Vol. 2774, pp. 1245-1253, 2003.
  16. J. Galbally, R. Cappelli, A. Lumini, G. Gonzalez-de- Rivera, D. Maltoni, J. Fierrez, 1. Ortega-Garcia, D. Maio "An evaluation of direct attacks using fake fingers generated from ISO templates, " Pattern Recognition Letters, Vol. 31, pp. 725-732, 2009.
  17. T. Matsumoto, H. Matsumoto, K. Yamada, and S. Hoshino, "Impact of artificial 'gummy' fingers on fingerprint systems, "Proceedings of SPIE Vol. 4677, Optical Security and Counterfeit Deterrence Techniques IV, January 2002.
  18. Ajita Rattani, Walter J. Scheirer, and Arun Ross, “Open Set Fingerprint Spoof Detection Across Novel Fabrication Materials”, IEEE Transactions on Information Forensics and Security, Vol. 10, No. 11, November 2015.
  19. B. DeCann, B. Tan and S. Schuckers "A Novel Region Based Liveness Detection Approach for Fingerprint Scanners, "Advances in Biometrics Lecture Notes in Computer Science, Springer Berlin Heidelberg, Vol. 5558, pp. 627-636,2009.
  20. A. Abhyanka and S. Schuckers, "Wavelet-based Approach to Detecting Liveness in Fingerprint Scanners," Proceedings of the SPIE Vol. 5404, Defense and Security Symposium, Biometric Technology for Human Identification, pp. 278-286, April 2004.
  21. H. Choi, R. Kang, K. Choi, and J. Kim, "Aliveness Detection of Fingerprints using Multiple Static Features ", World Academy of Science, Engineering and Technology 28, 2007.
  22. H. Choi, R. Kang, K. Choi, and J. Kim, "Aliveness Detection of Fingerprints using Multiple Static Features ", World Academy of Science, Engineering and Technology 28, 2007.
  23. Y. S. Moon, J. S. Chen, K. C. Chan, K. So, and K. S. Woo, “Wavelet-based fingerprint liveness detection,” Electron. Lett., vol. 41, no. 20, pp. 1112–1113, Sep. 2005.
  24. P. Coli, G. L. Marcialis, and F. Roli, “Power spectrum- based fingerprint vitality detection,” in Proc. IEEE Int. Workshop Autom. Identification. Adv. Technol. (AutoID), Alghero, Italy, Jun. 2007, pp. 169–173.
  25. B. Tan and S. Schuckers, “Liveness detection for fingerprint scanners based on the statistics of wavelet signal processing,” in Proc. Conf. Comput. Vis. Pattern Recognit. workshop, Jun. 2006, p. 26.
  26. A. Abhyankar and S. Schuckers, “Integrating a wavelet- based perspiration liveness check with fingerprint recognition,” Pattern Recognit., vol. 42, no. 3, pp. 452–464, 2009.
  27. E. Marasco and C. Sansone, “Combining perspiration- and morphology-based static features for fingerprint liveness detection,” Pattern Recognit. Lett., vol. 33, no. 9, pp. 1148– 1156, 2012.
  28. G. L. Marcialis, F. Roli, and A. Tidu, “Analysis of fingerprint pores for vitality detection,” in Proc. 20th Int. Conf. Pattern Recognit. (ICPR), Aug. 2010, pp. 1289–1292.
  29. M. Espinoza and C. Champod, “Using the number of pores on fingerprint images to detect spoofing attacks,” in Proc. Int. Conf. Hand-Based Biometrics, Hong Kong, 2001, pp. 1–5.
  30. B. Tan and S. Schuckers, “Spoofing protection for fingerprint scanner by fusing ridge signal and valley noise,” Pattern Recognit., vol. 43, no. 8, pp. 2845–2857, 2010.
  31. S. B. Nikam and S. Agarwal, “Wavelet energy signature and GLCM features-based fingerprint anti-spoofing,” in Proc. IEEE Int. Conf. Wavelet Anal. Pattern Recognit., Hong Kong, Aug. 2008, pp. 717–723.
  32. S. B. Nikam and S. Agarwal, “Local binary pattern and wavelet-based spoof fingerprint detection,” Int. J. Biometrics, vol. 1, no.2, pp. 141–159, 2008.
  33. L. Ghiani, G. L. Marcialis, and F. Roli, “Fingerprint liveness detection by local phase quantization,” in Proc. 1st Int. Conf. Pattern Recognit., 2012, pp. 537–540.
  34. X. Jia et al., “Multi-scale block local ternary patterns for fingerprints vitality detection,” Proc. Int. Conf. Biometrics, Jun. 2013, pp. 1–6.
  35. D. Gragnaniello, G. Poggi, C. Sansone, and L. Verdoliva, “Fingerprint liveness detection based on Weber local image descriptor,” in Proc. IEEE Workshop Biometric Meas. Syst. Secure. Med. Appl., Sep. 2013, pp. 46–50.
  36. L. Ghiani, A. Hadid, G. L. Marcialis, and F. Roli, “Fingerprint liveness detection using binarized statistical image features,” in Proc. IEEE 6th Int. Conf. Biometrics, Theory, Appl. Syst., Sep./Oct. 2013, pp. 1–6.
  37. Shankar Bhausaheb Nikam and Suneeta Agarwal, “Texture and Wavelet-Based Spoof Fingerprint Detection for Fingerprint Biometric Systems,” First International Conference on Emerging Trends in Engineering and Technology, 978-0-7695-32 67-7/08 $25.00 © 2008 IEEE, DOI        10.1109/ICETET.2008.134, pp. -675-680.
  38. Shankar Bhausaheb Nikam and Suneeta Agarwal, “Wavelet Energy Signature And GLCM Features-Based Fingerprint Anti-Spoofing,” Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, Hong Kong, 30-31 Aug. 2008, IEEE, pp.-717- 723.
  39. Shankar Bhausaheb Nikam and Suneeta Agarwal, “Fingerprint Anti-Spoofing Using Ridgelet Transform,” 978-1-4244-2730-7/ 08/$25.00 0D2008 IEEE.
  40. Luis Filipe A. Pereira, Hector N. B. Pinheiro, Jose Ivson S. Silva, Anderson G. Silva, Thais M. L. Pina, George D. C. Cavalcanti, Tsang Ing Ren and Joao Paulo N. de Oliveira, “A fingerprint spoof detection based on MLP and SVM,” WCCI 2012 IEEE World Congress on Computational Intelligence June 10-15, 2012 - Brisbane, Australia.
  41. George D. C. Cavalcanti, Luis Filipe A. Pereira, Hector N. B. Pinheiro, Jose Ivson S. Silva, Anderson G. Silva, Thais M. L. Pina, Daniel B. O. Carvalho and Tsang Ing Ren, “A modular architecture based on image quality for fingerprint spoof detection,” 2012 IEEE International Conference on Systems, Man, and Cybernetics October 14-17, 2012, COEX, Seoul, Korea.
  42. L.F.A. Pereira, H.N.B. Pinheiro, G.D.C. Cavalcanti And Tsang Ing Ren, “Spatial Surface Coarseness Analysis: Technique for Fingerprint Spoof Detection,” electronics letters 14th February 2013 Vol. 49 No. 4.
  43. Jing-Wein Wang, Ngoc Tuyen Le, Chou-Chen Wang, And Jiann-Shu Lee, “Enhanced Ridge Structure for Improving Fingerprint Image Quality Based On A Wavelet Domain,” IEEE Signal Processing Letters, VOL. 22, NO. 4, Pp.- 390-394 APRIL 2015.
  44. Samruddhi S. Kulkarni and Dr. Hemprasad Y. Patil, “A Fingerprint Spoofing Detection System Using LBP,” International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT) – 2016, 978-1-4673- 9939-5/16/$31.00 ©2016 IEEE, pp. -3413-3417.
  45. Emanuela Marasco and Carlo Sansone, “An anti- spoofing technique using multiple textural features in fingerprint scanners,” 978-1-4244-6304-6/10/$26.00 ©2010 IEEE.
  46. Ankita Chaudhari and P.J. Deore, “Prevention of spoof attacks in fingerprinting using histogram features,” Nirma University International Conference on Engineering, Nuicone-2012, 06-08 december, 2012, 978-1- 4673-1719- 1/12/$31.00©2013 IEEE.
  47. David Menotti, Giovani Chiachia, Allan Pinto, William Robson Schwartz, Helio Pedrini, Alexandre Xavier Falcão, and Anderson Rocha, “Deep Representations for Iris, Face, and Fingerprint Spoofing Detection,” IEEE Transactions on Information Forensics and Security, VOL. 10, NO. 4, APRIL 2015, pp.- 864-879.
  48. Murilo Varges da Silva, Aparecido Nilceu Marana and Alessandra Aparecida Paulino, “On the Importance of Using High-Resolution Images, Third Level Features and Sequence of Images for Fingerprint Spoof Detection,” ICASSP 2015, 978-1-4673-6997-8/15/$3l.00 ©2015 IEEE, pp.- 1807-1811.
  49. Ajita Rattani, Walter J. Scheirer, and Arun Ross, “Open Set Fingerprint Spoof Detection Across Novel Fabrication Materials,” IEEE Transactions on Information Forensics and Security, VOL. 10, NO. 11, NOVEMBER 2015, pp.-2447-2460.
  50. Dongju Li, Hiroaki Kunieda, Supawan Kumpituck and Tsuyoshi Isshiki, “Online Detection of Spoof Fingers for Smartphone- based Applications,” 2015 IEEE 17th International Conference on High Performance Computing and Communications (HPCC), 2015 IEEE 7th International Symposium on Cyberspace Safety and Security (CSS), and 2015 IEEE 12th International Conf on Embedded Software and Systems (ICESS), 978-1-4799- 8937-9/15$31.00©2015 IEEE, DOI 10.1109/ HPCC-CSS-ICESS.2015.322.
  51. Emanuela Marasco, Peter Wild and Bojan Cukic, “Robust and Interoperable Fingerprint Spoof Detection via Convolutional Neural Networks,” 978-1-5090-0770- 7/16/$31.00 ©2016 IEEE.
  52. Yaohui Ding and Arun Ross, “An Ensemble of One- Class SVMs for Fingerprint Spoof Detection Across Different Fabrication Materials,” IEEE International Workshop on Information Forensics and Security (WIFS), 978-1-5090-1138-4/16/ 2016 IEEE.



author

For Authors

Author Membership provide access to scientific innovation, next generation tools, access to conferences/seminars
/symposiums/webinars, networking opportunities, and privileged benefits.
Authors may submit research manuscript or paper without being an existing member of LJP. Once a non-member author submits a research paper he/she becomes a part of "Provisional Author Membership".

Know more

institutes

For Institutions

Society flourish when two institutions come together." Organizations, research institutes, and universities can join LJP Subscription membership or privileged "Fellow Membership" membership facilitating researchers to publish their work with us, become peer reviewers and join us on Advisory Board.

Know more

subsribe

For Subscribers

Subscribe to distinguished STM (scientific, technical, and medical) publisher. Subscription membership is available for individuals universities and institutions (print & online). Subscribers can access journals from our libraries, published in different formats like Printed Hardcopy, Interactive PDFs, EPUBs, eBooks, indexable documents and the author managed dynamic live web page articles, LaTeX, PDFs etc.

Know more