CHALLENGES AND SCOPE OF FINGERNAIL PLATES IN BIOMETRICS

  • • Fusion: Fingernail plates have been seen to provide appreciable biometric authentication results, when these are fused with finger knuckles [5]. Also, the performance of the fusion of multiple fingernail plates may be a prospective scope, something which has been explored to a certain extent in this work. The fingernail plate may also be investigated in combination with other biometric traits which do not belong to the dorsal part of the human hand like fingerprint, iris, face, and voice. However, such systems would require sample acquisition in multiple steps.
  • • Application in Forensics: Drug analyses in nails have received significant attention because of the ability of nails to amass drugs, when subjected to long-term exposure [38]. Nail plates may be subjected to exhaustive experimentation in order to observe the changes or deformities caused by long- or short-term drug abuse. Additionally, trace evidences obtained from crime scenes encapsulating fingernail plates (as shown in Figure 9.2) shall be able to provide considerable help in forensic investigation.

Acceptability: The sample collection of fingernail plate images can be done using a very low-cost camera, without any constraints being imposed on the user. This has been implemented in the current work. As such, sample collection of this trait may be considered to be considerably user-friendly as it does not require active user cooperation.

• Spoofing: The nail plate enjoys a certain degree of advantage over popular hand biometrics like fingerprints. This is because people inadvertently leave behind fingerprints on whatever they touch, which is not possible in the case of nail plates. However, it would be significant to work towards designing anti-spoofing techniques particularly aimed towards nail plates.

CONCLUSIONS AND FUTURE SCOPE

This work has tried to further explore the fingernail plate as a biometric trait, considering three different deep learning methods for feature extraction. The nail plate has anatomically distinctive features which are less prone to impersonation.

This report analyses the performance of the nail plate in unimodal verification and identification systems. The results show that the nail plates under all the three considered feature extraction techniques provide substantially significant authentication performance.

Multimodal systems are known to compensate the drawbacks of a trait and to provide improved performance accuracy. In view of this, the fingernail plate has been explored in various multimodal systems. Score-level fusion has been implemented through four different rules for all three deep learning models. The results show that the multimodal verification systems perform much better than their unimodal counterparts. Various multimodal identification systems have been designed using different weighted and non-weighted fusion rules. The weights of the three nail plates for the weighted fusion methods have been attributed through empirical computation, and by using PSO in order to ensure optimal weight attribution. Comprehensive experiments have been carried out, and results depict that identification accuracy as high as 99.44% can be achieved when right weightage is given to the traits. The results also confirm the fact that more the depth of the model, better the results.

The significant results given by the experiments performed in this work give inspiration to further probe the scope of the nail plate in biometric authentication. It shall be interesting to design the implemented system in an adaptive framework [29], which shall lessen the computational time and cost. This is because such a system shall provide the results after deciding on the optimal fusion rule for the selected biometric traits. The future scope of this proposed work includes checking its efficacy in feature-level multibiometric systems. A larger database also may be prepared so as to scale up research in this field.

REFERENCES

  • 1. Kumar, A., Zhou, Y., “Human Identification using Finger Images.” IEEE Transactions on Image Processing, Vol. 21, No. 4. 2012, pp. 2228-2244.
  • 2. Kumar. A., Ravikanth, C., “Personal Authentication using Finger Knuckle Surface.” IEEE Transactions on Information Forensics and Security, Vol. 4, No. 1, 2009, pp. 98-110.
  • 3. Kumar. A., Hu, Z., “Personal Identification using Minor Knuckle Patterns from Palm Dorsal Surface.” IEEE Transactions on Information Forensics & Security, Vol. 11, No. 10. 2016, pp. 2338- 2348.
  • 4. Kumar. A.. Prathyusha, К. V., “Personal Authentication using Hand Vein Triangulation and Knuckle Shape.” IEEE Transactions on Image Processing, Vol. 18, No. 9, 2009, pp. 2127-2136.
  • 5. Horn Choudhury, S., Kumar, A., Laskar, S. H., “Biometric Authentication through Unification of Finger Dorsal Biometric Traits.” Information Sciences, Vol. 497, 2019,

pp. 202-218.

6. Huang, D., Tang, Y., Wang, Y., Chen, M„ Wang, Y., “Hand-Dorsa Vein Recognition by Matching Local Features of Multisource Keypoints.” IEEE Transactions on Cybernetics, Vol. 45, No. 9, 2015, pp. 1823-1837.

  • 7. Qin, H„ El-Yacoubi, M. A., “Deep Representation-based Feature Extraction and Recovering for Finger-Vein Verification.” IEEE Transactions on Information Forensics and Security, Vol. 12, No. 8, 2017, pp. 1816-1829.
  • 8. Kumar, A., Garg, S., Hanmandlu, M., “Biometric Authentication using Finger Nail Plates.” Expert Systems with Applications, Vol.41, No. 2, 2014, pp. 373-386.
  • 9. Diaz, A. A., Boehm, A. F., Rowe, W. E, “Comparison of Fingernail Ridge Patterns of Monozygotic Twins.” Journal of Forensic Sciences, Vol. 35, No. 1, 1990, pp. 97-102.
  • 10. Daniel III, C. R., Piraccini, В. M., Tosti, A., “The Nail and Hair in Forensic Science.” Journal of the American Academy of Dermatology, Vol. 50, No. 2, 2004, pp. 258-261.
  • 11. Hong, L., Jain, A., “Integrating Faces and Fingerprints for Personal Identification.” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 12, 1998, pp. 1295-1307.
  • 12. Kumar, A., Kumar, A., “Adaptive Management of Multimodal Biometrics Fusion Using Ant Colony Optimization.” Information Fusion, Vol. 32, No. B, 2016, pp. 49-63.
  • 13. Roberts, D. T., Taylor, W. D., Boyle, J., “Guidelines for Treatment of Onychomychosis.” The British Journal of Dermatology, Vol. 148, No. 3, 2002, pp. 402-410.
  • 14. Apolinar, E., Rowe, W. F., “Examination of Human Fingernail Ridges by Means of Polarized Light.” Journal of Forensic Sciences, Vol. 25, No. 1, 1980, pp. 154-161.
  • 15. Topping, A., Kuperschmidt, V, Gormley, A., “Method and Apparatus for the Automated Identification of Individuals by the Nail Beds of their Fingernails.” U.S. Patent, 5751835A. 1998.
  • 16. Garg, S., Kumar, A., Hanmandlu, M., “Biometric Authentication using Finger Nail Surface.” 12 th International Conference on Intelligent Systems Design and Applications (ISDA), IEEE, Kochi, 2012, pp. 497-502.
  • 17. Garg, S., Kumar, A., Hanmandlu, M., “Finger Nail Plate: A New Biometric Identifier.” International Journal of Computer Information Systems and Industrial Management Applications, Vol. 6. 2014, pp. 126-138.
  • 18. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P, “Gradient-Based Learning Applied to Document Recognition." Proceedings of the IEEE. Vol. 86, No.l 1. 1998. pp. 2278-2324.
  • 19. LeCun, Y„ Bengio, Y.. Hinton, G.. “Deep Learning.” Nature, Vol. 521. No. 7553, 2015, pp. 436-444.
  • 20. Bengio, Y., “Learning Deep Architectures for AI.” Foundations and Trends® in Machine Learning. Vol. 2, No. 1, 2009, pp. 1-127.
  • 21. Amato, G., Carrara, F., Falchi, F., Gennaro, C., Meghini, C., Vairo, C., “Deep Learning for Decentralized Parking Lot Occupancy Detection.” Expert Systems with Applications, Vol. 72, 2017, pp. 327-334.
  • 22. Goodfellow, I., Bengio, Y., Courville, A., Deep Learning, Cambridge, MA: The MIT Press. 2016.
  • 23. Razavian, A. S., Azizpour, H., Sullivan, J., Carlsson, S., “CNN Features off-the-shelf: An Astounding Baseline for Recognition.” Proceedings of the CVPR, 2014, pp. 512-519.
  • 24. Azizpour, H., Razavian, A. S., Sullivan, J., Maki, A., Carlsson, S., “From Generic to Specific Deep Representations for Visual Recognition.” Proceedings of the CVPR, 2015. pp. 36-45.
  • 25. Krizhevsky, A., Sutskever, I., Hinton, G. E., “ImageNet Classification with Deep Convolutional Neural Networks.” Proceedings of the Advances in Neural Information Processing Systems, 2012. pp. 1097-1105.
  • 26. ImageNet. http://www.image-net.org, Jun. 2015.
  • 27. He, K., Zhang, X., Ren, S., Sun, J., “Deep Residual Learning for Image Recognition.” Proceedings of the CVPR. 2016, pp. 1-9.
  • 28. Huang, G., Liu, Z., van der Maaten, L., Weinberger, K. Q., “Densely Connected Convolutional Networks.” Proceedings of the CVPR, 2017, pp. 2261-2269.
  • 29. Kumar, A., Kanhangad, V., Zhang, D., “A New Framework for Adaptive Multimodal Biometrics Management.” IEEE Transactions on Information Forensics and Security, Vol. 5. No. I, 2010. pp. 92-102.
  • 30. Ross, A., Nandakumar, K., Jain, A.K., “Handbook of Multibiometrics.” Springer- Verlag, New York, 2006.
  • 31. Monwar, M.M. “A Multimodal Biometric System based on Rank Level Fusion,” Ph.D. Thesis, University of Calgary, Dec. 2012.
  • 32. Kumar, A., Shekhar, S., “Personal Identification using Multibiometrics Rank-Level Fusion.” IEEE Transactions on Systems, Man, and Cybernetics, Part C (Appl. and Rev.), Vol. 41, No. 5, 2011. pp. 743-752.
  • 33. Но, T.K., Hull, J.J., Srihari, S.N., “Decision Combination in Multiple Classifier Systems.” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 16, No. 1, 1994, pp. 66-75.
  • 34. Kennedy, J., Eberhart, R., “Particle Swarm Optimization.” 1995 IEEE International Conference on Neural Networks, Vol. 4, 2002. pp. 1942-1948.
  • 35. Melnik, O., Vardi, Y., Zhang, C-H., “Mixed Group Ranks: Preference and Confidence in Classifier Combination.” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 8, 2004, pp. 973-981.
  • 36. Jovic, M., Hatakeyama, Y., Dong, F., Hirota, K., “Image Retrieval based on Similarity Score Fusion from Feature Similarity Ranking Lists.” Fuzzy Systems and Knowledge Discovery, ser. Lecture Notes in Computer Science, Springer Berlin Heidelberg, Vol. 4223, 2006, pp. 461-470.
  • 37. Nandakumar, K. “Multibiometric Systems: Fusion Strategies and Template Security,” Ph.D. Thesis, Michigan State University, 2008.
  • 38. Cappelle, D., Yegles, M., Neels, H., van Nuijs, A. L. N.. Doncker, M.D., Maudens, K., Covaci, A., Crunelle, C. L., “Nail Analysis for the Detection of Drugs of Abuse and Pharmaceuticals: A Review.” Forensic Toxicology, Vol. 33, 2015, pp. 12-36.
 
Source
< Prev   CONTENTS   Source   Next >