Improved Algorithm for Separating Latent Overlapped Fingerprints

Abstract
Authors
Keywords
Conclusion
References

Latent Overlapped fingerprints are frequently encountered in latent fingerprints lifted from crime scenes. Overlapping occurs when the same location of an object is touched by one or more fingers several times. It is necessary to separate such latent overlapped fingerprints into component fingerprints so that existing fingerprint matchers can recognize them. In fact, fingerprint examiners usually do not collect latent overlapped fingerprints since they are too complicated to process. Thus it is desired to develop an algorithm to separate the overlapped fingerprints into individual fingerprints in order to reduce the labour of fingerprint examiners. A new approach for separating latent overlapped fingerprints are proposed to improve the perfection of the separating algorithms by overcoming the difficiency in principal component analysis (PCA) technique. A new method provides robustness and efficiency to the system.

Published In : IJCSN Journal Volume 5, Issue 2

Date of Publication : April 2016

Pages : --

Figures :14

Tables : --

Publication Link : Improved Algorithm for Separating Latent Overlapped Fingerprints

Abhishek Pawar : Department of Computer Science and Engineering, G. H. Raisoni College of Engineering, Nagpur University Nagpur, Maharashtra, India

Mangala Madankar : Department of Computer Science and Engineering, G. H. Raisoni College of Engineering, Nagpur University Nagpur, Maharashtra, India

Overlapped Fingerprints, Gabor Filters, Principal Component Analysis, minutia

Earlier there is no more work done on separating overlapped fingerprints. Earlier there is adaptive orientation model which cannot separate more than two fingerprints. Also they are not robust and efficient. The PCA subspace projection is not strong enough to keep the orientation models to be fingerprint-like, which leads some of the separating results not having valid fingerprint flow patterns. It may be possible to implement proposed algorithm for separating latent overlapped fingerprints, several overlapped fingerprints separation algorithms have been proposed. However, they are not yet fully automatic, and different levels of human interventions are required. We proposed the usage of Independent Component Analysis (ICA) to separate latent overlapped fingerprints, but they provided neither algorithm details, nor a thorough experiment. We proposed a model based separation approach, which gives quite a noteworthy matching accuracy. However, this method requires additional manual markups of the orientation clues, which definitely increases the workload of examiners. There are still some limitations in our method. Our proposed algorithm works only on good quality fingerprints. As a future study, we plan to study separation of bad quality fingerprints.

[1] F. Chen, J. Feng, A. K. Jain, J. Zhou, and J. Zhang, “Separating overlapped fingerprints”, IEEE Trans. Inf. Forensics Security, vol. 6, no. 2, pp. 346–359, Jun. 2011. [2] Le Hoang Thai and Ha Nhat Tam, “Fingerprint recognition using standardized fingerprint model”, International Journal of Computer Science Issues, Vol. 7, Issue 3, No 7, May 2010. [3] M. Singh, D. K. Singh, and P. K. Kalra, “Fingerprint separation: An application of ICA”, in Proc. SPIE, Apr. 2008, p. 69820L. [4] A. Rosenfeld, R. A. Hummel, and S. W. Zucker, “Scene labeling by relaxation operations”, IEEE Trans. Syst. Man, Cybern., vol. SMC-6, no. 6, pp. 420–433, Jun. 1976. [5] A. Hyvärinen, J. Karhunen, and E. Oja, “Independent Component Analysis”, vol. 46. Hoboken, NJ, USA: Wiley, 2004. [6] Fanglin Chen, Jianjiang Feng and Jie Zhou, “On separating overlapped fingerprints”, 978-1-4244-7580-3/10/$26.00 ©2010 IEEE. [7] Yuan Shi, Jianjiang Feng and Jie Zhou, “Separating Overlapped Fingerprints Using Constrained Relaxation Labeling”, 978-1-4577-1359-0/11, 2011. [8] Q. Zhao and A. K. Jain, “Model based separation of overlapping latent fingerprints”, IEEE Trans. Inf. Forensics Security, vol. 7, no. 3, pp. 904–918, Jun. 2012. [9] Jianjiang Feng, Yuan Shi, and Jie Zhou, “Robust and Efficient Algorithms for Separating Latent Overlapped Fingerprints”, IEEE Transactions On Information Forensics And Security, Vol. 7, No. 5, October 2012. [10] Ning Zhang, Yali Zang, Xin Yang, Xiaofei Jia, and Jie Tian, “Adaptive Orientation Model Fitting for Latent Overlapped Fingerprints Separation”, IEEE Transactions On Information Forensics And Security, Vol. 9, No. 10, October 2014. [11] J. Feng, Y. Shi, and J. Zhou, “Robust and efficient algorithms for separating latent overlapped fingerprints”, IEEE Trans. Inf. Forensics Security, vol. 7, no. 5, pp. 1498–1510, Oct. 2012. [12] Sangram Bana and Dr. Davinder Kaur, “Fingerprint Recognition using Image Segmentation”, International Journal Of Advanced Engineering Sciences And Technologies Vol No. 5, Issue No. 1, 012 – 023, 2011. [13] Jinwei Gu, Jie Zhou and Chunyu Yang, “Fingerprint Recognition by Combining Global Structure and Local Cues”, IEEE Transaction On Image Processing, Vol. 15, No. 7, July 2006. [14] R. Reka and Dr. S. Uma, “Automatic Overlapped Fingerprint Separation”, International Journal of Commerce, Business and Management (IJCBM), Vol. 1, No.1, 2012. [15] Zin Mar Wini and Myint Myint Sein, “Texture Feature based Fingerprint Recognition for Low Quality Images”, 978-1-4577-1362-0/11, IEEE 2011. [16] S. Arivazbagan, T.G. Arul Flora and L. Ganesan, “Fingerprint verification using Gabor co-occurrences features”, in: International Conference on Computational Intelligence and Multimedia Applications, pp. 281-285, 2007. [17] M. Yazdi and K. Gheysari, “A new approach for the fingerprint classification based on gray-level co-occurrence matrix”, Int. J. Comput. Inform. Sci. Eng, pp.171-174, 2008.