روشی مطمئن برای مقابله با مشکلات طبقهبندی اثر انگشت
محورهای موضوعی : مهندسی برق و کامپیوترفائزه ميرزايي 1 , حسين ابراهيمپور کومله 2 , محسن بيگلري 3
1 - دانشگاه کاشان
2 - دانشگاه کاشان
3 - دانشگاه صنعتی شاهرود
کلید واژه: شناسایی اثر انگشت طبقهبندی اثر انگشت طبقهبندی احتمالی طبقهبندی مبتنی بر قانون,
چکیده مقاله :
اثر انگشت بیومتریکی است که به دلیل ویژگیهای منحصر به فردش، بیشترین کاربرد را در سیستمهای تشخیص و تعیین هویت داشته است. در سیستمهای تعیین هویت، تصویر ورودی با تمام تصاویر ثبتشده در پایگاه مقایسه میگردد و در صورتی که پایگاه داده حجیم باشد، عمل مقایسه بسیار زمانبر خواهد بود. برای نمونه میتوان به پایگاههای داده موجود در FBI اشاره نمود. یکی از راه حلهای تأییدشده برای افزایش سرعت، طبقهبندی تصاویر است. در طبقهبندی مطلق، به هر اثر انگشت تنها یک کلاس تخصیص مییابد. دلایل مختلفی چون نویز یا عدم وجود همه نقاط یکتا در محدوده تصویر، تعیین یک کلاس مطلق برای همه تصاویر را دچار مشکل میکند. در این مقاله، روشی جدید بر پایه طبقهبندی احتمالی ارائه شده که برای هر تصویر ورودی، مجموعهای از کلاسها مشخص میشود که هر یک دارای یک احتمال میباشند. در مرحله انطباق، کلاسها به ترتیب اولویتشان جستجو میشوند. آزمایشات صورتگرفته بر روی پایگاه داده شناختهشده 2002 FVC، تأثیر استفاده از طبقهبندی احتمالی را به روشنی نشان داده است. با در نظر گرفتن کلاسهای دوم و سوم تعیینشده توسط روش پیشنهادی، دقت شناسایی سیستم تقریباً 18% افزایش یافته است، در صورتی که سرعت آن، 2 تا 3 برابر بیشتر از طبقهبندی مطلق میباشد.
Fingerprint as a biometric has the most applications in verification and identification systems, because of its specific properties. In identification systems, input image is compared with all of images stored in the database. In huge databases, the comparison will take large amounts of time; Consider FBI databases, for instance. Image classification is one of the approved methods to increase the identification speed. Only one class is assigned to each fingerprint in tradition absolute classification. Various reasons like noise or lack of all the singularity points in captured region, cause the problem in determination of an absolute class for all the images. In this article, a new method based on probabilistic classification is presented. In the proposed approach, a set of classes are considered for each input image with a specific probability. These classes are searched in order of their probabilities priority in matching stage. Experiments on well-known FVC2002 database, exhibit the effect of probable classification clearly. Using only the second and third classes assigned by the proposed method, the identification system achieves about 18% increase in accuracy and 2-3 times speedup in compared to the traditional methods.
[1] D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar, Handbook of Fingerprint Recognition, Springer - Verlag New York Inc, 2009.
[2] A. I. Awad and K. Baba, "Efficient fingerprint classification using singular point," Int. J. of Digital Information and Wireless Communications, vol. 1, no. 3, pp. 611-616, 2011.
[3] M. Bhuyan and D. Bhattacharyya, "An effective fingerprint classification and search method," Int. Journal of Computer Science and Network Security, vol. 9, no. 11, pp. 39-48, Nov. 2009.
[4] I. S. Msiza, B. Leke - Betechuoh, F. V. Nelwamondo, and N. Msimang, "A fingerprint pattern classification approach based on the coordinate geometry of singularities," in Proc. IEEE Int. Conf. on Systems, Man, and Cybernetics, pp. 510-517, 11-14 Oct. 2009.
[5] L. Wang and M. Dai, "Application of a new type of singular points in fingerprint classification," Pattern Recognition Letters, vol. 28, no. 13, pp. 1640-1650, 2007.
[6] H. Zhang and X. Wang, "A new fingerprint enhancement algorithm," in Proc. Third IEEE Int. Cof on Broadband Network and Multimedia Technology, IC-BNMT'10, pp. 1222-1225, Beijing, China, 26-28 Oct. 2010.
[7] L. O'Gorman and J. V. Nickerson, "An approach to fingerprint filter design," Pattern Recognition, vol. 22, no. 1, pp. 29-38, Jan. 1989.
[8] L. Hong, Y. Wan, and A. Jain, "Fingerprint image enhancement: algorithm and performance evaluation," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 20, no. 8, pp. 777-789, Aug. 1998.
[9] K. Arora, and P. Garg, "A quantitative survey of various fingerprint enhancement techniques," Int. J. of Computer Applications, vol. 28, no. 5, pp. 24-29, Aug. 2011.
[10] W. Wang, J. Li, F. Huang, and H. Feng, "Design and implementation of Log-Gabor filter in fingerprint image enhancement," Pattern Recognition Letters, vol. 29, no. 3, pp. 301-308, Feb. 2008.
[11] Y. Wang, J. Hu, and F. Han, "Enhanced gradient - based algorithm for the estimation of fingerprint orientation fields," Applied Mathematics and Computation, vol. 185, no. 2, pp. 823-833, Feb. 2007.
[12] J. Wang and X. Sun, "Fingerprint image enhancement using a fast Gabor filter," in Proc. 8th World Congress Intelligent Control and Automation, WCICA , pp. 6347-6350, 7-9 Jul. 2010.
[13] M. Yang - Biao, "Fingerprint enhancement based on Gabor Filter [J]," Computer Engineering and Application. vol. 45, no. 10, pp. 172-175, 2009.
[14] C. Watson, G. Candela, and P. Grother, Comparison of FFT Fingerprint Filtering Methods for Neural Network Classification, NIST Technical Report 5493 NISTIR-5493, 1994.
[15] S. Wang, W. W. Zhang, and Y. S. Wang, "Fingerprint classification by directional fields," in Proc. 4th IEEE Int. Conf. on Multimodal Interfaces, pp. 395-399, 2002.
[16] M. Kawagoe and A. Tojo, "Fingerprint pattern classification," Pattern Recognition, vol. 17, no. 3, pp. 295-303, 1984.
[17] A. K. Jain, S. Prabhakar, and L. Hong, "A multichannel approach to fingerprint classification," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 21, no. 4, pp. 348-359, Apr. 1999.
[18] K. Nilsson and J. Bigun, "Localization of corresponding points in fingerprints by complex filtering," Pattern Recognition Letters, vol. 24, no. 13, pp. 2135-2144, Sep. 2003.
[19] K. Nilsson and J. Bigun, "Complex filters applied to fingerprint images detecting prominent symmetry points used for alignment," Biometric Authentication, Lecture Notes in Computer Science, vol. 2359, pp. 39-47, 2002.
[20] G. Aguilar, G. Sanchez, K. Toscano, M. Nakano - Miyatake, and H. Perez - Meana, "Automatic fingerprint recognition system using fast fourier transform and gabor filters," Cientifica, vol. 12, no. 1, pp. 9-16, 2008.
[21] V. Areekul, U. Watchareeruetai, K. Suppasriwasuseth, and S. Tantaratana, "Separable gabor filter realization for fast fingerprint enhancement," in Proc. IEEE Int. Conf. on . Image Processing, ICIP 2005, vol. 3, pp. 253-256, 11-14 Sep. 2005.
[22] J. Yang, L. Liu, T. Jiang, and Y. Fan, "A modified gabor filter design method for fingerprint image enhancement," Pattern Recognition Letters, vol. 24, no. 12, pp. 1805-1817, Aug. 2003.
[23] K. Kale, R. Manza, V. Humbe, and P. Deshmukh, "Fingerprint image enhancement using composite method," in Proc. GSPx-2005 Pervasive Signal Processing Conf., California USA,, 24-27 Oct. 2005.
[24] A. K. Jain and F. Farrokhnia, "Unsupervised texture segmentation using gabor filters," Pattern Recognition, vol. 24, no. 12, pp. 1167-1186, Dec. 1991.
[25] J. G. Daugman, "Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters," Optical Society of America, J., A: Optics and Image Science, vol. 2, no. 7, pp. 1160-1169, Jul 1985.
[26] http://onin.com/fp/fphistory.html, "The history of fingerprint".
[27] J. W. Wang, "Classification of fingerprint based on traced orientation flow," in Proc. IEEE Int. Symp. on Industrial Electronics, ISIE, pp. 1585-1588, 4-7 Jul. 2010.
[28] D. Maio, D. Maltoni, R. Cappelli, J. L. Wayman, and A. K. Jain, "FVC 2000: fingerprint verification competition," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 24, no. 3, pp. 402-412, Mar. 2002.
[29] D. Maio, D. Maltoni, R. Cappelli, J. Wayman, and A. Jain, "FVC2004: Third fingerprint verification competition," in Proc. of the Int. Conf. on Biometric Authentication, 5 pp., 2004.
[30] (11/10/2012). CASIA-FingerprintV5. Available: http://biometrics.idealtest.org/
[31] D. Maio, D. Maltoni, R. Cappelli, J. L. Wayman, and A. K. Jain, "FVC2002: Second fingerprint verification competition," in Proc. of 16th Int. Conf. on Pattern Recognition, vol. 3, pp. 811-814, 2002.