شناسایی افراد از طریق رگ‌های خونی انگشت دست در فضای رادون با به کارگیری الگوهای فضایی مشترک
محورهای موضوعی : مهندسی برق و کامپیوتر
1 - دانشگاه صنعتی شاهرود
2 - دانشگاه صنعتی شاهرود
کلید واژه: شناسایی رگ انگشت آستانه‌گذاری آنتروپی محلی تبدیل رادون الگوهای فضایی مشترک (CSP),
چکیده مقاله :
یکی از مناسب‌ترین بیومتریک‌ها برای شناسایی افراد، رگ‌های انگشت دست می‌باشد. در این مقاله روش جدیدی ارائه شده است که به شناسایی افراد از طریق رگ‌های خونی انگشت دست با دقت بالا می‌پردازد. این مقاله ابتدا از آستانه‌گذاری آنتروپی محلی برای قطعه‌بندی و استخراج رگ‌ها از تصاویر انگشت استفاده می‌نماید. آستانه‌گذاری آنتروپی محلی رگ‌ها را به خوبی استخراج می‌کند اما تصاویر حاصل از آن نویزی هستند به این مفهوم که رگ‌های استخراج‌شده ممکن است به صورت خطوط متقاطع ظاهر شوند. برای کم‌کردن حساسیت مرحله شناسایی نسبت به نویزهای موجود در تصاویر قطعه‌بندی شده، از تبدیل رادون استفاده می‌کنیم. تبديل رادون به علت داشتن ماهيت انتگرالي، نسبت به نويزهاي موجود در تصوير حساس نيست و بنابراین در مقایسه با سایر روش‌ها نسبت به نویز از مقاومت بیشتری برخوردار است. همچنین با استفاده از این تبدیل علاوه بر این که به استخراج خطوط رگ به طور دقیق نیاز نیست، دقت و سرعت شناسایی نیز افزایش می‌یابد. برای استخراج ویژگی از تصاویر رگ انگشت، الگوهای فضایی مشترک به بلوک‌های تبدیل رادون اعمال می‌شوند. در مرحله شناسایی نیز از دو روش نزدیک‌ترین همسایهNN) -1) و شبکه عصبی پرسپترون چندلایه (MLP) استفاده می‌شود. آزمایش‌های انجام‌شده روی مجموعه تصاویر رگ انگشت پایگاه داده دانشگاه پکینگ نرخ موفقیت 6753/99 درصد در شناسایی افراد را نشان می‌دهد.
One of the most fitting biometric for identifying individuals is finger veins. In this paper, we study the human recognition via finger vein images that recognize persons at a high level of accuracy. First we use entropy based thresholding for segmentation and extraction veins from finger vein images. The method extract veins as well, but the images are very noisy. That means in addition to the veins that appeared as dark lines, they have some Intersecting lines. Then we applied radon transformation to segmented images. The radon transform is not sensitive to the noise in the images due to its integral nature, so in comparison with other methods is more resistant to noise. This transform does not require the extraction of vein lines accurately, that can help to increase accuracy and speed. Then for extracting features from finger vein images, common spatial patterns are applied to the blocks of Radon Transform. In identification step two methods are used: Nearest Neighbor (1-NN) and Artificial Neural Network (MLP). Experiments conducted on sets of finger vein image database of Peking University show 99.6753 percent success rate in identifying individuals.
[1] X. J. Meng, G. P. Yang, Y. L. Yin, and R. Y. Xiao, "Finger vein recognition based on local directional code," Sensors, vol. 12, no. 12, pp. 14937-14952, Nov. 2012.
[2] K. Park, "Finger vein recognition by combing global and local feature base on SVM," Computing and Informatics, vol. 30, no. 2, pp. 295-309, Apr. 2011.
[3] G. P. Yang, X. M. Xi, and Y. L. Yin, "Finger vein recognition based on (2D) 2PCA and metric learning," J. Biomed. Biotechnol, vol. 2012, 9 pp., Mar. 2012.
[4] G. P. Yang, X. M. Xi, and Y. L. Yin, "Finger vein recognition based on a personalized best bit map," Sensors, vol. 12, no. 2, pp. 1738-1757, Feb. 2012.
[5] J. D. Wu and C. T. Liu, "Finger-vein pattern identification using principal component analysis and the neural network technique," Expert Syst, vol. 38, no. 5, pp. 5423-5427, May 2011.
[6] C. B. Yu, D. M. Zhang, and H. B. Li, "Finger vein image enhancement based on multi-threshold fuzzy algorithm," in Proc. of the 2nd Int. Congress on Image and Signal Processing, CISP'09, 3 pp., Tianjin, China, Oct. 2009.
[7] J. F. Yang and J. L. Yang, "Multi-channel Gabor finger design for finger vein image enhancement," in Proc. of the 5th International Conf. on Image and Graphic,s ICIG'09, pp. 87-91, Xi'an, China, Sept. 2009.
[8] J. F. Yang and M. F. Yan, "An improved method for finger-vein image enhancement," in Proc. of the 2010 IEEE 10th Int. Conf. on Signal Processing, pp. 1706-1709, Beijing, China, Oct. 2010.
[9] J. F. Yang, J. L. Yang, and Y. H. Shi, "Combination of Gabor wavelets and circular Gabor filter for finger-vein extraction," in Proc. of the 5th Int. Conf. on Emerging Intelligent Computing Technology and Applications, pp. 346-354, , Ulsan, Korea, Sept. 2009.
[10] N. Miura, A. Nagasaka, and T. Miyatake, "Feature extraction of finger-vein patterns based on repeated line tracking and its application to personal identification," Mach. Vis. Appl, vol. 15, no. 4, pp. 194-203, Oct. 2004.
[11] C. B. Yu, H. F. Qin, L. Zhang, and Y. Z. Cui, "Finger-vein image recognition combining modified Hausdorff distance with minutiae feature matching," Interdisciplinary Sciences: Computational Life Sciences, vol. 1, no. 4, pp. 280-289, Dec. 2009.
[12] W. Song, T. Kim, H. C. Kim, J. H. Choi, H. J. Kong, and S. R. Lee, "A finger-vein verification system using mean curvature," Patt. Recogn. Lett, vol. 32, no. 11, pp. 1541-1547, Aug. 2011.
[13] N. Miura, A. Nagasaka, and T. Miyatake, "Extraction of finger-vein patterns using maximum curvature points in image profiles," in Proc. of the 9th IAPR Conf. on Machine Vision Applications, MVA'05, pp. 347-350, Tsukuba, Japan, May 2005.
[14] B. N. Huang, Y. G. Dai, and R. F. Li, "Finger-vein authentication based on wide line detector and pattern normalization," in Proc. of the 20th Int. Conf. on Pattern Recognition, pp. 1269-1272, Istanbul, Turkey, Aug. 2010.
[15] K. J. Wang, J. Y. Liu, P. Popoola Oluwatoyin, and W. X. Feng, "Finger vein identification based on 2-D Gabor filter," in Proc. of the 2nd Int. Conf. on Industrial Mechatronics and Automation, pp. 10-13, Wuhan, China, May 2010.
[16] B. A. Rosdi, C. W. Shing, and S. A. Suandi, "Finger vein recognition using local line binary pattern," Sensors, vol. 11, no. 12, pp. 11357-11371, Nov. 2011.
[17] E. C. Lee, H. Jung, and D. Kim, "New finger biometric method using near infrared imaging," Sensors, vol. 11, no. 3, pp. 2319-2333, Feb. 2011.
[18] J. D. Wu and C. T. Liu, "Finger-vein pattern identification using principal component analysis and the neural network technique," Expert Systems with Applications, vol. 38, no. 5, pp. 5423-5427, May 2011.
[19] Z. Liu, Y. H. Yin, H. Wang, S. Song, and Q. Li, "Finger vein recognition with manifold learning," J. of Network and Computer Applications, vol. 33, no. 3, pp. 275-282, May 2010.
[20] J. D. Wu and C. T. Liu, "Finger-vein pattern identification using SVM and neural network technique," Expert Systems with Applications, vol. 38, no. 11, pp. 14284-14289, Oct. 2011.
[21] T. Chanwimaluang and G. Fan, "An efficient blood vessel detection algorithm for retinal images using local entropy thresholding," in Proc. of IEEE Int. Symp. on Circuits and Systems, vol. 5, pp. 21-24, Bangkok, Thailand, Mar 2003.
[22] N. R. Pal and S. K. Pal, "Entropic thresholding," Signal Processing, vol. 16, no. 2, pp. 97-108, Feb. 1989.
[23] C. I. Chang, K. Chen, J. Wang, and M. L. G. Althouse, "A relative entropy-based approach to image thresholding," Pattern Recognition, vol. 27, no. 9, pp. 1275-1289, Sept. 1994.
[24] A. Gavlasova and A. Prochazka, "Simulink modelling of radon and wavelet transforms for image feature extraction," in Proc. Int. Conf. Technical Computing, 7 pp., Prague, Czech Republic2005.
[25] A. Asad, S. A. M. Gilani, and U. Shafique, "Affine invariant feature extraction using a combination of Radon and wavelet transforms," T. Sobh (ed.), in Innovations and Advanced Techniques in Computer and Information Sciences and Engineering, pp. 93-97, 2013.
[26] X. Jia, J. J. Cui, D. Y. Xue, and F. Pan, "An adaptive dorsal hand vein recognition algorithm based on optimized HMM," J. of Computational Information Systems, vol. 8, no. 8, pp. 313-322, 2012.
[27] A. Kumar and Y. B. Zhou, "Human identification using finger images," IEEE Trans. Image Process., vol. 21, no. 4, pp. 2228-2244, Apr. 2011.
[28] Radon Transform, http://homepages.inf.ed.ac.uk/rbf/CVonline/ LOCAL_COPIES/AV0405/HAYDEN/Slice_Reconstruction.html, Accessed on 1 Sept. 2014
[29] S. Venturas and I. Flaounas, "Study of radon transformation and application of its inverse to NMR," Athenas, Available from cgi.di.uoa.gr/~erga/mobio/05/proj2/Flaounas_Venturas_Final.doc, 2005, Accessed on 19 October 2007.
[30] J. Muller-Gerking, G. Pfurtscheller, and H. Flyvbjerg, "Designing optimal spatial filters for single-trial EEG classification in a movement task," Clin. Neurophysiol, vol. 110, no. 5, pp. 787-798, May 1999.
[31] E. Niedermeyer and F. H. L. D. Silva, Electroencephalography: Basic Principles, Clinical Applications, and Related Fields, Lippincott Williams & Wilkins, 2005.
[32] S. Kulkarni and R. D. Raut, "Finger vein recognition," IOSR J. of Electrical and Electronics Engineering, vol. 2, pp. 32-36, 2014.
[33] PKU Finger Vein Database (V4) from Peking University, http://rate.pku.edu.cn/.
[34] J. D. Wu and S. H. Ye, "Driver identification using finger-vein patterns with radon transform and neural network," Expert Syst. Appl, vol. 36, no. 3, pp. 5793-5799, Apr. 2009.
