Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Embedded processor optimised for vascular pattern recognition

© The Institution of Engineering and Technology
Received 19/06/2012, Accepted 10/12/2012, Revised 23/11/2012, Published

In this study, the authors propose an efficient embedded processing architecture that uses the vascular pattern extraction (VPE) algorithm to authenticate a user to an embedded system. This study first considers the use of direction-based vascular pattern extraction (DBVPE), and analyses the computational workload involved in running software implementations on an embedded processor. The authors then present a comprehensive performance analysis of the VPE algorithm and examine in detail the various factors that contribute to processing latencies, including VPE recognition processing. In order to improve the efficiency of VPE processing in embedded devices, the authors offer details regarding the process needed to create a highly efficient application-specific processor and extend the base instruction set of the processor by using custom instructions for recognition processing. The authors implemented our proposed methodology in the context of a commercial extensible processor design flow using the Xtensa platform from Tensilica Inc. Our experiments show that our proposed methodology achieves a 3.95-fold increase in the vascular pattern recognition speed. Hence, the authors consider our technique to be efficient.

Inspec keywords: embedded systems; vein recognition; feature extraction

Other keywords: Tensilica Inc; application-specific processor; DBVPE algorithm; direction-based VPE algorithm; embedded processing architecture; vascular pattern recognition speed; embedded processor; VPE recognition processing; running software implementations; direction-based vascular pattern extraction; Xtensa platform; embedded devices; commercial extensible processor design flow; base instruction set

Subjects: Computer vision and image processing techniques; Image recognition

References

    1. 1)
      • 13. Biometrics.gov.: ‘Vascular pattern recognition’, http://www.biometrics.gov/Documents/VascularPatternRec.pdf (accessed July 2012).
    2. 2)
      • 5. Rosli, A.N.C., Ahmad, R.B., Shakaff, A.Y.M.: ‘Embedded system for biometric identification based on Iris detection’. Proc. Int. Conf. Electronic Design, Penang, Malaysia, December 2008, pp. 1–6.
    3. 3)
      • 4. Chu, S.W., Yeh, M.C., Cheng, K.T.: ‘A real-time, embedded face-annotation system’. Proc. ACM Int. Conf. Multimedia, Vancouver, Canada, October 2008, pp. 989–990.
    4. 4)
      • 10. MIPS Technologies: ‘32 and 4bit Cores’, http://www.mips.com (accessed November 2012).
    5. 5)
      • 16. Wang, L., Leedham, G.: ‘A thermal hand-vein pattern verification system’. Proc. Int. Conf. Advances in Pattern Recognition, Bath, UK, August 2005, pp. 58–65.
    6. 6)
      • 14. Kumar, A., Prathyusha, K.V.: ‘Personal authentication using hand vein triangulation and knuckle shape’, IEEE Trans. Image Process, 2009, 38, (9), pp. 2127–2136 (doi: 10.1109/TIP.2009.2023153).
    7. 7)
      • 7. Grabowski, K., Napieralski, A.: ‘Hardware architecture optimized for Iris recognition’, IEEE Trans. CSV T., 2011, 21, (9), pp. 1293–1303.
    8. 8)
      • 20. Analog Devices, Inc.: ‘ADSP-BF533’, http://www.analog.com/en/processors-dsp/blackfin/adsp-bf533/processors/product.html (accessed November 2012).
    9. 9)
      • 19. ARM Ltd.: ‘ARM926 Processor’, http://www.arm.com/products/processors/classic/arm9/arm926.php (accessed November 2012).
    10. 10)
      • 12. Aaraj, N., Ravi, S., Raghunathan, A., Jha, N.K.: ‘Hybrid architectures for efficient and secure face authentication in embedded systems’, IEEE Trans. VLSI Syst., 2007, 15, (3), pp. 269–308 (doi: 10.1109/TVLSI.2007.893608).
    11. 11)
      • 15. Lin, C.L., Fan, K.C.: ‘Biometric verification using thermal images of palm-dorsa vein patterns’, IEEE Trans. Circuits Syst. Video Technol., 2004, 14, (2), pp. 199–213 (doi: 10.1109/TCSVT.2003.821975).
    12. 12)
      • 17. Im, S.K., Park, H.M., Kim, S.W., Chung, C.K., Choi, H.S.: ‘Improved vein pattern extracting algorithm and its implementation’. Proc. Int. Conf. Consumer Electronics, Los Angles, USA, June 2000, pp. 2–3.
    13. 13)
      • 3. Pa, N.S., Chang, S.P.: ‘An embedded system for real-time facial expression recognition based on the extension theory’, Elsevier Comput. Math. Appl., 2011, 61, (8), pp. 2101–2106.
    14. 14)
      • 2. Schaumont, P., Hwang, D., Verbauwhede, I.: ‘Platform-based design for an embedded fingerprint authentication device’, Comput.-Aided Des. Integr. Circuits Syst., 2005, 24, (12), pp. 1929–1936 (doi: 10.1109/TCAD.2005.853709).
    15. 15)
      • 18. Im, S.K., Chio, H.S., Kim, S.W.: ‘A direction-based vascular pattern extraction algorithm for hand vascular pattern verification’, ETRI J., 2003, 25, (2), pp. 101–108 (doi: 10.4218/etrij.03.0102.0211).
    16. 16)
      • 9. Synopsys Inc.: ‘ARC cores’, http://www.synopsys.com (accessed November 2012).
    17. 17)
      • 8. Tensilica Inc.: ‘Xtensa 8 processor’, http://www.tensilica.com (accessed November 2012).
    18. 18)
      • 6. Judith, L.J., Raul, S.R., Belen, F.S.: ‘Iris biometrics for embedded systems’, IEEE Trans. VLSI Syst., 2011, 19, (2), pp. 274–282 (doi: 10.1109/TVLSI.2009.2033701).
    19. 19)
      • 1. Jain, A., Bolle, R., Pankanti, S.: ‘Biometrics persona identification in networked society’ (Kluwer Academic Publishers, 1999).
    20. 20)
      • 11. Guptat, P., Ravi, S., Raghunathan, A., Jhat, N.K.: ‘Efficient fingerprint-based user authentication for embedded systems’. Proc. Design Autom. Conf., June 2005, Anaheim. USA, pp. 244–247.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cds.2012.0192
Loading

Related content

content/journals/10.1049/iet-cds.2012.0192
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address