Multimedia Tools and Applications

, Volume 76, Issue 5, pp 6859–6887 | Cite as

Enhanced maximum curvature descriptors for finger vein verification

  • Munalih Ahmad Syarif
  • Thian Song Ong
  • Andrew B. J. Teoh
  • Connie Tee
Article

Abstract

Maximum Curvature Method (MCM) is one of the promising methods for finger vein verification. MCM scans the curvature of the vein image profiles within a finger for feature extraction. However, the quality of the image can be poor due to variations in illumination and sensor conditions. Furthermore, traditional MCM matching of the vein pattern requires extensive processing time. To address these limitations, we propose an integrated Enhanced Maximum Curvature (EMC) method with Histogram of Oriented Gradient (HOG) descriptor for finger vein verification. Unlike MCM, EMC incorporates an enhancement mechanism to extract small vein delineation that is hardly visible in the extracted vein patterns. Next, HOG is applied instead of image binarization to convert a two-dimensional vein image into a one-dimensional feature vector for efficient matching. The HOG descriptor is able to characterize the local spatial representation of a finger vein by capturing the gradient information effectively. The proposed method is evaluated based on two datasets namely the PKU Finger Vein Database (V4) and SDUMLA-HMT finger vein database. Experiments show promising verification results with equal error rates as low as 0.33 % for DB1 and 0.14 % for DB2 respectively, when EMC+HOG+SVM is applied.

Keywords

Biometrics Finger vein Support vector machine Histogram of oriented gradient Maximum curvature 

References

  1. 1.
    Aziz WNAA, Seman K, Abdullah I, Sayuti NS (2013) Finger vein minutiae points extraction based on maximum curvature points in image profile and finger print application methods. Aust J Basic Appl Sci 7:751–756Google Scholar
  2. 2.
    Bertozzi M, Broggi A, Del Rose M, Felisa M, Rakotomamonjy A, Suard F (2007) A pedestrian detector using histograms of oriented gradients and a support vector machine. In: Proceedings of the 2007 IEEE, WAGoogle Scholar
  3. 3.
    Chang CC, Lin CJ (2011) LIBSVM: A library for support vector machine. ACM Trans Intell Syst Technol 2(3):1–27CrossRefGoogle Scholar
  4. 4.
    Dalal N, Trigss B. (2005) Histograms of Oriented Gradients for Human Detection. In: International conference on computer vision and pattern recognition, MontbonnotGoogle Scholar
  5. 5.
    Dong S, Yang J, Chen Y, Wang C, Zhang X, Park DS (2015) Finger vein recognition based on Multi-Orientation weighted symmetric local graph structure. KSII Trans Internet Inf Syst 9(10):4126–4142Google Scholar
  6. 6.
    Frangi AF, Niessen WJ, Vincken KL, Viergevr MA (1998) multiscale vessel enhancement filtering. Med Imag Comput Comput Assist Interv - MICCAI 1998:130–137Google Scholar
  7. 7.
    Gabarda S, Cristobal G (2007) Blind image quality assessment through anisotropy. J Opt Soc Am A 24Google Scholar
  8. 8.
    Hsu W, Chang CC, Lin CJ A Practical Guide to Support Vector Classification, (2010). [Internet]. Available: http://www.csie.ntu.edu.tw/cjlin/papers/guide/guide.pdf
  9. 9.
    Hartung D, Tistarelli M (2013) Busch, vein minutia Cylinder-Codes (v-MCC). In: 2013 international conference on biometricsGoogle Scholar
  10. 10.
    Huang B, Dai Y, Li R, Tang D, Li W (2010) Finger-vein Authentication Based on Wide Line Detector and Pattern norMalization. In: 2010 International Conference on Pattern RecognitionGoogle Scholar
  11. 11.
    Joon HC, Song W, Kim T, Lee SR, Kim HC (2009) Finger vein extraction using gradient norMalization and principal curvature. In: Proceedings of the SPIE, p 2009Google Scholar
  12. 12.
    Jang Y, Kang B, Park KR (2008) A study on touchless finger vein recognition robust to the alignment and rotation of finger. J Korea Inf Process Soc 15-B:275–284Google Scholar
  13. 13.
    Juang CF, Chiu SH, Shiu SJ, Huang HJ Block Histogram-Based Support Vector Machine For Skin Color SegmentationGoogle Scholar
  14. 14.
    Kang W (2012) Vein Pattern Extraction Based on Vectograms of Maximal Intra-neighbor. Pattern Recogn Lett 33:1916–1923CrossRefGoogle Scholar
  15. 15.
    Kohler T, Budai A, Kraus MF, Odstrcilik J (2013) Automatic No-Reference Quality Assessment for Retinal Fundus Images using Vessel Segmentation, Computer-Based Medical Systems (CBMS). In: 2013 IEEE 26th International Symposium PortoGoogle Scholar
  16. 16.
    Lian Z, Rui Z, Chengbo Y (2008) Study on the Identity Authentication System of Finger Vein. In: 2nd International Conference on Bioninformatics and Bimedical Engineering. ICCBE, ShanghaiGoogle Scholar
  17. 17.
    Lee EC, Lee HC, Park KR (2009) Finger Vein Recognition Using Minutia-Based Alignment and Local Binary Pattern-Based Feature Extraction. Wiley Periodicals, Inc., pp 179–186Google Scholar
  18. 18.
    Miura N, Nagasaka A, Miyatake T (2005) Extraction of Finger-Vein patterns using maximum curvature points in image profiles in MVA, vol 2005. IAPR Conference on Machine Vision Applications, Tsukuba Science CityGoogle Scholar
  19. 19.
    Miura N, Nagasaka A, Miyatake T (2004) Feature extraction of finger vein patterns based on repeated line tracking and its application to personal identification. Machine Vision and Applications:194–203Google Scholar
  20. 20.
    Ong TS, Teng JH, Muthu KS, Teoh ABJ (2013) Multi-instance Finger Vein Recgnition Using Minutiae Matching. In: 2013 6th International Congress on Image and Signal ProcessingGoogle Scholar
  21. 21.
    Rosdi BA, Shing CW, Suandi SA (2011) Finger vein recognition using local line binary pattern. Sens (Basel) 11:11357–11371CrossRefGoogle Scholar
  22. 22.
    Recognition Algorithm Test Engine (Peking University), [Internet]. Accessed: http://rate.pku.edu.cn/RATE/showdatabase?database=1018
  23. 23.
    SDUMLA-HMT Database, [Internet]. Acessed: http://mla.sdu.edu.cn/sdumla-hmt.html
  24. 24.
    Tibshirani R (1996) Regression Shrinkage and Selection via the LASSO. J R Stat Soc B:267–288Google Scholar
  25. 25.
    Wen X, Zhao J, Liang X (2010) Research enhancing human finger vein pattern characteristics. In: 2010 Asia-Pacific conference on power electronics and designGoogle Scholar
  26. 26.
    Wang K, Ma H, Popoola O, Li X (2010) A Novel Finger Vein Pattern Extraction Method Using Oriented Filtering Technology. In: Proceedings of the 8th World Congress on Intelligent Control and Automation JinanGoogle Scholar
  27. 27.
    Xi X, Yang G, Yin Y, Meng X (2013) Finger Vein Recognition with Personalized Feature Selection. Sens ISSN 1424-8220:11243–11259CrossRefGoogle Scholar
  28. 28.
    Yanagawa T, Aoki S, Ohyama T (2007) Human Finger Vein Images are Diverse and Its Patterns are Useful for Personal Identification, MHF 2007-12, FukuokaGoogle Scholar
  29. 29.
    Yang J, Shi Y, Yang J (2010) Finger-Vein Recognition Based on a Bank Gabor Filters. SpringerGoogle Scholar
  30. 30.
    Yang G, Xi C, Yin Y (2012) Finger vein recognition based on a personalized best bit map. Sensors 12:1738–1757CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Munalih Ahmad Syarif
    • 1
  • Thian Song Ong
    • 1
  • Andrew B. J. Teoh
    • 2
  • Connie Tee
    • 1
  1. 1.Faculty of Information Science and TechnologyMultimedia UniversityMelakaMalaysia
  2. 2.School of Electrical and Electronics EngineeringYonsei UniversitySeoulKorea

Personalised recommendations