The Segmentation Algorithm for Hand Vein Images Based on Improved Niback Algorithm

Abstract:

The local dynamic threshold segmentation algorithm, Niblack algorithm, is more suitable for hand vein images segmentation by comparing the common- used algorithms. But the traditional Niblack algorithm has weakness, so this paper proposed an improved Niblack algorithm in which the coefficient is adaptive estimated. The results show that the improved algorithm can better segment the hand vein outlines, preserve the vein original characteristics, and meet the needs of the follow-up feature extraction and recognition.

• Periodical: Advanced Materials Research (Volumes 532-533)
• Pages: 1558-1562
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.532-533.1558
• Online since: June 2012
• Authors: Xiu Mei Guo, Wei Dong Zhou, Cheng Yi Wang
• Keywords: Adaptived Coefficient, Hand Vein Segmentation, Improved Niback Algorithm

References

[1] Wang K J, Zhang Y. Hand vein recognition based on multi supplemental features of multi-classifier fusion decision [ C ]. Proceedings of the 2006 IEEE, 2006: 1790-1795.

DOI: 10.1109/icma.2006.257486

[2] PARK G, SANG K IM, CHOIH. A person identification algorithm utilizing hand vein pattern[C]. Korea Signal processing Conference, 1997, 10(1): 1107-1110.

[3] Wang L Y, Leedham G, Cho S Y D. Minutiae feature analysis for infrared hand vein pattern biometrics. Pattern Recog-nition, 2008, 41(3): 920-929.

DOI: 10.1016/j.patcog.2007.07.012

[4] Shahin M, Badawi A, Kamel M. Biometric authentication using fast correlation of near infrared hand vein patterns. International Journal of Biometrical and Medical Sciences, 2007, 2(3): 141-148.

[5] Vlachos M, Dermatas E. Vein segmentation in infrared images using compound enhancing and crisp clustering. In: Proceedings of the 6th International Conference on Computer Vision Systems. Santorini, Greece: Springer, 2008. 393-402.

DOI: 10.1007/978-3-540-79547-6_38

[6] Zhang Y B, Li Q, You J, Bhattacharya P. Palm vein ex-traction and matching for personal authentication. In: Pro-ceedings of International Conference on Visual Information Systems. Shanghai, China: Springer, 2007. 154-164.

DOI: 10.1007/978-3-540-76414-4_16

[7] Im S K, Choi H S. A direction-based vascular pattern extraction algorithm for hand vascular pattern verification. Electronica and Telecommunications Research Institute Journal, 2003, 25(2): 101- 108.

DOI: 10.4218/etrij.03.0102.0211

[8] Lopez S, Gonzalez A. Hand veins segmentation and matching under adverse conditions. In: Proceedings of the SPIE on Bioengineered and Bioinspired Systems. Bellingham, USA: SPIE, 2003. 166-177.

DOI: 10.1117/12.499035

[9] Chen L K, Zheng H, Li L, Xie P, Liu S. Near-infrared dorsal hand vein image segmentation by local thresholding using grayscale morphology. In: Proceedings of the 1st International Conference on Bioinformatics and Biomedical Engi-neering. Wu han , China: 2007. 868-871.

DOI: 10.1109/icbbe.2007.226

[10] Zhang Z B, Ma S L, Han X. Multiscale feature extraction of finger-vein patterns based on curvelets and local interconnection structure neural network. In: Proceedings of the18th International Conference on Pattern Recognition. HongKong, China: IEEE, 2006. 145-148.

DOI: 10.1109/icpr.2006.848

[11] Niblack W. An Introduction to Image Processing[C]. NJ: Prentice-Hall, 1986: 115-116.