DOI QR코드

DOI QR Code

Development of Feature Extraction Algorithm for Finger Vein Recognition

지정맥 인식을 위한 특징 검출 알고리즘 개발

  • 김태훈 (선문대학교 정보통신공학과) ;
  • 이상준 (선문대학교 스마트자동차공학부)
  • Received : 2018.05.28
  • Accepted : 2018.07.12
  • Published : 2018.09.30

Abstract

This study is an algorithm for detecting vein pattern features important for finger vein recognition. The feature detection algorithm is important because it greatly affects recognition results in pattern recognition. The recognition rate is degraded because the reference is changed according to the finger position change. In addition, the image obtained by irradiating the finger with infrared light is difficult to separate the image background and the blood vessel pattern, and the detection time is increased because the image preprocessing process is performed. For this purpose, the presented algorithm can be performed without image preprocessing, and the detection time can be reduced. SWDA (Down Slope Trace Waveform) algorithm is applied to the finger vein images to detect the fingertip position and vein pattern. Because of the low infrared transmittance, relatively dark vein images can be detected with minimal detection error. In addition, the fingertip position can be used as a reference in the classification stage to compensate the decrease in the recognition rate. If we apply algorithms proposed to various recognition fields such as palm and wrist, it is expected that it will contribute to improvement of biometric feature detection accuracy and reduction of recognition performance time.

본 연구는 지정맥 인식에 중요한 정맥 패턴 특징검출을 위한 알고리즘이다. 특징검출 알고리즘은 패턴인식 시 인식결과에 많은 영향을 끼치므로 중요하다. 인식률은 손가락 위치 변화에 따라 기준도 변화되므로 저하되는 특징을 가지고 있다. 또한, 손가락에 적외선 광을 조사하여 획득한 영상은 영상 배경과 혈관 패턴을 분리하기에 어렵고, 영상 전처리과정을 수행하므로 검출시간이 증대되는 특징을 가지고 있다. 이를 위해, 제시하는 알고리즘은 영상 전처리과정이 없이 수행되어 검출 시간을 줄일 수 있고, 지정맥 영상에 SWDA(Shifted Waveform Data Analysis) 알고리즘을 적용하여 손가락 마디 위치 및 정맥 패턴 검출이 가능한 특징을 가지고 있다. 적외선 투과율이 낮아 상대적으로 어두운 정맥 영상도 검출 오류 최소화가 가능한 특징을 보였다. 또한, 손가락 마디 위치는 분류 단계에서 기준으로 활용하면 인식률 저하를 보완할 수 있는 특징을 가지고 있다. 추후 손바닥, 손목 등 신체 여러 인식분야에 제안하는 알고리즘을 적용한다면 생체 특징 검출 정확도 향상 및 인식 수행 시간 감소에 기여할 것으로 기대된다.

Keywords

References

  1. Eun Kim, The probability of iris-like '1 billionth' ... Security pass? Steal from my body [Internet], http://www.dt.co.kr/contents.html?article_no=2018032102101832816001&ref=nave.
  2. Naver knowledge encyclopedia, Biometrics [Internet], http://terms.naver.com/entry.nhn?docId=3473651&cid=58439 &categoryId=58439.
  3. NewsWire, Tractica, Biomatrix market forecasts to $ 14.9 billion in 2024 [Internet], http://www.newswire.co.kr/newsRead.php?no=792234.
  4. Unan Lee, Korea Future Technology Education, Seminar on Industry through Biometrics Technology [Internet], http://www.gukjenews.com/news/articleView.html?idxno=725583.
  5. Eui Chul Lee, Hyeon Chang Lee and Kang Ryoung Park, "Finger vein recognition using minutia‐based alignment and local binary pattern‐ based feature extraction," International Journal of Imaging Systems and Technology, Vol.19, No.3, pp.179-186, 2009. https://doi.org/10.1002/ima.20193
  6. Yuhang Ding, Dayan Zhuang, and Kejun Wang, "A study of hand vein recognition method," in Proceedings of the IEEE International Conference Mechatronics and Automation, pp.2106-2110, 2005.
  7. Eui Chul Lee, "A Method for Improving Vein Recognition Performance by Illumination Normalization," Journal of the Korea Institute of Information and Communication Engineering, Vol.17, No.2, pp.423-430, 2013. https://doi.org/10.6109/jkiice.2013.17.2.423
  8. J. Kim, M. Kim, I. Won, S. Yang, K. Lee, and W. Huh, "A biomedical Signal Segmentation Algorithm for Event Detection Based on Slope Tracing," Conf Proc IEEE Eng Med Biol Soc., pp.1889-1892, 2009.
  9. Hyun Kim and Hakil Kim, "Rotation-Scale-Translation -Intensity Invariant Algorithm for Fingerprint Identification," The Institute of Electronics Engineers of Korea - S, Vol.35, No.6, pp.838-850, 1998.
  10. Woo-Suk Yang. "Biometric Personal Identification Using Iris Image," The Journal of the Institute of Internet, Broadcasting and Communication, Vol.7, No.6, pp.73-82. 2007.
  11. Myung-Hyun Yoo, Jeong-Seon Park, Sang-Woong Lee, Hyong-Chol Choi, and Seong-Whan Lee, "The State of the Art and the Prospects for the Face - based Biometrics," Communications of the Korean Institute of Information Scientists and Engineers, Vol.19, No.7, pp.22-31, 2001.
  12. Jason Kim and Saewoom Lee, "Trend and prospect of telebio recognition technology using bio-signals," Review of KIISC, Vol.26, No.4, pp.41-46, 2016.
  13. Heesung Kim, Junhee Cho, "A Method for Finger Vein Recognition using a New Matching Algorithm," Journal of KISS : Software and Applications, Vol.37, No.11, pp.859-865, 2010.
  14. Mingoo Kang, "Design of Image Recognition Module for Face and Iris Area based on Pixel with Eye Blinking," Journal of Internet Computing and Services, Vol.18, No.1, pp.21-26, 2017. https://doi.org/10.7472/JKSII.2017.18.1.21
  15. Ju-won Lee and Byeong-ro Lee, "ROI Extraction and Enhancement for Finger Vein Recognition," Journal of the Korea Institute of Information and Communication Engineering, Vol.19, No.4 pp.948-953, 2015. https://doi.org/10.6109/jkiice.2015.19.4.948
  16. HeeKyung Kim, Seungmain Lee and Bongsoon Kang, "Enhanced Vein Detection Method by Using Image Scaler Based on Poly Phase Filter," Journal of the Korea Institute of Information and Communication Engineering, Vol.22, No.5, pp.734-739, 2018. https://doi.org/10.6109/JKIICE.2018.22.4.734