DOI QR코드

DOI QR Code

Robust Face Recognition Against Illumination Change Using Visible and Infrared Images

가시광선 영상과 적외선 영상의 융합을 이용한 조명변화에 강인한 얼굴 인식

  • Kim, Sa-Mun (Department of Control and Robotics Engineering, Chungbuk University) ;
  • Lee, Dea-Jong (Department of Control and Robotics Engineering, Chungbuk University) ;
  • Song, Chang-Kyu (Department of Control and Robotics Engineering, Chungbuk University) ;
  • Chun, Myung-Geun (Department of Control and Robotics Engineering, Chungbuk University)
  • 김사문 (충북대학교 제어로봇공학과) ;
  • 이대종 (충북대학교 제어로봇공학과) ;
  • 송창규 (충북대학교 제어로봇공학과) ;
  • 전명근 (충북대학교 제어로봇공학과)
  • Received : 2014.03.09
  • Accepted : 2014.05.23
  • Published : 2014.08.25

Abstract

Face recognition system has advanctage to automatically recognize a person without causing repulsion at deteciton process. However, the face recognition system has a drawback to show lower perfomance according to illumination variation unlike the other biometric systems using fingerprint and iris. Therefore, this paper proposed a robust face recogntion method against illumination varition by slective fusion technique using both visible and infrared faces based on fuzzy linear disciment analysis(fuzzy-LDA). In the first step, both the visible image and infrared image are divided into four bands using wavelet transform. In the second step, Euclidean distance is calculated at each subband. In the third step, recognition rate is determined at each subband using the Euclidean distance calculated in the second step. And then, weights are determined by considering the recognition rate of each band. Finally, a fusion face recognition is performed and robust recognition results are obtained.

얼굴인식은 인식과정에서 인식자에게 거부감을 유발하지 않고, 적극적인 행위 없이 자동으로 인식 과정을 거치는 장점이 있다. 그러나 촬영 환경에서의 조명 변화로 인하여 다른 인식 방법인 지문 인식이나 홍채 인식에 비하여 인식률이 저하되는 단점이 있다. 따라서 본 논문에서는 퍼지 선형판별분석법을 기반으로 가시광선 영상과 적외선 영상의 웨이블릿 대역의 선택적 융합방법을 이용하여 조명 변화에 강인한 얼굴 인식 방법을 제안한다. 첫 번째 단계에서 가시광선 영상과 적외선 영상을 웨이블릿 변환하여 4개의 대역으로 분할한다. 두 번째 단계에서 각 대역에 해당하는 학습영상과 테스트 영상의 유클리디안 거리를 계산한다. 세 번째로 앞서 계산된 유클리디안 거리를 이용하여 각 대역에서의 인식 실험을 수행하고, 4개 대역에서의 인식률을 고려하여 가중치를 설정한다. 마지막으로 부여된 가중치와 해당 대역의 유클리디안 거리를 융합하여 얼굴인식을 수행하여 외부 변화에 강인한 얼굴 인식 결과를 얻었다.

Keywords

References

  1. A. Torabi, et., al, "An iterative integrated framework for thermal-visible image registration, sensor fusion, and people tracking for video surveillance application", Computer Vision and Image understanding, Vol. 116, pp.210-221, 2012. https://doi.org/10.1016/j.cviu.2011.10.006
  2. Myung Geun Chun, Seong G. Kong. "Focusing in thermal imagery using morphological gradient operator", Pattern Recognition Letters, Vol. 38, pp.20-25, 2014. https://doi.org/10.1016/j.patrec.2013.10.023
  3. Wong, W.K., Zhao, H., "Eyeglasses removal of thermal image based on vision information", Information Fusion, Vol.14, pp.163-176, 2013. https://doi.org/10.1016/j.inffus.2011.09.002
  4. Waled Hussein Al-Arashi, Haidi Ibrahim, Shahrel Azmin Suandi. "Optimizing principal component analysis performance for face recognition using genetic algorithm", Neurocomputing, Vol.128, pp.415-420, 2014 https://doi.org/10.1016/j.neucom.2013.08.022
  5. Bai-ling Zhang, Haihong Zhang, Shuzhi Sam Ge. "Face recognition by applying wavelet subband representation and kernel associative memory", Neural Networks, IEEE Transactions on, Vol. 15, pp.166-177, 2004. https://doi.org/10.1109/TNN.2003.820673
  6. Lin Lan, Zhao Ge, Tang Yan-Dong, Tian Jian-Dong, He Si-Yuan. "Illumination Compensation for Face Recognition Using Only One Image", Acta Automatica Sinica Vol.39, pp.2090-2099, 2013 https://doi.org/10.1016/S1874-1029(14)60001-X
  7. Seonkeol Kim, Hang-Bong Kang. "Visible Image Enhancement Method Considering Thermal Information from Infrared Image", JBE Vol.18, pp.550-558, 2013. https://doi.org/10.5909/JBE.2013.18.4.550
  8. Quan-Sen Sun, Sheng-Gen Zeng, Yan Liu, Pheng-Ann Heng, De-Shen Xia. "A new method of feature fusion and its application in image recognition", Pattern Recognition, Vol.38, pp.2437-2448, 2005. https://doi.org/10.1016/j.patcog.2004.12.013
  9. Keun-Chang Kwak, Witold Pedrycz. "Face recognition using a fuzzy fisherface classifier", Pattern recognition Vol.38, pp.1717-1732, 2005. https://doi.org/10.1016/j.patcog.2005.01.018
  10. Jin-Il Park, Wook-Jae Lee, Jae-Hoon Cho, Chang-Kye Song, Myung-Geun Chun, "Gait Recognition and Person Identification for Surveillance Robots", Journal of Institute of Control, Robotics and Systems, Vol.15, pp.511-518, 2009. https://doi.org/10.5302/J.ICROS.2009.15.5.511
  11. Lu J, Plataniotis K.N, Venetsanopoulos, A.N. "Face recognition using LDA-based algorithms", Neural Networks, IEEE Transactions on, Vol. 14, pp.195-200, 2003. https://doi.org/10.1109/TNN.2002.806647
  12. Rafael C. Gonzalez, Richard E. Woods. "Digital Image Processing", Prentice Hall, 2007.
  13. T. Stathaki, Image Fusion: Algorithms and Application, Academic Press, 2008.