2D Face Image Recognition and Authentication Based on Data Fusion

데이터 퓨전을 이용한 얼굴영상 인식 및 인증에 관한 연구

  • 박성원 (한국 IBM 소프트웨어연구소) ;
  • 권지웅 (서울대학교 전기컴퓨터공학부, 자동화시스템공동연구소) ;
  • 최진영 (서울대학교 전기컴퓨터공학부, 자동화시스템공동연구소)
  • Published : 2001.08.01

Abstract

Because face Images have many variations(expression, illumination, orientation of face, etc), there has been no popular method which has high recognition rate. To solve this difficulty, data fusion that fuses various information has been studied. But previous research for data fusion fused additional biological informationUingerplint, voice, del with face image. In this paper, cooperative results from several face image recognition modules are fused without using additional biological information. To fuse results from individual face image recognition modules, we use re-defined mass function based on Dempster-Shafer s fusion theory.Experimental results from fusing several face recognition modules are presented, to show that proposed fusion model has better performance than single face recognition module without using additional biological information.

얼굴인식은 이미지의 많은 변동(표정, 조명, 얼굴의 방향 등)으로 인해 한 가지 인식 방법으로는 높은 인식률을 얻기 어렵다. 이러한 어려움을 해결하기 위해, 여러 가지 정보를 융합시키는 데이터 퓨전 방법이 연구되었다. 기존의 데이터 퓨전 방법은 보조적인 생체 정보(지문, 음성 등)를 융합하여 얼굴인식기를 보조하는 방식을 취하였다. 이 논문에서는 보조적인, 생체 정보를 사용하지 않고, 기존의 얼굴인식방법을 통해 얻어지는 상호보완적인 정보를 융합하여 사용하였다. 개별적인 얼굴인식기의 정보를 융합하기 위해, 전체적으로는 Dempster-Shafer의 퓨전이론에 근거하면서, 핵심이 되는 질량함수를 새로운 방식으로 재정의학 퓨전모델을 제안하였다. 제안된 퓨전모델을 사용하여 개별적인 얼굴인식기의 정보를 융합한 결과, 보조적인 생체정보 없이, 개별적인 얼굴인식기보다 나은 인식률을 얻을 수 있었다.

Keywords

References

  1. 서울대학교 석사학위논문 데이터 퓨전을 이용한 얼굴영상 인식 및 인증에 관한 연구 박성원
  2. Proceedings of IEEE v.83 Human and machine recognition of faces : A survey R. Chellappa;C. Willson;S. Sitohey
  3. 1997 European Conference on Security and Detection Audio-visual person recognition:an evaluation of data fusion strategies C. C. Chibelushi;F. Deravi;J. S. Mason
  4. 1997 Sixth International Conference on Image Processing and Its Application v.1 Feature-level data fusion for bimodal person recognition C. C. Chibelushi;J. S. D. Mason;F. Deravi
  5. IEEE Trans. Nerual Network v.8 no.1 Face Recognition:A Convolutional Neural Network Approach C. L. Giles;A. C. Tsoi;A. D. Back
  6. Evidence Theory and its application v.1 J. W. Guan;D. A. Bell
  7. Proceedings of the IEEE v.85 no.1 An introduction to multisensor data fusion D. L. Hall;J. Llinas
  8. IEEE trans. Pattern Analysis and Machine Intelligence v.17 no.12 Extending the feature vector for automatic face recognition X. Jia;M. S. Nixon
  9. Pattern Recognition v.29 no.5 Locating and Extracting the eye in human face images K. M. Lam;H. Yan
  10. IEEE trans. Pattern Analysis and Machine Intellegence v.20 no.7 An analytic-to-holistic approach for face recognition based on a single frontal view K.-M. Lam;H. Yan
  11. IEEE trans. Nerual Network v.8 no.1 Face recognition/detection by probabilistic decision-based nerual network S. H. Lin;S. Y. Kung
  12. IECON '90., 16th Annual Conference of IEEE v.1 A tutorial on multisensor integration and fusion R. C. Luo;M. G. Kay
  13. Intelligent Information Systems, Australian and New Zealand Conference on Neural Networks for learning human facial feature from labeled graph models A. R. Mirhosseini;H. Yan
  14. Optical Eng. v.37 no.3 Adaptive deformable model for mouth boundary detection A. R. Mrihosseini;H. Yan;K. M. Lam
  15. ICASSP 98 v.5 Hidden Markov Model for face recognition A. V. Nefian;M. H. Hayes
  16. Proceedings of the IEEE v.77 no.2 A tutorial on hidden Markov models and selected applications in speech recognition L. R. Rabiner
  17. Image and Vision Computing v.12 no.8 HMM-based architecture for face identification F. Samaria;S. Young
  18. Mathematical Theory of Evidence G. G. Shafer
  19. Multisensor Fusion and Integration for Intelligent Systems, 1994. IEEE international Conference on MFI '94. Audio-visual sensor fusion system for intelligent sound sensing K. Takahashi;H. Yamasaki
  20. Proceedings of International Conference on Pattern Recognition Face recognition using eigenfaces M. Turk;A. Pentland