Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Facial Expression Recognition by Combining Adaboost and Neural Network Algorithms

에이다부스트와 신경망 조합을 이용한 표정인식

  • Received : 2010.06.22
  • Accepted : 2010.11.06
  • Published : 2010.12.25
Download PDF
⟨ Previous Next ⟩

Abstract

Human facial expression shows human's emotion most exactly, so it can be used as the most efficient tool for delivering human's intention to computer. For fast and exact recognition of human's facial expression on a 2D image, this paper proposes a new method which integrates an Discrete Adaboost classification algorithm and a neural network based recognition algorithm. In the first step, Adaboost algorithm finds the position and size of a face in the input image. Second, input detected face image into 5 Adaboost strong classifiers which have been trained for each facial expressions. Finally, neural network based recognition algorithm which has been trained with the outputs of Adaboost strong classifiers determines final facial expression result. The proposed algorithm guarantees the realtime and enhanced accuracy by utilizing fastness and accuracy of Adaboost classification algorithm and reliability of neural network based recognition algorithm. In this paper, the proposed algorithm recognizes five facial expressions such as neutral, happiness, sadness, anger and surprise and achieves 86~95% of accuracy depending on the expression types in real time.

표정은 사람의 감정을 표현하는 대표적인 수단이다. 이러한 이유로 표정은 사람의 의도를 컴퓨터에 전하는데 효과적인 방법으로 사용될 수 있다. 본 논문에서는 2D 영상에서 사람의 표정을 보다 빠르고 정확하게 인식하기 위해 Discrete Adaboost 알고리즘과 신경망 알고리즘을 통합하는 방법을 제안한다. 1차로 Adaboost 알고리즘으로 영상에서 얼굴의 위치와 크기를 찾고, 2차로 표정별로 학습된 Adaboost 강분류기를 이용하여 표정별 출력 값을 얻으며, 이를 마지막으로 Adaboost 강분류기 값으로 학습된 신경망 알고리즘의 입력으로 이용하여 최종 표정을 인식한다. 제안하는 방법은 실시간이 보장된 Adaboost 알고리즘의 특성과 정확성을 개선하는 신경망 기반 인식기의 신뢰성을 적절히 활용함으로서 전체 인식기의 실시간성을 확보하면서도 정확성을 향상시킨다. 본 논문에서 구현된 알고리즘은 평온, 행복, 슬픔, 화남, 놀람의 5가지 표정에 대해 평균 86~95%의 정확도로 실시간 인식이 가능하다.

Keywords

References

  1. 이용재, 이칠우, “전역 및 부분 특징 정보를 이용한 제스처 인식,” 정보과학회논문지: 소프트웨어및 응용, 32권, 8호, pp. 759-768, 2005.
  2. Andreas Haag, Silke Goronzy, Peter Schaich and Jason Williams, "Emotion Recognition Using Bio-sensors: First Steps towards an Automatic System," In Proceedings of LNCS, vol.3068, pp.36-48, 2004.
  3. 심귀보, 박창현, "음성인식으로 감정인식 요소 분석," 퍼지 및 지능 시스템학회 논문지, 11권, 11호, pp. 510-515, 2001.
  4. 고현주, 이대종, 박장환, 전명근, "웨이블릿 변환을 이용한 음성에서의 감정 추출 및 인식 기법," 퍼지및 지능 시스템학회 논문지, 14권, 2호, pp. 150-155, 2004. https://doi.org/10.5391/JKIIS.2004.14.2.150
  5. B. Fasela, Juergen Luettin, “Automatic facial expression analysis: a survey,” Pattern Recognition, vol. 36, pp. 259-275, 2003. https://doi.org/10.1016/S0031-3203(02)00052-3
  6. A. Lanitis, C. J. Taylor, and T. F. Cootes,“Automatic interpretation and coding of face images using flexible models,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 743-756, 1997. https://doi.org/10.1109/34.598231
  7. Yeongjae Cheon, Daijin Kim, "A Natural Facial Expression Recognition Using Differential-AAM and k-NNS," Pattren Recognition, vol.42, no.7,pp.1340-1350, 2008.
  8. Bouchra Abboud, Franck Davoine, Mo Dang, "Facial expression recognition and synthesis based on an appearance model," Signal Processing: Image Communication, vol.19, no.8, pp.723-740, 2004.
  9. Yongsheng Gao, Maylor K. H. Leung, Siu Cheung Hui, Mario W. Tananda, “Facial Expression Recognition From Line-Based Caricatures,” IEEE Transactions on Systems, Man, and Cybernetics—Part A: Systems and Humans, vol. 33, no. 3, May. 2003. https://doi.org/10.1109/TSMCA.2003.817057
  10. C. L. Lisetti and D. E. Rumelhart, “Facial expression recognition using a neural network,” The 11th International Flairs Conference. AAAI Press, 1998.
  11. C. Padgett, G.W. Cottrell, "Representing face images for emotion classification," Proc. Conf. Advances in Neural Information Processing Systems, vol. 9, pp. 894-900, 1997.
  12. Do Hyoung Kim, Sung Uk Jung, Myung Jin Chung, “Extension of cascaded simple feature based face detection to facial expression recognition,” Pattern Recognition Letters, vol. 29, pp. 1621-1631, 2008. https://doi.org/10.1016/j.patrec.2008.04.006
  13. DuanDuan Yang, LianWen Jin, JunXun Yin, LiXin Zhen, JianCheng Huang, “Facial Expression Recognition with Pyramid Gabor Features and Complete Kernel Fisher Linear Discriminant Analysis”, International Journal of Information Technology, vol. 11, no. 9, pp 91-100, 2005.
  14. Irene Kotsia, Stefanos Zafeiriou, Ioannis Pitas, “Texture and shape information fusion for facial expression and facial action unit recognition,” Pattern Recognition, vol. 41, pp. 833-851, 2008. https://doi.org/10.1016/j.patcog.2007.06.026
  15. C. Padgett, G. Cottrell, “Representing Face Image for Emotion Classification," Advances in Neural Information Processing Systems, vol. 9, pp. 894-900, 1996.
  16. J. Lien, T. Kanade, J. Cohn, C. Li, “Automated facial expression recognition based on FACS action units,” IEEE Proceedings of the Second International Conference on Automatic Face and Gesture Recognition, 1998.
  17. B. Fasel, J. Luettin, “Recognition of a symmetric facial action unit activities and intensities,” Proceedings ofthe International Conference on Pattern Recognition, pp. 1100-1103, 2000.
  18. Paul Viola, Michael J. Jones, "Robust Real-Time Face Detection," International Journal of Computer Vision, vol. 57, no. 2, pp. 137-154, 2004. https://doi.org/10.1023/B:VISI.0000013087.49260.fb
  19. Y. Freund and R. E. Schapire, "A Short Introduction to Boosting", Journal of Japanese Society for Artificial Intelligence, vol. 14, no. 2, Sep. 1999.
  20. Japanese Female Facial Expression JAFFE http://kasrl.org/jaffe.html

Cited by

  1. A Study on Chaff Echo Detection using AdaBoost Algorithm and Radar Data vol.23, pp.6, 2013, https://doi.org/10.5391/JKIIS.2013.23.6.545