Adaptive Facial Expression Recognition System based on Gabor Wavelet Neural Network

가버 웨이블릿 신경망 기반 적응 표정인식 시스템

  • 이상완 (한국과학기술원 전자전산학과) ;
  • 김대진 (한국과학기술원 인간친화 복지 로봇 시스템 연구센터) ;
  • 김용수 (대전대학교 컴퓨터 공학부) ;
  • 변증남 (한국과학기술원 전자전산학과)
  • Published : 2006.02.01


In this paper, adaptive Facial Emotional Recognition system based on Gabor Wavelet Neural Network, considering six feature Points in face image to extract specific features of facial expression, is proposed. Levenberg-Marquardt-based training methodology is used to formulate initial network, including feature extraction stage. Therefore, heuristics in determining feature extraction process can be excluded. Moreover, to make an adaptive network for new user, Q-learning which has enhanced reward function and unsupervised fuzzy neural network model are used. Q-learning enables the system to ge optimal Gabor filters' sets which are capable of obtaining separable features, and Fuzzy Neural Network enables it to adapt to the user's change. Therefore, proposed system has a good on-line adaptation capability, meaning that it can trace the change of user's face continuously.


  1. Gyu-Tae Park, 'A Study on Extraction of Emotion from Facial Image using Soft Computing Techniques', Ph.D Thesis, Dept. of Electrical Engineering and Computer Science, KAIST.1998
  2. S.B. Gokturk, et aI., 'Model-Based Face Tracking for View-Independent Facial Expression Recognition', Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 272 - 278.,1998
  3. A. Kapoor, Q. Yuan, R.W. Picard, 'Fully Automatic Upper Facial Action Recognition,' IEEE International Analysis and Modeling of Faces and Gestures, pp. 195 - 202., 1998
  4. L. Franco, A. Treves, 'A Neural Network Facial Expression Recognition System using Unsupervised Local Processing,' Proceedings of the 2nd International Symposium on Image and Signal Processing and Analysis (ISPA 2001), pp. 628 - 632. ,2001
  5. B. Fasel, 'Multiscale Facial Expression Recognition using Convolutional Neural Networks.' Proceedings of the third Indian Conference on Computer Vision, Graphics and Image processin, 2002
  6. B. Fasel, 'Robust Facial Analysis using Convolutional Neural Networks,' Proceedings of the International Conference on Pattern Recognition, 2002
  7. Y. S. Kim, C. H. Ham and Y. S. Baek, 'A Fuzzy Neural Network Model Solving the Underutilization Problem' Journal of Korea Fuzzy Logic and Intelligent Systems Society, Vol. 11, pp. 354-3.58. 2001
  8. Yonsei University et aI., Systems for Recognizing and Synthesizing facial Expressions and Gestures, The Report of the Project supported by Ministry of Science and Technology, G17-A-06