한국정보통신학회논문지 (Journal of the Korea Institute of Information and Communication Engineering)

  • 제11권5호
  • /
  • Pages.977-984
  • /
  • 2007
  • /
  • 2234-4772(pISSN)
  • /
  • 2288-4165(eISSN)
한국정보통신학회 (The Korea Institute of Information and Commucation Engineering)
권호 표지
DOI QR코드

DOI QR Code

움직임분석 및 색상정보를 이용한 실시간 얼굴추적

Realtime Face Tracking using Motion Analysis and Color Information

  • 이규원 (대전대학교 정보통신공학과)
  • 발행 : 2007.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

동영상으로부터 움직임 분석 및 색상정보를 이용한 실시간 얼굴 추적 방법을 제안한다. 시간미분연산에 의하여 실시간으로 입력되는 동영상으로부터 움직임 영역을 검출한 후, 컬러공간 융합 필터링에 의하여 얼굴 영역 후보 화소를 검출하고 눈, 입등 얼굴 구성 요소 검출에 의하여 얼굴 영역의 실시간 추적을 행하였다. 얼굴 구성요소의 참조 템플릿을 구축한 후 신규 입력되는 연속영상의 얼굴 영역으로부터 템플릿 매칭을 행함으로써 추출된 얼굴 영역의 신뢰도를 판정하는 방법으로 얼굴 영역 추적의 안정도를 향상시켰다.

A realtime face tracking algorithm using motion analysis from image sequences and color information is proposed. Motion area from the realtime moving images is detected by calculating temporal derivatives first, candidate pixels which represent face region is extracted by the fusion filtering with multiple color models, and realtime face tracking is performed by discriminating face components which includes eyes and lips. We improve the stability of face tracking performance by using template matching with face region in an image sequence and the reference template of face components.

키워드

참고문헌

  1. C. Fyfe, R. Baddeley, 'Finding Compact and Sparse Distributed Representations of Visual Images,' Network Computation in Neural Systems v6 (3) : pp333-344. 1995 https://doi.org/10.1088/0954-898X/6/3/002
  2. Te-won Lee, 'Independent Component Analysis Theory and Application,' Kluwer Academic Publishers, 1998
  3. Bartlett, M. Stewart, 'Face Image Analysis by Unsupervised Learning,' Kluwer Academic Publishers, 2001
  4. B. A. Olshausen, D. J. Field, 'Sparse Coding with an Overcomplete Basis Set: A Strategy Employed by VI,' Vision Res., vol. 37, No. 23, pp. 3311-3325, 1997 https://doi.org/10.1016/S0042-6989(97)00169-7
  5. Thorsten Joachims, 'Learning to Classify Text using Support Vector Machines Methods, Theory, and Algorithms,' Kluwer Academic Publishers, 2002
  6. T.Cooke, 'Two variations on Fisher's linear discriminant for pattern recognition,' IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 24, pp.268-273, Feb.2002 https://doi.org/10.1109/34.982904
  7. Patrik Hoyer, 'Non-negative Matrix Factorization with Spareseness Constraints,' Journal of Machine Learning Research, vol. 5, pp.1457-1469, Nov. 2004
  8. Feng Jiao, W.Gao, X.Chen, G.Cui and S.Shan, 'A face Recognition Method based on Local Feature Analysis,' Proc. of ACCV2002, pp.1-5, Jan.2002
  9. Don Murray and Anup Basu, 'Motion Tracking with an Active Camera,' IEEE Trans. on PAMI, vol. 16, No. 5, pp. 449-459, May 1994 https://doi.org/10.1109/34.291452
  10. R. C. Nelson and R. Polana, 'Qualitative Recognition of Motion using Temporal Texture,' Proc. of CVGIP, vol. 56, No.1, pp.78-89, 1992 https://doi.org/10.1016/1049-9660(92)90087-J
  11. Robert M. Haralick and Linda G. Shapiro, Computer And Robot Vision, pp 346 - 350, Addison Wesley, 1992
  12. Qian Chen, Tetsuo Shimada, Haiyuan Wu, Tadayoshi Shioyama, 'Head Pose Estimation Using both Color and Feature Information,' Proc. of International Conference on Pattern Recognition, vol. 2, pp.842-845, Sep. 2000

피인용 문헌

  1. 다중생체인식 기법을 이용한사용자 인식률 향상 vol.12, pp.8, 2008, https://doi.org/10.6109/jkiice.2008.12.8.1456