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

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지

A Study On Holistic Synthesis Human Face Images

얼굴 영상의 합성에 관한 연구

  • Published : 2002.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a method to automatically synthesized human fare images from holistic descriptions. We compactly represent the face set by a small set of prototypes, which can be used in simple ways generated controlled morphings. This becomes possible because separation of 2D-shape and texture provides a faithful, closed and convex representation of images, and smooths the mapping between images and their properties. With this approach, the user watches an images being continuously morphed according to his indications, and the synthesized images always obey the natural physiognomic constraints.

본 논문에서는 전체적으로 묘사된 얼굴의 특징을 이용하여 얼굴 영상을 합성하는 방법을 제안한다. 제안된 방법은 얼굴의 형태를 대조하는 방법을 이용하여 만든 원영상의 작은 부분 영상들을 가지고 얼굴을 재현하였으며 얼굴 영상에서 2차원적 형태와 구조를 분리함으로서 음영부분과 경계부분을 표현할 수 있었으며, 영상과 영상의 특성을 나타내는 얼굴 부분영역을 조화롭게 재배치함으로서 합성을 가능케 하였다. 실험결과 본 논문에서 제안된 방법으로 합성한 얼굴 영상은 항상 자연스러운 얼굴 영상을 나타냄으로서 제안된 방법의 실효성을 입증하였다.

Keywords

References

  1. D. Beymer. 'Vectorizing face images by interleaving shape and texture computations.' Technical Report AIM 1537, MIT, AI Lab, 1995
  2. D. Beymer and T. Poggio. 'Face Recognition from one example view.' Technical Report AIM 1536, MIT, AI Lab, 1995
  3. M. Bichsel and A. Pentland. 'Human face recognition and the face images set's topology.' CVGIP: Image Understanding, 59(2):254-261, March, 1994 https://doi.org/10.1006/ciun.1994.1017
  4. R. Brunelli and T. Poggio. 'Face recognition through geometrical features.' In G. Sandini, editor, Lecture Notes in Computer Science, pages 792-800, Springer Verlag, 1992
  5. T. Cootes, G. Edwards and C. Taylor. 'Active appearance models.' In Proc. ECCV'98, volume Ⅱ, pages 484-498, 1998
  6. T. Poggio and R. Brunelli. 'A novel approach to graphics.' Technical Report AIM 1354, MIT, AI Lab, 1992
  7. D. Rowland and D. Parrrett. 'Manipulating facial appearance through shape and color.' IEEE Computer Graphics Appl., pages 70-76, Sep. 1995
  8. S. Ullman and R. Basri. 'Recognition by linear combinations of models.' IEEE Trans. PAMI, 13(10):992-1005, Oct. 1991 https://doi.org/10.1109/34.99234
  9. T. Vetter and T. Poggio. 'Linear object classes and image synthesis from a single example image.' Technical Report AIM 1531, MIT, AI Lab, 1995