CANDIDE - a parameterized face

CANDIDE is a parameterised face mask specifically developed for model-based coding of human faces. Its low number of polygons (approximately 100) allows fast reconstruction with moderate computing power.

CANDIDE is controlled by global and local Action Units (AUs). The global ones correspond to rotations around three axes. The local Action Units control the mimics of the face so that different expressions can be obtained.

The concept of Action Units was first described about 40 years ago by Carl-Herman Hjortsjö in his book Man's Face and the Mimic Language (in Swedish) [6]. This work was later extended by Paul Ekman and Wallace V Friesen of the Department of Psychiatry at University of California Medical Center [2].

The CANDIDE model was created by Mikael Rydfalk at the Image Coding Group at Linköping University in 1987 [10]. This work was motivated by the first attempts to perform image compression through animation [3, 4].

The CANDIDE model became known to a larger public through journal articles [5, 7, 8]. It is publically available and is now used by research groups around the world.

The CANDIDE versions

The original CANDIDE, described in the report by M. Rydfalk [10], contained 75 vertices and 100 triangles and is demonstrated by the Java demo. This version is rarely used.

The first widespread version, for many years the de facto standard Candide model, is a slightly modified model with 79 vertices, 108 surfaces and 11 Action Units. This model was created by Mårten Strömberg while implementing the xproject package, and is here referred to as Candide-1.

Later, Bill Welsh at British Telecom [11] created another version with 160 vertices and 238 triangles covering the entire frontal head (including hair and teeth) and the shoulders. This version, known as Candide-2 is also included in the xproject package, but is delivered with only six Action Units.

A third version of CANDIDE has been derived from the original one. The main purpose of another model is to simplify animation by MPEG-4 Facial Animation Parameters [9]. Therefore, about 20 vertices have been added, most of them corresponding to MPEG4 feature points. This model is called Candide-3 [1] and is included in the WinCandide package.

You can download the latest version fo the wfm (wireframe) file defining the CANDIDE model (v3.1.6).

Candide-1

Candide-2

Candide-3

The different versions of Candide (click for larger images).

Software

Numerous people have used Candide in various softwares. Examples of available software using the CANDIDE model are:

References

[1] J. Ahlberg, CANDIDE-3 -- an updated parameterized face, Report No. LiTH-ISY-R-2326, Dept. of Electrical Engineering, Linköping University, Sweden, 2001.
Abstract - Order full report (in pdf or postscript)
[2] P. Ekman and W. V. Friesen, Facial Action Coding System, Consulting Psychologist Press, 1977.
[3] R. Forchheimer and O. Fahlander, "Low bit-rate coding through animation," Proc. Picture Coding Symposium, Davis, CA, USA, 1983.
[4] R. Forchheimer, O. Fahlander and T. Kronander, "A semantic approach to the transmission of face images," Proc. Picture Coding Symposium, Cesson-Sevigne, France, 1984.
[5] R. Forchheimer and T. Kronander, "Image Coding - from Waveforms to Animation," IEEE Trans. on ASSP, Vol. 37, No. 12, Dec. 1989.
[6] C.-H. Hjortsjö, Människans ansikte och det mimiska språket (In Swedish, "Man's Face and the Mimic Language", Studentlitertur, Lund, Sweden, 1969.
[7] H. Li, P. Roivanen, R. Forchheimer, "3D Motion Estimation in Model-Based Facial Image Coding," IEEE Trans. on PAMI, Vol. 15, No. 6, June. 1993, pp. 545 - 555.
[8] H. Li, A. Lundmark, R. Forchheimer, "Image Sequence Coding at Very Low Bitrates: A Review," IEEE Trans. on Image Processing, Vol. 3, No. 5, Sep. 1994, pp. 589 - 609.
[9] MPEG Working Group on Visual, International Standard on Coding of Audio-Visual Objects, Part 2 (Visual), ISO-14496-2, 1999.
[10] M. Rydfalk, CANDIDE, a parameterized face, Report No. LiTH-ISY-I-866, Dept. of Electrical Engineering, Linköping University, Sweden, 1987.
[11] B. Welsh, Model-Based Coding of Images, PhD dissertation, British Telecom Research Lab, Jan. 1991.



This page is made in GNU Emacs. No fancy WYSIWYG!