Abstract
In the domain of telecommunication applications, videophony, teleconferency, the representation and modelization of human face, and its expressions, knows an important development. In this paper, we present the basic principles of image sequences coding with main approaches and methods to lead to 3D model-based coding. Then, we introduce our 3D wire-frame model with which we have developed some compression and triangulated surface representation methods. An original approach to simulate and reproduce facial expressions with radial basis functions is also presented.
Résumé
Dans le cadre des applications de télécommunications, visiophonie, téléconférence, la représentation et la modélisation du visage humain et de ses expressions connaît un développement important. Dans cet article il est présenté les principes de base du codage des séquences d’images avec les principales approches et méthodes pour aboutir au codage basé sur un modèle 3D. Puis on introduit un modèle 3D à trame de fils avec lequel a été développé diverses méthodes de compression et de représentation de surfaces triangulées. Une approche originale pour simuler et reproduire les expressions faciales à l’aide de fonctions de base radiales(fbr) est présentée.
Similar content being viewed by others
References
[AIZ89]Alzawa (K.), HaRashima (H.), Saito (T.). Model-based analysis synthesis image coding [MBASIC) system for a person’s face,Signal Processing: Image Communication,1, pp. 139–152, (1989).
[AIZ93]Aizawa (K.), Choi (C. S.), Harashima (H.), Huang (T. S.), Human facial motion analysis synthesis with application to model-based coding Motion analysis and image sequence processing in Sezan, M and Lagendijk R. Editors,Kluwer Academics Publishers, pp. 317–348, (1993).
[AIZ95]Aizawa (K.), Huang (T. S.), “Model-based image coding: Advanced video coding techniques for very low bit-rate application”Proceedings of the IEEE,83, no 2, pp. 259–271, (Feb 1995).
[AKI93]Akimoto (T.), Suenaga (Y.), “Automatic creation of 3-D facial models”IEEE Tram CGA, pp. 16–22 (Sept. 1993.)
[ANG94]Ang (Y), “Face recognition based on anatomical features”Meeting Paris MPEG4 (1994).
[BRU93]Brunelli (R.) Poggio (T.), “Face recognition: features versus templates”IEEE Trans PAM 15, pp. 1042–1052, (1993).
[BOZ94]Bozdagi (G.) .Tekalp (M.), Onural (L.), “Simulta- neous 3-D motion estimation and wireframe model adaptation including photometric effects for knowledge-based video coding”ICASSP ’94, Adelaide, Australia, Apr. 1994.
[BUH93]Buhmann (M. D.), “New developments in the theory of radial basis function interpolation”Multivariate Approximations From CAGD to Wavelets, Kurt letter and Florencio Utreras (eds.) pp. 35–75, (1993).
[CHO90]Choi (C. S.), Harashima (H.), Takebe (T.), “Analysis and synthesis of facial expressions in knowledge-based coding of facial image sequences” inProc. 3rd JC-CNSS pp. 80–84, (Dec 1990).
[CHO94]Choi (C. S.), Aizawa (K.), Harashima (H.), (T.) Takebe, “Analysis and synthesis of facial image sequence in model-based image coding,”IEEE Trans CSVT,4, no 3, pp. 257- 275, (June 1994).
[ENI96]Ebibara (K.) Ohya (J.) , Kishino (F.), “Real-time facial expression detection based on frequencey domain transform” SPIE’96,2727, pp. 916–926 (1996).
[EGG95]Egger (O.) Van Den Branden Lambrecht (C.) , “High compression image coding based on a mixed morpho-logi-cal/linear subband decomposition”COST211ter Simulation subgroup Darmstad 95, (1995).
[EIS97]Eisert (P.) , Girod (B.) , “Facial expression analysis for model-based coding of video sequences”,PCS’97, pp. 33–37 (sept. 1997).
[EKM71]Ekman (P.) Fresen (W.), “Manual for the facial action coding system” Palo Alto :Consulting psychologists press, (1971).
[ESS94]Esa (I. A.] , « Visual interpetation of facial expressions using dynamic modeling »,PhD thesis, MIT (1994.)
[ESS95](I. A.) Essa.(A.) Pentland, “Facial expression recognition using visually extracted facial action parameters”International workshop on automatic face, and gesture recognition. Zurich 95. pp. 35–40. (1995.)
[GRA95]Graf (H. P.), Chen (T.), Petajan (E.), Cosatto (E.), “Locating faces and facial parst”International workshop on automatic face, and gesture recognition, Zurich 95, pp. 41–46, (1995).
[GUE92]Guenter (B.) , “A system for simulating human facial animation” InState of the art in computer animation, pp. 191–202,Springer-Verlag (1992).
[HOR97]Horne (C.) , “MPEG-4: SNHC Verification Model 4.0”ISO/IEC JTC1/SC29AVG11, N1666 MPEG97, april 1997.
[HUA92]Huang (C. L.), Chen (C. W.), « Human facial feature extraction for face interpretation and recognition »Pattern Recognition,25, no 12, pp. 1435–1444, (1992).
[JAC95](A;) Jacquin (A.) Eleftheriadis, “Automatic location tracking of faces and facial features in video sequences” International workshop on Automatic face and gesture recognition, Zurich 95, pp. 142–147, (1995).
[KAN91]Kaneko (M.), Koike (A.), Hatori (Y.), “Coding of facial image sequence based on a 3-D model of the head and motion detection”J. Visual Commun, and Image Represent.,2, no 1, pp. 39–54, (mar. 1991).
[KAU95]Kauff (P.), Voigt (B.), “On fusion of motion and spatial segmentation”COST2llter Simulation subgroup, Darmstad 95, (1995).
[KON95]Konen (W.), Schulze-Kruger (E.), “ZN-Face: A system for access control using automated face recognition”International workshop on automatic face and gesture recognition, Zurich 95, pp. 18–23, (1995).
[KRU95]Kruse (S.-M.) , “Scene segmentation from dense displacement vector fields using randomized Hough transfrom”COST2 liter Simulation sub-group, Darmstad95 (1995.)
[LAN95]Lantis (A.), Taylor (C. J.), Cootes (T. F.), Ahmed (T.), Automatic interpretation of human faces and hand gesturs using flexible models,International workshop on Automatic face and gesture recognition, Zurich 95, pp. 98–105, (1995).
[LAV92]Lavagetto (F.), Curings (S.), “Videophone coding based on 3-D modeling of facial muscles,”SPIE Visual comm. Image Process ’92,1818, no 3, pp. 1366–1374 (1992).
[LAV94]Lavagetto (F.), Cocurullo (F.), Curinga (S.), Objectoriented videophone coding through fast adaptative segmentationMeeting Paris MPEG4, (1994).
[LEE95]Lee (Y. C), Terzopoulos (D.), Waters (K.), “Realistic modeling for facial animation”Computer graphics 95, pp. 55–62, (1995).
[LI94]Li (H.), Lundmark (A.), Forchheimer (R.), image sequence coding at very low bitrates : a review »IEEE Trans IP,3 no 5, (sept. 1994.)
[MAH95]Manohey(D. P.), Facial animationComputers Graphics World, no 1,18 pp. 60–62, (Jan. 1995).
[MAL97]Malassiotis (S.), Strintzis (M. G.), Coding of video conference stereo image sequences using 3D models,Signal Processing: Image Communication, 9, no 2, pp. 125–135, (1997.)
[MEY95]Meyer (F.), Minimum spanning forests for morphological segementationCOST2llter Simulation subgroup, Darmstad95, (1995).
[MOR93](H.) Lorikawa, (H.) Harashima, Incremental segmentation of moving pictures: an analysis by synthesis approachIEICE Trans;Inform;and Syst. E76-D, no 4, pp. 446–453, (April 1993).
[MUS89]Musmann (H.), Hotter (H.), Ostermann (J.), Object-oriented analysis-synthesis coding of moving images,Signal processing: image communication, I, pp. 117–138, (1989.)
[MUS95]Musmann (H.), A layered coding system for very low bit rate video codingSignal processing image communication, pp. 267–278, (1995).
[NAH90](M.) Nahas, (H.) Hutric, (M.) Rioux, (J.) Domey, Facial image systhesis using skin texture recordingVisual compute,6, no 6, pp. 337–343 (1990).
[NAK91]Nakaya (Y.) Chuah (Y. C), Harashima (H.). Model-based/waveform hybrid coding for videophone images.Proc. 3rd CJX-CNSS (Dec. 1990).
[OST90]Ostermann (J.), Modeling of 3D moving objects for analysis-synthesis coder,SPIE Symposium on sensing and reconstruction of 3D objects and scenes. 1260, (1990.)
[OST93]Ostermann (I.), “simoca European initiative towards MPEG-4buy cost 211” (1993.)
[OST94]Ostermann (J.), Object-based analysis-synthesis coding based (obasc) on the source model of moving rigid 3-D objectsSignal Processing: Image Communication,6, pp. 143–161, (1994).
[PAR82]Parke (F. I.), Parameterized models for facial animationIEEE CGA 12. pp. 61–68 (Nov. 1982).
[PAR89]Parke (F. I), Parameterized models for facial animation revisited”SIGGRAPH Facial animation tutorial notes, pp. 43–56 ACM SIC7GRAPH’89, (1989).
[PAT91]Patterson (E. C.), (P. C.) Lrrwinowicz, Greene (N.) , Facial animation by spatial mapping States of the art in computer animation, pp. 31–44,Springer-Verlag (1989.)
(PEA89)Pearson (D.), Model-base image coding in Proc.Globecom-89, pp. 554–558, (1989).
[PEA95]Pearson (D.), Model-based coding : past and future inProc. PCS’96, Melbourne, Australia, pp. 1–6, (march 1996.)
[PIE62]Pierce (J. R.) Developments in model-based video coding in Signals, Systems and noise,Hutchinson and Co;, London, pp. 139–141, (1962).
[POG95]Poggio (T.), Beymer (D.), “Learning networks for face analysis and systhesis”International workshop on Automatic face and gesture recognition, Zurich 95, pp. 160–165 (1995).
[PRO96]Provine (J. A.), Bruton (L. T.), 3-D model based coding - A very low bit rate coding scheme for video-conferencing.” Proc.IEEE ISCASV6 Atlanta , pp. II 798–801, (may 1996).
[REI93]Reinders (M. J. T.), Odijk (F. A.), Van Der Lubbe (J. C. A.), Gerbrands (J. J.),Tracking of global motion and facial expressions of a human face in image sequencesProc. SPIE, 2094, pp. 1516–1527, (1993).
[ROS94]Rosenblum (M.), (Y.) Yacoob, Davis (L.) , Human emotion recognition from motion using a radial basis functin network architecture.Workshop on Motion of non-rigid and articulated objects, Austin, Texas, pp. 43–49. (Nov. 1994).
[SAM92]Samal (A.), Iyengar (P. A.), Automatic recognition and analysis of human faces and facial expressions: a survey.Pattern Recognition. 25, no 1, pp. 65–67, (1992).
[SAU94]Saulnier (A.), Viaud (M. L.), Geldreich (D.), Analyse et synthèse en temps réel de visage pour la télévirtualité.Imagina 94, pp. 173–182, (1994).
[SLO87]Sloan (S. W.), A fast algorithm for constructing Delaunay triangulation in the plane.Aav. Eng. Software,9 no 1, pp. 34–55 (1987).
[SO91]So (I.), Nakamura (O), Minami (T.), A study on a model-based coding system based on isodensity maps of facial images.Pattern Recognition,24, pp. 263–272, (1991).
[SOL96]Soligon (O.),LE Méhauté (A.), Roux (C.) , Représentation et compression de surfacesProc. Coresa’96, pp. 50–54, (1996).
[SOL97]Soligon (O.), Le Méhauté (A.), Roux (C), Simulation des expressions faciales par les fonctions de base radiales,Actes CORESA’97, pp. 155–161, (1997).
[STU95]Stucki (P.), Faces, skulls and models - An overview »International workshop on Automatic face and gesture recognition, Zurich 95, pp. 1–6, (1995).
[TER90]Terzopoulos (D.), Waters (K.), Physically-based facial modeling, analysis, and animation.Visualization and computer animation,1, pp. 73–80, (1990.)
[TER93](D.) Terzopoulos (K.) Waters, Analysis ans synthesis of facial image sequences using physical and anatomical models.IEEE Trans. PAMI 15, no 1, pp. 82–89, (Jan ; 1993).
[THA93]Thalmann (N. M.), Thalmann (D.), The artificial live of synthetic actors.Trans of the Inst. of Electron, Inf. and Comm. Eng., J76D, pp. 1506–1514 (Aug. 1993.)
[VAN95]Van Damme (R. M. J.), Alboul (L.). Tight triangulations,Mathematical methods for curves and surfaces, Eds. M;Dachlen, T. Lyche and L Schumaker, pp. 517–526 (1995).
[WAT95]Waters (K.). An automatic lip-synchronisation algorithm for synthetic facesImagina 95, pp. 36–45 (1995).
[WEL91]Welsh (B.), Model-base image coding.PhD dissertation,University of Essex (1991).
[WIS95]Wiskott (I.), Fellous (J.-M.), Kruger (N.), Von Der Malsburg (C.). Face recognition and gender determination.International workshop on Automatic face and gesture recognition, Zurich 95, pp. 92–97, (1995).
[WU93]Wu (W. Y.), Wang (M. J.). Detecting the dominant points by the curvature-based polygonal approximation.CGVIP: Graphical Models and Image Processing,55, no 2, pp. 79–88, (Mar. 1993).
[YAN93]Yang (G.), Huang (T. S.). Human face detection in a scene.Proc. IEEE, (1993).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Soligon, O., MehautÉ, A.L. & Roux, C. Towards 3-D model-based video coding. Ann. Télécommun. 53, 229–241 (1998). https://doi.org/10.1007/BF02997679
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02997679