Morphing of image represented objects using a physical methodology

ABSTRACT

This paper presents a methodology to do morphing between image represented objects, attending to their physical properties. It can be used amongst images of different objects, or otherwise, between different images of the same object.According to the used methodology the given objects are modelled by the Finite Element Method, and some nodes are matched by Modal Analysis. Then, by solving the Dynamic Equilibrium Equation the displacement field is determined, which allows the simulation of the objects' deformation.This physical approach also allows the computation of the involved strain energy, therefore the estimated morphing can be represented by the local or global strain energy values.This paper also describes the solution used to simulate only the non-rigid components of the involved deformation.

REFERENCES

• 1: Bathe, K., Finite Element Procedures, Prentice-Hall, 1996
• 2: Cook, R., Malkus, D., Plesha, M., Concepts and Applications of Finite Element Analysis, Wiley, 1989
• 3: Horn, B., Closed-Form Solution of Absolute Orientation using Unit Quaternions, Journal of the Optical Society America A., 1987
• 4: John Martin , Alex Pentland , Stan Sclaroff , Ron Kikinis, Characterization of Neuropathological Shape Deformations, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.20 n.2, p.97-112, February 1998 [doi>10.1109/34.659928]
• 5: Nastar, C., Ayache, N., Fast Segmentation, Tracking, and Analysis of Deformable Objects, Fourth International Conference on Computer Vision, Berlin, Germany, 1993
• 6: Nastar, C., Modèles Phisiques Déformables et Modes Vibratoires pour l'Analyse du Mouvement non-rigide dans les Images Multidimensionnelles, L'École Nationale des Ponts et Chaussées, 1994
• 7: Chahab Nastar , Nicholas Ayache, Frequency-Based Nonrigid Motion Analysis: Application to Four Dimensional Medical Images, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.18 n.11, p.1067-1079, November 1996 [doi>10.1109/34.544076]
• 8: Pinho, R., Determinação do Campo de Deslocamentos a partir de Imagens de Objectos Deformáveis, Universidade do Porto, 2002
• 9: Sclaroff, S., Modal Matching: A Method for Describing, Comparing, and Manipulating Digital Signals, MIT, 1995
• 10: Stan Sclaroff , Alex P. Pentland, Modal Matching for Correspondence and Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.17 n.6, p.545-561, June 1995 [doi>10.1109/34.387502]
• 11: Sclaroff, S., Deformable Prototypes for Encoding Shape Categories in Image Databases, Pattern Recognition, vol. 30, no. 4, pp. 627--642, Apr. 1997
• 12: Tavares, J., Análise de Movimento de Corpos Deformáveis usando Visão Computacional, FEUP, 2000
• 13: Tavares, J., Barbosa, J., Padilha, A., Determinação de Correspondência entre Modelos de Contorno e de Superficie, utilizando Modelização por Elementos Finitos e Análise Modal, em Visão por Computador, VI Congresso Nacional de Mecânica Aplicada e Computacional, Aveiro, 2000
• 14: Tavares, J., Barbosa, J., Padilha, A., Matching Image Objects in Dynamic Pedobarography, RecPad'2000 11th Portuguese Conference on Pattern Recognition. Porto, Portugal, 2000
• 15: Tavares, J., Barbosa, J., Padilha, A., Apresentação de um Banco de Desenvolvimento e Ensaio para Objectos Deformáveis, RESI - Revista Electrónica de Sistemas de Informação, vol. 1, 2002

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.10 Vision and Scene Understanding
            Subjects: Modeling and recovery of physical attributes

General Terms:
Algorithms, Experimentation, Theory

Keywords:
Dynamic Equilibrium Equation, computer vision, deformable objects, finite element method, modal analysis, morphing