Ill-Posed Problems and Regularization Analysis in Early Vision

While in classical optics the problem is to determine the images of physical objects, vision is confronted with the inverse problem of recovering three-dimensional shape from the light distribution in the image. Most processes of early vision such as stereomatching, computation of motion and all the ``structure from" processes can be regarded as solutions to inverse problems. This common characteristic of early vision can be formalized---{\it most early vision problems are ``ill-posed problems" in the sense of Hadamard}. We will show that a mathematical theory developed for regularizing ill-posed problems leads in a natural way to the solution of early vision problems in terms of variational principles of a certain class. This is a new theoretical framework for some of the variational solutions already obtained in the analysis of early vision processes. It also shows how several other problems in early vision can be approached and solved.

[1]  C. Reinsch Smoothing by spline functions , 1967 .

[2]  Berthold K. P. Horn,et al.  Determining lightness from an image , 1974, Comput. Graph. Image Process..

[3]  D Marr,et al.  Cooperative computation of stereo disparity. , 1976, Science.

[4]  Tomaso Poggio,et al.  A Theory of Human Stereo Vision , 1977 .

[5]  S. Ullman The interpretation of structure from motion , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[6]  Ellen C. Hildreth,et al.  Implementation Of A Theory Of Edge Detection , 1980 .

[7]  W. Eric L. Grimson,et al.  Shape Encoding and Subjective Contours , 1980, AAAI.

[8]  D Marr,et al.  Theory of edge detection , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[9]  Katsushi Ikeuchi,et al.  Numerical Shape from Shading and Occluding Boundaries , 1981, Artif. Intell..

[10]  Harry G. Barrow,et al.  Interpreting Line Drawings as Three-Dimensional Surfaces , 1980, Artif. Intell..

[11]  John E. W. Mayhew,et al.  Psychophysical and Computational Studies Towards a Theory of Human Stereopsis , 1981, Artif. Intell..

[12]  W E Grimson,et al.  A computer implementation of a theory of human stereo vision. , 1981, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[13]  Demetri Terzopoulos Multi-Level Reconstruction of Visual Surfaces: Variational Principles and Finite Element Representations , 1982 .

[14]  W E Grimson,et al.  A computational theory of visual surface interpolation. , 1982, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[15]  Demetri Terzopoulos,et al.  Multilevel computational processes for visual surface reconstruction , 1983, Comput. Vis. Graph. Image Process..

[16]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[17]  T. Poggio,et al.  A generalized ordering constraint for stereo correspondence , 1984 .

[18]  E. Hildreth The computation of the velocity field , 1984, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[19]  Alan L. Yuille The Smoothest Velocity Field Token Matching Schemes , 1984, ECAI.

[20]  T. Poggio,et al.  Fingerprints theorems for zero crossings , 1985 .

[21]  Alex P. Pentland,et al.  From Pixels to Predicates: Recent Advances in Computational and Robotic Vision , 1986, IEEE Expert.