Appariement d'images par invariants locaux de niveaux de gris. Application à l'indexation d'une base d'objets. (Image matching by local greyvalue invariants. Applied to indexing an object database)

Cette these s'inscrit dans le domaine de l'appariement, un sujet fondamental en vision par ordinateur. Ce domaine recouvre des problemes varies allant de celui de l'appariement entre deux images a celui de l'appariement d'une image et un modele CAO. Notre approche permet d'apparier des objets s'ils sont observes dans des scenes complexes, s'ils sont partiellement visibles et s'ils sont apercus de points de vue differents. Cette methode est etendue a l'interrogation de bases d'images et a la reconnaissance d'objets. Notre approche est basee sur une caracterisation locale des niveaux de gris d'une image. Cette caracterisation est calculee en des points particuliers des images : les points d'interet. Ces points sont detectes automatiquement et sont representatifs de l'objet observe. De ce fait, la caracterisation obtenue represente une information tres riche. De plus, elle est invariante pour le groupe des similitudes image et permet d'apparier des images ayant subi de telles transformations. Comme le groupe des similitudes absorbe au premier ordre les variations dues a un changement de point de vue lors d'une projection perspective, notre representation est quasi-invariante et donc robuste a une telle transformation. La solution presentee a ete appliquee a la recherche d'une image dans une volumineuse base d'images. Comme la multiplicite des correspondances ne permet plus d'avoir directement de reponse satisfaisante, une methode statistiquement robuste fait emerger la solution. D'autre part, pour effectuer une recherche rapide dans une large base un mecanisme d'indexation a ete developpe. La recherche d'image a ete etendue a la reconnaissance d'objet a partir d'une seule image. Pour ce faire, un objet 3D est modelise par une collection d'images representatives de l'objet. Pour obtenir une information 3D, des donnees symboliques sont ajoutees aux differents aspects de l'objet stockes dans la base. La relation trilineaire permet alors de retrouver ces donnees sur une image recherchee.

[1]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[2]  D. Hilbert,et al.  Ueber die vollen Invariantensysteme , 1893 .

[3]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[4]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[5]  H. Kalmus Biological Cybernetics , 1972, Nature.

[6]  Miss A.O. Penney (b) , 1974, The New Yale Book of Quotations.

[7]  共立出版株式会社 コンピュータ・サイエンス : ACM computing surveys , 1978 .

[8]  Paul Beaudet,et al.  Rotationally invariant image operators , 1978 .

[9]  Stephen D. Shapiro,et al.  Feature space transforms for curve detection , 1978, Pattern Recognition.

[10]  Hans P. Moravec Visual Mapping by a Robot Rover , 1979, IJCAI.

[11]  M. Teague Image analysis via the general theory of moments , 1980 .

[12]  P. J. Burt,et al.  Fast Filter Transforms for Image Processing , 1981 .

[13]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[14]  Hans P. Moravec Rover Visual Obstacle Avoidance , 1981, IJCAI.

[15]  Hans-Hellmut Nagel,et al.  Volumetric model and 3D trajectory of a moving car derived from monocular TV frame sequences of a street scene , 1981, Comput. Graph. Image Process..

[16]  Robert C. Bolles,et al.  3DPO: A Three- Dimensional Part Orientation System , 1986, IJCAI.

[17]  Rodney A. Brooks,et al.  Model-Based Three-Dimensional Interpretations of Two-Dimensional Images , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Hans-Hellmut Nagel,et al.  Displacement vectors derived from second-order intensity variations in image sequences , 1983, Comput. Vis. Graph. Image Process..

[19]  Farzin Mokhtarian,et al.  Scale-Based Description and Recognition of Planar Curves and Two-Dimensional Shapes , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Olivier D. Faugeras,et al.  HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Michael Brady,et al.  Seeds of Perception , 1987, Alvey Vision Conference.

[23]  W. Eric L. Grimson,et al.  Localizing Overlapping Parts by Searching the Interpretation Tree , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  J. Alison Noble,et al.  Finding Corners , 1988, Alvey Vision Conference.

[25]  David G. Lowe,et al.  Three-Dimensional Object Recognition from Single Two-Dimensional Images , 1987, Artif. Intell..

[26]  Joachim H. Rieger,et al.  On the classification of views of piecewise smooth objects , 1987, Image Vis. Comput..

[27]  D. Kriegman,et al.  Computing exact aspect graphs of curved objects: Solids of revolution , 1989, [1989] Proceedings. Workshop on Interpretation of 3D Scenes.

[28]  W. Eric L. Grimson On the Recognition of Curved Objects , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  Rachid Deriche,et al.  Accurate corner detection: an analytical study , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[31]  Haim J. Wolfson,et al.  Model-Based Object Recognition by Geometric Hashing , 1990, ECCV.

[32]  David J. Kriegman,et al.  On Recognizing and Positioning Curved 3-D Objects from Image Contours , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[33]  Chien-Huei Chen,et al.  CAD-based feature-utility measures for automatic vision programming , 1991, [1991 Proceedings] Workshop on Directions in Automated CAD-Based Vision.

[34]  Alex Pentland,et al.  Why aspect graphs are not (yet) practical for computer vision , 1991, [1991 Proceedings] Workshop on Directions in Automated CAD-Based Vision.

[35]  Katsushi Ikeuchi,et al.  Why aspect graphs are not (yet) practical for computer vision , 1991, [1991 Proceedings] Workshop on Directions in Automated CAD-Based Vision.

[36]  Andrew Zisserman,et al.  Geometric invariance in computer vision , 1992 .

[37]  O. D. Faugeras,et al.  Camera Self-Calibration: Theory and Experiments , 1992, ECCV.

[38]  Shimon Ullman,et al.  Limitations of Non Model-Based Recognition Schemes , 1992, ECCV.

[39]  Isaac Weiss Noise resistant projective and affine invariants , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[40]  Rüdiger von der Heydt,et al.  Detection of General Edges and Keypoints , 1992, ECCV.

[41]  R. Deriche Recursively Implementing the Gaussian and its Derivatives , 1993 .

[42]  Joachim M. Buhmann,et al.  Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[43]  Wolfgang Förstner,et al.  A Framework for Low Level Feature Extraction , 1994, ECCV.

[44]  Josef Bigün,et al.  N-folded Symmetries by Complex Moments in Gabor Space and their Application to Unsupervised Texture Segmentation , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[45]  Amnon Shashua,et al.  Trilinearity in Visual Recognition by Alignment , 1994, ECCV.

[46]  Deformable Kernels for Early Vision , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[47]  Nilanjan Ray,et al.  Pattern Recognition Letters , 1995 .

[48]  Emanuele Trucco,et al.  Geometric Invariance in Computer Vision , 1995 .

[49]  Kenji Nagao,et al.  Recognizing 3D objects using photometric invariant , 1995, Proceedings of IEEE International Conference on Computer Vision.

[50]  Patrick Gros,et al.  Matching and Clustering: Two Steps Toward Automatic Object Modeling in Computer Vision , 1995, Int. J. Robotics Res..

[51]  Roger MohrLifia Epipole and Fundamental Matrix Estimation Using the Virtual Parallax Property , 1995 .

[52]  Hanns Schulz-Mirbach,et al.  Anwendung von Invarianzprinzipien zur Merkmalgewinnung in der Mustererkennung , 1995 .

[53]  Glenn Healey,et al.  The Illumination-Invariant Recognition of 3D Objects Using Local Color Invariants , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[54]  Tony Lindeberg,et al.  Scale-Space Theory in Computer Vision , 1993, Lecture Notes in Computer Science.

[55]  IEEE Transactions on Robotics and Automation , 2022 .