On the definition and recognition of planar shapes in digital images

Musé, Pablo

Supervisor(es): Morel, Jean-Michel

Resumen:

This thesis deals with the recognition of shapes in digital images. A suitable shape representation is derived by analyzing invariance to perturbations that do not significantly affect visual recognition: contrast changes, partial occlusion, noise, perspective distortion. The atours of such a representation,called shape elements, provide semi local descriptions of shapes. Matching shape elements enables the recognition of "partial shapes" : Then, "global shapes" are defined as groups of partial shapes showing some spatial coherence. Deriving unsupervised thresholds involved in all decision levels of the shape recognition process, is the central points of this work. We propose decision rules for both the correspondence problem of partial shapes, and for the detection of global shapes. The proposed framework is based on a general detection methodology asserting that meaningful events may be viewed as exceptions to randomness.


Cette thèse traite de la reconnaissance des formes dans les images numériques. Une représentation appropriée des formes est déduite de l'analyse des perturbations qui n'affectent pas la reconnaissance : changement de contraste, occlusion partielle, bruit, perspective. Les atomes de cette représentation, appelés "éléments de forme", fournissent des descriptions semi-locales des formes. L'appariement de ces éléments permet de reconnaitre des formes partielles. Les formes globales sont alors définies comme des groupes de formes partielles présentant une cohérence dans leur disposition spatiale. L'aspect fondamental de ce travail est la mise en place de seuils non-supervisés, à tous les niveaux de décision du processus de reconnaissance. Nous proposons des règles de décision pour la en correcpondance de formes partielles ainsi que pour la détection de formes globales. Le cadre proposé est basé sur une méthodologie générale de la détection dans laquelle un événement est significatif s'il n'est pas susceptible d'arriver par hasard.


Detalles Bibliográficos
2004
Inglés
Universidad de la República
COLIBRI
http://hdl.handle.net/20.500.12008/20206
Acceso abierto
Licencia Creative Commons Atribución – No Comercial – Sin Derivadas (CC - By-NC-ND)
Resumen:
Sumario:This thesis deals with the recognition of shapes in digital images. A suitable shape representation is derived by analyzing invariance to perturbations that do not significantly affect visual recognition: contrast changes, partial occlusion, noise, perspective distortion. The atours of such a representation,called shape elements, provide semi local descriptions of shapes. Matching shape elements enables the recognition of "partial shapes" : Then, "global shapes" are defined as groups of partial shapes showing some spatial coherence. Deriving unsupervised thresholds involved in all decision levels of the shape recognition process, is the central points of this work. We propose decision rules for both the correspondence problem of partial shapes, and for the detection of global shapes. The proposed framework is based on a general detection methodology asserting that meaningful events may be viewed as exceptions to randomness.