On the definition and recognition of planar shapes in digital images
Pablo Musé · Americanae (AECID Library) · 2004
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.