A Shock-based approach for Indexing of Image Databases using Shape

摘要

Projected shape of objects is a significant cue in fast and robust selection of images in response to visual content queries. Yet, existing methods for indexing into digital image libraries do not take full advantage of shape, primarily because this ultimately involves fundamentally difficult vision problems such as segmentation and recognition. These problems are difficult because realistic images depict objects in occlusion relationship, boundaries of objects are not clearly defined and often become ambiguous among spurious boundaries, boundaries change relative orientation in articulated objects, etc. We present a symmetry-based approach to the use of shape for indexing that relies on (i) a simultaneous symmetry-based and contour-based representation of shape, (ii) a propagation-based method to extract partial symmetries from real images, (in) transforms to augment this representation with that of its "neighboring" shapes, (iv) the generation of user-sketched queries using intuitive shape deformations, and (v) multistage (structural, parametric and metric) inexact graph-matching to extract and rank images containing objects similar to the user-defined query.