Qualitative similarity measures-The case of two-dimensional outlines
Computer Vision and Image Understanding
Retrieving shapes efficiently by a qualitative shape descriptor: the scope histogram
CIVR'06 Proceedings of the 5th international conference on Image and Video Retrieval
| Hi-index | 0.00 |
Depending on their contents digital libraries require specific means for searching in them for objects, especially in the case of pictorial objects. In this paper, we devote our attention to those fields in which silhouettes of objects or their outlines are of interest, i.e. whenever features are particularly distinctive which reside at the contour of objects. A set of qualitative features is provided which can easily be made in sketches and which can be robustly distinguished in a query-by-sketch approach. As those qualitative features can be computed separately for each object offline, objects can be indexed with logarithmic time by their qualitative description.