Segmentation of edges into lines and arcs
Image and Vision Computing
Stable and Robust Vectorization: How to Make the Right Choices
GREC '99 Selected Papers from the Third International Workshop on Graphics Recognition, Recent Advances
Searching an Engineering Drawing Database for User-Specified Shapes
ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
Symbol spotting in technical drawings using vectorial signatures
GREC'05 Proceedings of the 6th international conference on Graphics Recognition: ten Years Review and Future Perspectives
A method for symbol spotting in graphical documents
DAS'06 Proceedings of the 7th international conference on Document Analysis Systems
Hi-index | 0.00 |
In this paper a geometric hash function able to cluster similar shapes and its use for symbol spotting in technical documents is presented. A very compact representation of features describing each primitive composing a symbol are used as key indexes of a hash table. When querying a symbol in this indexing table a voting scheme is used to validate the hypothesis of where this symbol is likely to be found. This hashing technique aims to perform a fast spotting process to find candidate locations needing neither a previous segmentation step nor a priori knowledge or learning step involving multiple instances of the object to recognize.