Title :
Active 3D object models
Author :
Bolle, Ruud M. ; Califano, Andrea ; Kjeldsen, Rick ; Mohan, Rakesh
Author_Institution :
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Abstract :
A novel approach is presented for pruning the amount of search needed to match image features to object models. The technique relies on active networks which capture various visibility and geometric constraints between features of a model to prune these features from search space during matching. The networks, which can be efficiently implemented in Boolean logic, integrate harmoniously with the previous work in feature recognition and object matching. A method is proposed for clustering model features (vsets) and four types of constraints which assist in building the networks. The authors show, both analytically and empirically, the dramatic reduction in search provided by activation nets
Keywords :
Boolean functions; computer vision; computerised pattern recognition; 3D object models; Boolean logic; active networks; clustering model features; feature recognition; geometric constraints; image features; object matching; object models; search space; visibility constraints; Boolean functions; Computer vision; Encoding; Face detection; Indexing; Layout; Object recognition; Solid modeling; Spatial resolution;
Conference_Titel :
Computer Vision, 1990. Proceedings, Third International Conference on
Conference_Location :
Osaka
Print_ISBN :
0-8186-2057-9
DOI :
10.1109/ICCV.1990.139543