Abstract | ||
---|---|---|
We present a Mean Field Theory method for locating twodimensionalobjects that have undergone rigid transformations.The resulting algorithm is a coarse-to-fine correlation matching.We first consider problems of matching synthetic point data, andderive a point matching objective function. A tractable line segmentmatching objective function is derived by considering eachline segment as a dense collection of points, and approximating itby a sum of gaussians. The algorithm is tested on real... |
Year | Venue | Keywords |
---|---|---|
1993 | NIPS | objective function,mean field theory |
Field | DocType | Citations |
Line segment,Point set registration,Mathematical optimization,Computer science,Rigid transformation,Mean field theory,Real image,Correlation matching | Conference | 4 |
PageRank | References | Authors |
1.96 | 3 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chien-Ping Lu | 1 | 272 | 18.14 |
Eric Mjolsness | 2 | 1058 | 140.00 |