Graphical Templates for Model Registration
IEEE Transactions on Pattern Analysis and Machine Intelligence
Face recognition by elastic bunch graph matching
Intelligent biometric techniques in fingerprint and face recognition
A Fast Radial Symmetry Transform for Detecting Points of Interest
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Representation and Detection of Deformable Shapes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Belief Propagation in Large, Highly Connected Graphs for 3D Part-Based Object Recognition
ICDM '06 Proceedings of the Sixth International Conference on Data Mining
The Representation and Matching of Pictorial Structures
IEEE Transactions on Computers
Hi-index | 0.00 |
In this paper a novel non-rigid matching technique is presented to reliably detect near-regular object configurations in images in the presence of substantial clutter. The objects in near-regular configurations span a grid with not necessarily congruent grid cells. In addition, the output of object detectors is typically associated with ambiguities, causing occasional spurious false alarms.We propose a detection approach of spatially extended near-regular structures which reliably deals with missing objects and clutter. The search for the optimal local spatial object arrangement is formulated as a non-rigid matching problem and it is guided by the criterion of structural energyminimization while maximizing image likelihood. The applicability of the approach is demonstrated by presenting experimental results for the detection of near-regular object configurations.