Object recognition and localization via pose clustering
Computer Vision, Graphics, and Image Processing
Neural networks and the bias/variance dilemma
Neural Computation
Pose Estimation by Fusing Noisy Data of Different Dimensions
IEEE Transactions on Pattern Analysis and Machine Intelligence
Structural Matching by Discrete Relaxation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Probabilistic Indexing for Object Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Model-Based Object Recognition by Geometric Hashing
ECCV '90 Proceedings of the First European Conference on Computer Vision
Alignment by maximization of mutual information
ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Graph-Based Methods for Vision: A Yorkist Manifesto
Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
| Hi-index | 0.00 |
This paper describes a structural method for object alignment by pose clustering. The idea underlying pose clustering is to decompose the objects under consideration into k-tuples of primitive parts. By bringing pairs of k-tuples into correspondence, sets of alignment parameters are estimated. The global alignment corresponds to the set of parameters with maximum votes. The work reported here offers two novel contributions. Firstly, we impose structural constraints on the arrangement of the k-tuples of primitives used for pose clustering. This limits problems of combinatorial background and eases the search for consistent pose clusters. Secondly, we use the EM algorithm to estimate maximum likelihood alignment parameters. Here we fit a mixture model to the set of transformation parameter votes. We control the order of the underlying mixture model using a minimum description length criterion.