Model-based recognition in robot vision
ACM Computing Surveys (CSUR)
International Journal of Computer Vision
Approximate nearest neighbors: towards removing the curse of dimensionality
STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
Comparing Images Using the Hausdorff Distance
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Combining Simple Discriminators for Object Discrimination
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
A Minimum Risk Metric for Nearest Neighbor Classification
ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Shape Indexing Using Approximate Nearest-Neighbour Search in High-Dimensional Spaces
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
A statistical approach to 3d object detection applied to faces and cars
A statistical approach to 3d object detection applied to faces and cars
Discriminative distance measures for object detection
Discriminative distance measures for object detection
A Cubist Approach to Object Recognition
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
On Binary Similarity Measures for Handwritten Character Recognition
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
International Journal of Computer Vision
Recognition of occluded objects by reducing feature interactions
Image and Vision Computing
Intelligent Data Analysis - Combined Learning Methods and Mining Complex Data
Hi-index | 0.01 |
We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes. The performance of the overall system is critically dependent on the distance measure used in the nearest neighbor search. A distance measure that minimizes the mis-classification risk for the 1-nearest neighbor search can be shown to be the probability that a pair of input image measurements belong to different classes. In practice, we model the optimal distance measure using a linear logistic model that combines the discriminative powers of more elementary distance measures associated with a collection of simple to construct feature spaces like color, texture and local shape properties. Furthermore, in order to perform search over large training sets efficiently, the same framework was extended to find hamming distance measures associated with simple discriminators. By combining this discrete distance model with the continuous model, we obtain a hierarchical distance model that is both fast and accurate. Finally, the nearest neighbor search over object part classes was integrated into a whole object detection system and evaluated against an indoor detection task yielding good results.