Normalized Cuts and Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Evolving Connectionist Systems: Methods and Applications in Bioinformatics, Brain Study and Intelligent Machines
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
A Generic Methodology for Partitioning Unorganised 3D Point Clouds for Robotic Vision
CRV '04 Proceedings of the 1st Canadian Conference on Computer and Robot Vision
Spectral clustering based on the graph p-Laplacian
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
A novel approach for salient image regions detection and description
Pattern Recognition Letters
Hi-index | 0.00 |
This paper describes a novel approach for incremental subspace learning which combines the best features of the evolving clustering method and the spectral clustering algorithm based on the graph p-Laplacian. The evolving clustering method is employed to classify each input sample into a set of spherically-shaped groups. Then, the spectral clustering algorithm is used to unsupervisedly cluster this reference set, resolving the shape of classes having non-zero covariance. The proposed approach has been applied to the problem of visual landmark recognition, in a mobile robot navigation framework. Experimental results show that the performance of the method is high in terms of error rate.