EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
International Journal of Computer Vision
Sparse Representations for Image Decompositions
International Journal of Computer Vision
A Distributed Algorithm for Content Based Indexing of Images by Projections on Ritz Primary Images
Data Mining and Knowledge Discovery
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Generic Model Abstraction from Examples
Revised Papers from the International Workshop on Sensor Based Intelligent Robots
Panoramic Eigenimages for Spatial Localisation
CAIP '99 Proceedings of the 8th International Conference on Computer Analysis of Images and Patterns
Appearance-Based Statistical Object Recognition by Heterogeneous Background and Occlusions
Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
Fisher Light-Fields for Face Recognition across Pose and Illumination
Proceedings of the 24th DAGM Symposium on Pattern Recognition
Appearance-Based 3-D Face Recognition from Video
Proceedings of the 24th DAGM Symposium on Pattern Recognition
Hierarchical Organization of Appearance-Based Parts and Relations for Object Recognition
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Robust Recognition of Scaled Eigenimages through a Hierarchical Approach
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Contour-based partial object recognition using symmetry in image databases
Proceedings of the 2005 ACM symposium on Applied computing
Generic Model Abstraction from Examples
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image and Vision Computing
Reconstruction and Recognition of Occluded Facial Expressions Using PCA
ACII '07 Proceedings of the 2nd international conference on Affective Computing and Intelligent Interaction
Reasoning Web
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Object recognition based on photometric alignment using ransac
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Occlusion invariant face recognition using selective LNMF basis images
ACCV'06 Proceedings of the 7th Asian conference on Computer Vision - Volume Part I
| Hi-index | 0.00 |
The basic limitations of the current appearance-based matching methods using eigenimages are non-robust estimation of coefficients and inability to cope with problems related to occlusions and segmentation. In this paper we present a new approach which successfully solves these problems. The major novelty of our approach lies in the way how the coefficients of the eigenimages are determined. Instead of computing the coefficients by a projection of the data onto the eigenimages, we extract them by a hypothesize-and-test paradigm using subsets of image points. Competing hypotheses are then subject to a selection procedure based on the Minimum Description Length principle. The approach enables us not only to reject outliers and to deal with occlusions but also to simultaneously use multiple classes of eigenimages.