Automatic feature point correspondences and shape analysis with missing data and outliers using MDL

Authors:
Kalle Åström;Johan Karlsson;Olof Enquist;Anders Ericsson
Affiliations:
Centre for Mathematical Sciences, Lund University, Sweden;Centre for Mathematical Sciences, Lund University, Sweden;Centre for Mathematical Sciences, Lund University, Sweden;Centre for Mathematical Sciences, Lund University, Sweden
Venue:
SCIA'07 Proceedings of the 15th Scandinavian conference on Image analysis
Year:
2007

Citing 8
Cited 0

Recognizing corners by fitting parametric models

International Journal of Computer Vision
Geometric Information Criterion for Model Selection

International Journal of Computer Vision
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Linear Fitting with Missing Data: Applications to Structure-from-Motion and to Characterizing Intensity Images

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Robustness and Specificity in Object Detection

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Aligning shapes by minimising the description length

SCIA'05 Proceedings of the 14th Scandinavian conference on Image Analysis
The minimum description length principle in coding and modeling

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

Automatic construction of Shape Models from examples has recently been the focus of intense research. These methods have proved to be useful for shape segmentation, tracking, recognition and shape understanding. In this paper we discuss automatic landmark selection and correspondence determination from a discrete set of landmarks, typically obtained by feature extraction. The set of landmarks may include both outliers and missing data. Our framework has a solid theoretical basis using principles of Minimal Description Length (MDL). In order to exploit these ideas, new non-heuristic methods for (i) principal component analysis and (ii) Procrustes mean are derived - as a consequence of the modelling principle. The resulting MDL criterion is optimised over both discrete and continuous decision variables. The algorithms have been implemented and tested on the problem of automatic shape extraction from feature points in image sequences.