Local appearance-based models using high-order statistics of image features

Authors:
Baback Moghaddam;David Guillamet;Jordi Vitrià
Affiliations:
Mitsubishi Electric, Research Laboratories, Cambridge, MA;Computer Vision Center, Dept. Informàtica, Universitat Autònoma de Barcelona, Barcelona, Spain;Computer Vision Center, Dept. Informàtica, Universitat Autònoma de Barcelona, Barcelona, Spain
Venue:
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Year:
2003

Citing 12
Cited 1

Representation of local geometry in the visual system

Biological Cybernetics
Blind separation of sources, Part 1: an adaptive algorithm based on neuromimetic architecture

Signal Processing
Color indexing

International Journal of Computer Vision
A computational approach for corner and vertex detection

International Journal of Computer Vision
Independent component analysis, a new concept?

Signal Processing - Special issue on higher order statistics
Local Grayvalue Invariants for Image Retrieval

IEEE Transactions on Pattern Analysis and Machine Intelligence
Probabilistic Visual Learning for Object Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
MDL-Based Selection of the Number of Components in Mixture Models for Pattern Classification

SSPR '98/SPR '98 Proceedings of the Joint IAPR International Workshops on Advances in Pattern Recognition
Image Indexing Using Color Correlograms

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Probabilistic Modeling of Local Appearance and Spatial Relationships for Object Recognition

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Comparing and Evaluating Interest Points

ICCV '98 Proceedings of the Sixth International Conference on Computer Vision

A Hidden Markov Model approach for appearance-based 3D object recognition

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a novel local appearance modeling method for object detection and recognition in cluttered scenes. The approach is based on the joint distribution of local feature vectors at multiple salient points and factorization with Independent Component Analysis (ICA). The resulting densities are simple multiplicative distributions modeled through adaptive Gaussian mixture models. This leads to computationally tractable joint probability densities which can model high-order dependencies. Furthermore, different models are compared based on appearance, color and geometry information. Also, the combination of all of them results in a hybrid model which obtains the best results using the COIL-100 object database. Our technique has been tested under different natural and cluttered scenes with different degrees of occlusions with promising results. Finally, a large statistical test with the MNIST digit database is used to demonstrate the improved performance obtained by explicit modeling of high-order dependencies.