Multi-view object representation with modified 2-layer IDP decomposition

Authors:
Roumen Kountchev;Vladimir Todorov;Roumiana Kountcheva
Affiliations:
Radio-communications Dept., Technical University of Sofia, Sofia, Bulgaria;T&K Engineering Co., Sofia, Bulgaria;T&K Engineering Co., Sofia, Bulgaria
Venue:
WSEAS Transactions on Signal Processing
Year:
2009

Citing 5
Cited 0

Digital image analysis: selected techniques and applications

Digital image analysis: selected techniques and applications
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope

International Journal of Computer Vision
Selecting Canonical Views for View-Based 3-D Object Recognition

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Cognitive image representation based on spectrum pyramid decomposition

MMACTEE'08 Proceedings of the 10th WSEAS International Conference on Mathematical Methods and Computational Techniques in Electrical Engineering
Three-dimensional natural video system based on layered representation of depth maps

IEEE Transactions on Consumer Electronics

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the paper is presented one new method for multi-view object representation based on image decomposition with modified Inverse Difference Pyramid. The method offers new approach for efficient description of the multi-view images using one of them as a reference one. The decomposition has a relatively low computational complexity because it is based on orthogonal transforms (Walsh-Hadamard, DCT, etc.). The relations which exist between transform coefficients from the consecutive decomposition layers permit significant reduction of the coefficients needed for the high-quality object representation.