The Analysis of Image Decomposition and Reconstruction Based on Contourlet Transform

DOI

10.2991/iiicec-15.2015.262How to use a DOI?

Keywords

image; decomposition; reconstruction; Contourlet.

Abstract

We introduce a new approach to image decomposition and reconstruction. We propose a double filter bank structure, named the pyramidal directional filter bank,by combining the Laplacian pyramid with a directional filter bank. Contourlet transform is a multi-scale and multi direction method of two-dimensional image. It has the multi direction and multi resolution, local positioning, strong expressing ability and anisotropic features,compared to other multiscale geometric analysis method. The Contourlet transform is made up of decomposition by Laplasse Pyramid and directional filter. First of all, Laplasse Pyramid transform for image multiscale decomposition, get low pass and band-pass sampling image, difference map of original image and low-pass sampling image, namely the low-frequency sub image and high frequency component. Then,directional filter bank DFB to high frequency sub-band decomposition into 2j directional subband. Multiscale decomposition of the low frequency subband repeated Laplasse Pyramid can realize image decomposition and multi direction, to avoid spills image low-frequency information effectively.This paper mainly introduces the working principle of contourlet transform, and also introduced the application of contourlet transform.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Rong Chen
PY  - 2015/03
DA  - 2015/03
TI  - The Analysis of Image Decomposition and Reconstruction Based on Contourlet Transform
BT  - Proceedings of the 2015 International Industrial Informatics and Computer Engineering Conference
PB  - Atlantis Press
SP  - 1185
EP  - 1188
SN  - 2352-538X
UR  - https://doi.org/10.2991/iiicec-15.2015.262
DO  - 10.2991/iiicec-15.2015.262
ID  - Chen2015/03
ER  -