A Simple Compressive Sampling Mode and the Recovery of Nature Images Based on Pixel Value Substitution

DOI

10.2991/icmt-13.2013.205How to use a DOI?

Keywords

Compressive Sensing • Pixel Value Substitution • Gaussian Measurement Matrix • Natural Images.

Abstract

Compressive Sampling (CS) is a new technique for information acquisition and processing. In this paper we propose a new algorithm based on Pixel Value Substitution (PVS) to reconstruct the nature images when the model of compressive sampling is very simple. By indirectly utilizing the fact that usually the gradient of a natural image is sparse, we divide the image into many small blocks, and for each block, we use only one typical value to represent all the pixels' values of that block. And thus we can construct a new matrix with full column rank from the Gaussian measurement matrix, and get a new system of equations that can be solved by the least square method which is also used in the greedy algorithms. And through analyzing we find out the statistical feature of the reconstructed signal, and the factors that influence the reconstruction quality, which tell us that, in order to get the most appropriate value for each pixel, the reconstruction needs to be repeated as is shown in the concrete steps of the algorithm, and also the block’s size should be appropriate. At last, experimental results are given to demonstrate the viewpoints in this paper and they show that, in addition to improving the quality, PVS can also significantly reduce the time consumption.

Copyright

© 2013, 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  - Shao Wenping
AU  - Ni Lin
PY  - 2013/11
DA  - 2013/11
TI  - A Simple Compressive Sampling Mode and the Recovery of Nature Images Based on Pixel Value Substitution
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 1683
EP  - 1692
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.205
DO  - 10.2991/icmt-13.2013.205
ID  - Wenping2013/11
ER  -