Pixel level image fusion based on ICA and wavelet transform

被引：0

作者：

Li Maokuan ^{[1
]}

Guan Jian ^{[1
]}

机构：

[1] Naval Aeronaut Engn Acad, Yantai 264001, Shandong, Peoples R China

来源：

2007 1ST ASIAN AND PACIFIC CONFERENCE ON SYNTHETIC APERTURE RADAR PROCEEDINGS | 2007年

关键词：

wavelet transform; Independent Component Analysis (ICA); Image Fusion;

D O I：

10.1109/APSAR.2007.4418596

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Image fusion is the process of producing a single image from a set of input images with more complete information and has broad applications in many fields, such as computer vision, automatic object detection, image processing, and remote sensing. In this paper, a pixel level image fusion algorithm based on Independent Component Analysis (ICA) and wavelet transform is proposed Firstly, we use the 2D discrete wavelet transform in order to extract multiple subband images. and then apply ICA on the subband images to get ICA bases, at last fuse the image by the independent component bases. The results show that it gives promising results as compared to previous methods and performs considerably well across a variety of multi-sensor imaging data.

引用

页码：229 / 231

页数：3