A Novel Pixel-Level and Feature-Level Combined Multisensor Image Fusion Scheme

Authors:
Min Li;Gang Li;Wei Cai;Xiao-Yan Li
Affiliations:
Xi'an Research Inst. of Hi-Tech Hongqing Town, Shaanxi Province, P.R.C. 710025;The Second Artillery Military Office in Li-Shan Microelectronics Company, Xi'an, P.R.C. 710075;Xi'an Research Inst. of Hi-Tech Hongqing Town, Shaanxi Province, P.R.C. 710025;Academy of Armored Force Engineering Department of Information Engineering, Beijing, P.R.C. 100858
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
Year:
2008

Citing 5
Cited 0

A Computational Approach to Edge Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Optimizing edge detectors for robust automatic threshold selection: coping with edge curvature and noise

Graphical Models and Image Processing
PCNN models and applications

IEEE Transactions on Neural Networks
Perfect image segmentation using pulse coupled neural networks

IEEE Transactions on Neural Networks
Inherent features of wavelets and pulse coupled networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a novel image fusion scheme, which combines the merits of pixel-level and feature-level fusion algorithms. It avoids some of the well-known problems in pixel-level fusion such as blurring effects and high sensitivity to noise and misregistration. The algorithm first segments images into several regions, then extract features from each segmented region to get the fused image. Two typical image segmentation methods, region growing and edge detection based are both presented in this paper. Experimental results have demonstrated that the proposed method has extensive application scope and it outperforms the multiscale decompositions (MSD) based fusion approaches, both in visual effect and objective evaluation criteria.