,Image Fusion Based on the Self-Organizing Feature Map Neural Networks

• 作 者: ZHANG Zhaoli SUN Shenghe
• 机 构: Automatic Test and Control Department,Harbin Institute of Technology,Harbin 150001,China
• 出 处: 中国电子杂志（英文版）
• 发表日期: 2001年1期
• 关键词: Image data fusion Median filter Self-organizing feature map neural network.

This paper presents a new image datafusion scheme based on the self-organizing featuremap (SOFM) neural networks.The scheme consists ofthree steps:(1) pre-processing of the images,whereweighted median filtering removes part of the noisecomponents corrupting the image,(2) pixel clusteringfor each image using two-dimensional self-organizingfeature map neural networks,and (3) fusion of the im-ages obtained in Step (2) utilizing fuzzy logic,whichsuppresses the residual noise components and thusfurther improves the image quality.It proves thatsuch a three-step combination offers an impressive ef-fectiveness and performance improvement,which isconfirmed by simulations involving three image sen-sors (each of which has a different noise structure).