摘要
提出了一种基于向量小波和神经网络的图像融合算法。首先对各源图像进行向量小波变换,根据变换后系数计算出各子块图像的清晰度,选取子块图像部分区域清晰度作为前溃神经网络的训练样本,调整神经网络权重;然后用训练好的神经网络组合融合图像的向量小波系数,对组合后的系数进行一致性校验;最后对该系数进行向量小波逆变换,得到融合图像。仿真实验表明,该算法能够较好地解决多传感器图像融合问题,生成的融合图像效果优于有代表性的图像融合方法。
A novel image fusion method using muliwavelet transform and neural network is proposed. Firstly, source images are decomposed with muliwavelet transform （MWT） and sub-image clarity coefficients are obtained. Some of them are selected as sample for training neural network. Then, output muliwavelet coefficients of fused image though neural network and verify them by consistency. Finally, the fused image is obtained with inverse MWT. Experimental results show that the proposed method outperforms traditional methods for image fusion.
出处
《工程图学学报》
CSCD
北大核心
2007年第4期79-83,共5页
Journal of Engineering Graphics
基金
国家自然科学基金资助项目(60473015)
