摘要
将粗糙集理论和神经网络结合,提出了一种基于粗神经网络的信息融合算法,用于图像融合的研究,该方法不仅可以接受定量的输入,而且可以接受定性的输入,即输入是一个范围,或者在观测时间内输入是变化的。由于粗神经网络的误差传递函数不可微,不能用BP算法训练粗神经网络,所以采用遗传算法训练粗神经网络。仿真实验结果表明,基于粗神经网络的信息融合方法可以有效地融合多幅带有噪声的图像,并取得了良好的融合效果。
Integrating rough set theory with neural network theory, a novel information fusion method based on rough neural network is proposed. It is used to fuse images. The input of this method could be not only quantitative, but also qualitative, i. e. a range or variable during the observation. Because the error transfer function of rough neural network isn't differentiable, BP algorithms could not be used to solve the problem of training the rough neural network, and genetic algorithms is applied. The simulation results indicated that the novel information fusion method based on rough neural network could fuse multi-images with noise from the same scenery effectively.
出处
《模式识别与人工智能》
EI
CSCD
北大核心
2003年第3期370-373,共4页
Pattern Recognition and Artificial Intelligence
基金
国家973计划资助项目(No.5131201-4)