PCA与PCNN结合的遥感图像分割方法

Segmentation method of remote sensed images based on principal component analysis and pulse coupled neural network

提出了一种基于主分量分析(PCA)与脉冲耦合神经网络(PCNN)结合的遥感图像分割方法。通过对图像在每个像素的邻域的基础上进行主分量分析,产生每个图像像素的特征向量,再用PCNN对得到的特征图像进行点火分割。实验结果表明,与传统方法比较,该算法在分割结果、实时性以及稳健性方面具有较强的优越性。

A segmentation method of remote sensed images based on principal component analysis and pulse coupled neural network is proposed.It presents principal component analysis on image based on neighborhood unions of per-pixel to obtain the eigenvector of per-pixel, then uses PCNN to set on fire to segment image with feature image.Experimental results have shown that compared with traditional method,the proposed method is stronger superiority in segmentation results,stablity and real time capability.