本文根据简单细胞的结构和功能特点,利用神经元间侧抑制和侧兴奋联接关系以及朝向子网,模拟生物细胞的朝向柱结构,设计了一个边缘检测人工神经网络模型,并用于遥感图像的边缘检测,实现了对遥感图像的分割,在一定程度上解决了传统方法中存在的边缘定位模糊等问题。 In this paper, based on the structural and functional characteristics of simple cells, an edge detection artificial neural network model is designed based on the connection between the lateral and lateral excitations of neurons and toward the sub-network to simulate the orientation column structure of biological cells. The detection and realization of remote sensing image segmentation, to some extent, to solve the problems of the traditional methods such as the edge of the fuzzy positioning.