基于部分重设的侧抑制神经网络及其在图像分割中的应用  

Lateral inhibition neural network with partial reset and its application in image segmentation

作　　者：张莉[1,2] 冯大政[1] 

机构地区：[1]西安电子科技大学雷达信号处理国家重点实验室,西安710071 [2]西安电子科技大学数学系,西安710071

出　　处：《控制与决策》2012年第3期464-467,472,共5页Control and Decision

基　　金：国家自然科学基金项目(60971111)

摘　　要：视觉细胞之间存在的侧抑制机制能够对接收到的视觉信息进行选择性的提取,鉴于此,运用数学方法模拟视觉细胞间存在的这种生理机制,提出一种具有侧抑制机制的视觉细胞神经网络.基于部分重设的阈值,利用该网络提出一种图像分割算法.仿真结果表明,部分重设能较好地控制脉冲激发模式的不规则性.在图像分割中,各种复杂场景下的仿真实验表明,基于部分重设的侧抑制神经网络的图像分割方法,其效果明显优于常数阈值下神经网络的分割方法.Though the mechanism called lateral inhibition exists among the visual ceils, visual information can be selectively detected. By simulating this mechanism among visual ceils through a mathematical method, a lateral inhibition neural network is proposed. A method of image segmentation based on this model with partial reset is presented. The simulation results show that partial reset may allow a fine control of the irregularity of the spike trains. In image segmentation, experimental results show that the lateral inhibition neural network with partial reset is more effective than the neural network with constant threshold by quantificationally evaluating their performance.

关 键 词：侧抑制 部分重设 点火脉冲时间间隔 图像分割 最大香农熵 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]