基于改进的脉冲耦合神经网络的红外目标分割方法

INFRARED IMAGE MULTI-THRESHOLD SEGMENTATION ALGORITHM BASED ON IMPROVED PULSE COUPLED NEURAL NETWORKS

针对红外目标的特点 ,提出了一种基于直方图的改进脉冲耦合神经网络 ( PCNN)图像分割方法 ,本算法摒弃了原有脉冲耦合神经网络模型中的时间指数下降机制 ,利用灰度直方图的知识直接获得 PCNN的分割门限 ,同时保留了弥补空间罅隙和灰度微小变化的优点 .实验表明本算法分割得到的目标区域更加完整 。

By considering the features of targets in infrared images, a new image segmentation algorithm based on the pulse coupled neural network (PCNN) and histogram method was presented. The proposed algorithm entirely abandons the mechanism of the time exponential decaying function and uses the results of the gray-level histogram analysis as the interior thresholds of PCNN. Meanwhile,it reserves the advantage of bridging small spatial gaps and minor intensity variations. Experiment results demonstrate that the proposed algorithm can got more complete region and edge information of infrared images. It is also of much lower complexity and of higher speed than the original one.