【摘要】 近年来的研究表明,脉冲耦合神经网络(PulseCoupledNeuralNetwork ,PCNN)可有效地用于图像分割.然而对于不同图像,常需要选取适当的网络参数,以得到有效的分割结果.但是,目前网络参数的选取还主要停留在人工调整和确定阶段,尚无一种能够根据图像本身特性自动确定参数的方法,这在很大程度上限制了PCNN的应用.针对这一问题,本文提出了一种基于简化PCNN的自适应图像分割方法,通过利用图像本身空间和灰度特性自动确定网络参数,实现对不同图像的分割.实验结果表明,本文算法可以有效地对不同图像进行自动分割,具有一定的健壮性.更多还原

【Abstract】 Recent researches indicate that pulse coupled neural network (PCNN) can be implemented on image segmentation effectively.However,it is necessary to determine the near optimal parameters of the network to achieve satisfactory segmentation results for different images.Up to now,the parameters are always adjusted manually and there is no method of adaptive parameter determination,which impedes its application in automatic image segmentation.To solve the problem,this paper brings forward an adaptive segmentation method based on a simplified PCNN with the parameters determined by images’ spatial and grey characteristics automatically.Segmentations on various images are implemented with the proposed method and the experimental results demonstrate its validity and robustness.更多还原