基于细胞神经网络的图像阈值化方法

Image thresholding approach based on CNN

图像阈值化是一种经典、简单而又非常有效的图像分割方法,并已得到了广泛的研究。在分析灰度图像直方图分布的基础上提出了一种基于细胞神经网络(CNN)结合直方图分析的图像阈值化方法,并给出了阈值化CNN所需阈值的自动搜索算法。实验结果表明,相对于其他两种经典的阈值化方法,该方法的阈值化分割结果较好。

Image thresholding is one of the classical,simple,and very effective techniques for image segmentation,and has been widely studied.This paper proposed an approach for image thresholding based on cellular neural network（CNN） associated with histogram analysis,and gave an automatic searching algorithm of threshold needed by threshold CNN.Experimental results show that the proposed approach obtains better segmenting results than other two classical methods.