基于PCNN的纹理图像增强算法

阐述了应用有生物学依据的脉冲耦合神经网络（PCNN）的脉冲发放特性进行图像增强的原理，并将此原理应用于具有纹理特性的指纹图像，从而产生了针对纹理图像增强的新方法。此方法主要利用纹理图象的灰度变化特性，采用将像素点灰度与所在邻域内灰度的局部均值比较的方法，使原方法更有针对性。实验结果证明，指纹图象增强效果显著。

Algorithm of texture image enhancement based on PCNN

Firstly the theory of image enhancement is demonstrated that applies the pulse transmitting character of the pulse-coupled neural network(PCNN),which is an artificial network based on biology.Then the fingerprint images with textures characteristic are processed with this new method,creating a new way to enhance the texture of a fingerprint image.This method mainly takes advantage of the grey level change of texture image to compare the pixel grey level value to the local mean of neighbour domain which the pixel belongs to,so the pertinence can be strengthened.The results prove that the effect of fingerprint image enhancement is obvious.