设计局部最大灰度值探测CNN模板的定理与应用

A Theorem for Designing Local Maximum Detection CNN with Applications

基于细胞神经网络(CellularNeuralNetwork,CNN)的图像处理的研究和应用已取得了很大进展。在图像处理中,有时需要确定图像各局部区域中最大灰度点的位置。文章对实现局部最大灰度值探测功能的CNN模板进行了理论分析和鲁棒性研究,提出了一个设计符合相应功能要求的鲁棒性CNN定理,它为设计相应的CNN模板参数提供了解析判据。通过数值模拟实例确认了理论结果在计算机图像处理中应用的有效性。

The researches and applications of image processing based on the Cellular Neural Network（CNN） have made great progresses.It is required in some circumstances to determine the positions of the pixels which have the locally maximum gray-scales in the images.This paper studies and analyzes robustness CNN templates with the functions to detect the pixels with locally maximum gray-scales （DLMG）.A theorem for designing the robustness DLMG CNN template parameters has been presented.Numerical examples show that our theoretical results are effective for computer image processing.