一种新的神经网络空洞滤波器的实现

Realization of New Hole Filter Based on CNN

本文深入研究了一种新的二维细胞自动机(CA),并据此提出了一种新的神经网络空洞滤波器实现方法,给出了系统实现的原理电路,并称其为细胞神经网络空洞滤波器(CNN-HF)。仿真结果表明,此系统能够有效的实现二值字符的空洞填充,且具有运行速度快,硬件实现容易等特点,期望能够在二维CA研究与应用设计方面有所启发和突破。

Based on the discussion of two-dimensional Cellular Automata (CA), a new kind of hole filter based on Cellular neural Networks, named as CNN-hole filter (CNN-HF) is proposed. Related circuit is accordingly designed to implement its function. Simulation results show that using the proposed algorithm, the hole in a figure can be filled effectively. Furthermore, it has many advantages, such as, high-speed processing, simple structure and easy integration and so on. It is expected to have profound influence on the technology of two-dimensional Cellular Automata.