基于细胞神经网络的从阴影恢复形状的新方法

细胞神经网络(CNN)是一种实时处理信号的大规模非线性模拟电路,它的连续时间特点以及局部互连特点使其可以进行并行计算,并且非常适用于超大规模集成电路(VLSI)的实现.本文针对从阴影恢复形状(SFS)问题,提出了一种基于硬件退火CNN的能量函数优化方法,并对该方法进行了详细分析,给出了实例的仿真结果,验证了该方法的有效性.该方法为并行处理算法,具有运算量小、易于大规模VLSI集成实现,且能够克服局部极小等优点,可以使SFS问题得到实时的处理.

A New Approach for Shape form Shading Based on CNN

A cellular neural network(CNN) is a large-scale nonlinear analog circuit suitable for real-time signal and image processing.CNN can be used for high-speed parallel computation and is easy to be translated into a VLSI implementation.This paper presents one new approach for shape from shading(SFS) using paralleled hardware annealing CNN that performs optimization algorithm.Some practical results are presented and briefly discussed,which demonstrates the successful operation of the proposed algorithm.This new approach is very affordable to parallelism and analog VLSI implementation,which allowing the SFS solution to be performed in real-time.