摘要
Hopfield神经网络是经典的人工神经网络之一,本文利用离散型Hopfield神经网络来对各种道路交通标志进行识别,并讨论在加噪、旋转等条件下对交通标志识别率的影响。同时,对图像的复杂度、识别率、图像识别前后的信噪比进行了讨论与分析。
The Hopfield neural network is one of the commonly applied neural networks in the artificial intelligence fields.In this paper,the pattern recognition of selected traffic signs is presented using the discrete Hopfield neural network.The correlation is explored between the pattern recognition success rate and the level of noise addition and rotation as corruption mixed with the given patterns.Some new concepts,such as the complexity of traffic signs and recognition rate,are defined and employed in this work.The analytical and test results well indicate the good potentials of the Hopfield neural network in the identification of traffic signs and other similar patterns.
出处
《计算机工程与科学》
CSCD
北大核心
2011年第8期132-137,共6页
Computer Engineering & Science
基金
浙江省宁波市自然科学基金资助项目(2010A610109)
关键词
HOPFIELD神经网络
交通标志
图像复杂度
信噪比
识别率
Hopfield neural network
traffic signs
image complexity
anti-noise performance
pattern recognition rate
