摘要
本文提出一种适于光学实现的三层神经网络模型,该模型具有对多目标转动不变的模式识别能力.该模型被用于对四种飞行器的平面内旋转识别.计算机仿真表明,该模型对样本模式、非样本模式以及有局部遮挡时,皆有良好的联想识别能力.
A model of three-layer optical neural network is proposed for pattern recognition with rotation invariance. As an example, the model is applied to recognize the projective views of four classes of aircrafts. Investigation of computer simulations shows that the model has good capacity of pattern recognition for patterns both inside and outside the training sets, as well as partially shaded patterns.
出处
《红外与毫米波学报》
SCIE
EI
CAS
CSCD
北大核心
1992年第1期69-75,共7页
Journal of Infrared and Millimeter Waves
基金
国家自然科学基金
关键词
模式识别
鉴别函数
光学神经网络
pattern recognition, rotation invariance, synthetic discriminant function, optical neural network
