摘要
本文运用神经网络理论分析了光学相关不变性模式识别的局限性，在保持光学相关模式识别方法的合理内涵的基础上，提出了基于两层神经网络的不变性模式识别方法，分析了这种方法的普适性、适应性、最优并行性及其在硬件实现上的优点，并给出该方法用于多个飞行目标多畸变不变性识别的实验结果．
The limitation of invariant optical correlation pattern recognition is analyzed according to the theory of neural networks. Maintaining the rational contents in optical correlation pattern recognition, a method for invariant pattern recognition based on a two layer feed forward neural network is proposed. The method possesses universality, adaptability, optimal parallelism and advantages in hardware implementation as well. By using the proposed method, an experimental system and the result of multiple distortion invariant classification on three airplanes are reported.
出处
《南开大学学报（自然科学版）》
CAS
CSCD
北大核心
1999年第3期69-74,共6页
Acta Scientiarum Naturalium Universitatis Nankaiensis
基金
国家自然科学基金
关键词
光学相关
不变性模式识别
神经网络
局限性
optical correlation
invariant pattern recognition
neural network
