摘要
随着信息系统的广泛应用,光学字符识别(Optical Character Recognition,OCR)技术取的了长足的进步。通过引入模拟退火算法、"交叉算子"和"变异算子",提出了一种改进粒子群优化算法(Improved Particle Swarm Optimization,IPSO)对神经网络的参数进行优化计算。试验证明,OCR方法具有很高的识别效率。
Optical character recognition technology got great development due to extensive application of information systems.SA,＂intercross operator ＂ and ＂aberrance operator＂ are combined to improve PSO＇s performance,a new IPSO（Improved Particle Swarm Optimization） is formed to optimize the parameters of BP neural network.Experiments shows the arithmetic has wonderful performance in OCR.
出处
《煤炭技术》
CAS
北大核心
2010年第12期158-160,共3页
Coal Technology
基金
北京市属市管高等学校人才强教计划资助项目(BGZY2007)
关键词
改进的粒子群优化
BP神经网络
光学字符识别
improved particle swarm optimization
BP neural networks
optical character recognition
