摘要
文字和符号的识别是当今人工智能与模式识别的一个重要研究方向。当前的识别技术主要问题之一是识别的速度不够高。本文采用雷达信号处理中的Krylov子空间方法FDR来识别文字和符号。该方法无需生成协方差矩阵的估计,也无需对样本协方差矩阵求逆,在保证识别正确率不变的情况下使算法的识别速度得到加快。本文用实测数据验证了该方法性能的有效性。
Recognition of characters and symbols is an important research direction in artificial intelligence and pattern recognition nowadays. One of the main problems of current recognition technology is that the speed of recognition is not high enough. In this paper, Krylov subspace method FDR in radar signal processing is used to identify characters and symbols. The method needn't the estimation and the inverse of the covariance matrix of the sample. It makes the recognition speed of the algorithm faster while the correct recognition rate is kept constant. The effectiveness of the method is verified by measured data.
引文
[1]Noman Islam,Zeeshan Islam,Nazia Noor.A Survey on Optical Character Recognition System[J],Journal of Information&Communication Technology,2016,10(2):1-4.
[2]Karez Abdulwahhab Hamad,Mehmet Kaya.A Detailed Analysis of Optical Character Recognition Technology[J],International Journal of Applied Mathematics,Electronics and Computers,2016,4(Special Issue):244-249.
[3]Er.Neetu Bhatia.Optical Character Recognition Techniques:A Review[J],International Journal of Advanced Research in Computer Science and Software Engineering,2014,4(5):1219-1223.
[4]Richa Goswami,O.P.Sharma.A Review on Character Recognition Techniques[J],International Journal of Computer Applications,2013,83(7):19-23.
[5]Karez Abdulwahhab Hamad,Mehmet Kaya.A Detailed Analysis of Optical Character Recognition Technology[J],International Journal of Applied Mathematics,Electronics and Computers,2016,4(Special Issue),244-249
[6]Saad Y.An overview of Krylov subspace methods with applications to control problems.Technical Report,MTNS89,RIACS,NASA Ames Research Center,Moffet Field,Calif,USA,1989
[7]唐斌.机载雷达Krylov子空间STAP算法研究[D],电子科技大学,2008.