摘要
探讨独立分量分析在字符识别系统中的应用.在分析图像处理及其特征提取的基础上,提出一种可有效提高字符识别精度、降低误识率的基于独立分量分析和神经网络的手写体字符识别系统.实验表明,提出的字符识别系统与单独基于神经网络的字符识别系统相比,其识别率和适应性优越,适合应用于对字符识别精度要求高的场合.
Independent Components Analysis (ICA)is an effective approach of blind source separation and has been received attention because of its potential application in signal processing, such as telecommunication and image processing. In this paper, the fundamental principle and algorithm of ICA are introduced. The feasibility of ICA for feature extraction is studied and a new method of handwriting character recognition based on the combination of ICA and neural networks is proposed. The experiment results show that ICA has good performance for feature extraction and this proposed method is more effective in recognizing handwriting character in comparison with the method based on neural networks directly.
出处
《深圳大学学报（理工版）》
EI
CAS
2004年第1期61-65,共5页
Journal of Shenzhen University(Science and Engineering)
基金
国家自然科学基金资助项目(60172065)
