要提高脱机手写字符识别的识别率，关键是特征的提取。
Extraction of features is critical to improve the recognition rate of off-line handwritten characters.
提出一种应用于手写字符识别的基于梯度归一化模糊梯度特征提取方法。
A fuzzy gradient feature extraction method based on gradient normalization applied in handwritten character recognition is proposed.
本文用到的方法对于在合理的模型假设下解决手写字符识别问题呈现了很大的潜力。
The proposed approach in this paper offers a great potential for solving difficult handwriting character recognition problems under reasonable assumptions.
实验证明将改进的BP算法用于手写字符识别有较好的识别效果，提高了算法的收敛速度。
Experiments show that the recognition system based on improved BP algorithm has achieved a good rate of recognition, and the convergence speed become faster.
在探索手写字符识别的方法上采用了统计学习理论，利用支撑向量机SVM作为基本的识别工具。
Support Vector Machine (SVM) is used as the implementation basis, which is a tool of Statistical Learning Theory (SLT).
在探索手写字符识别的方法上采用了统计学习理论，利用支撑向量机SVM作为基本的识别工具。
Support Vector Machine (SVM) is used as the implementation basis, which is a tool of Statistical Learning Theory (SLT).
应用推荐