大写金额

基于HMM的分类器集成方法在脱机手写大写金额识别中的应用

Off-line handwritten amount in words recognition using classifiers combination method based on HMM

若文字与数字不一致，应以大写金额为准。

If there is a discrepancy between words and figures , the amount in words will prevail .

基于HMM的脱机手写大写金额识别中的单分类器性能分析

Performance Analysis of Single Classifier in Recognition of Off-line Handwritten Amount in Words Based on HMM

结合实际应用，阐述了将小写金额转换成大写金额的必要性和重要性，给出了采用分段处理的改进算法，并用PowerBuilder实现了该算法。

On the basis of real use , this paper elaborates the importance and necessity to convert money from Arabic character to capital Chinese character , gives the improved arithmetic in subsections , and realized the arithmetic in PowerBuilder .

支票大写金额的印刷体与手写体辨识

A Distinguishing Method of Printed and Handwritten Legal Amount on Chinese Bank Check

一种改进的小写金额到大写金额的转换算法

An Improved Arithmetic to Convert Money from Arabic Character to Capital Chinese Character

支票大写金额图像分割策略

Strategy for Segmentation of Legal Amount Images

支票手写体汉字大写金额识别的非线性规范化

An Improved Nonlinear Normalization Method and Its Application to Handwritten Legal Amount Recognition on Chinese Cheque

本系统以银行票据中常用的大写金额汉字为识别样本进行了实验，取得了比较满意的成果。

We take the formal character of Chinese numbers in bank bill as recognition sample for experiments , and the results are satisfying .

银行支票手写体汉字大写金额识别的实验结果表明应用模糊子笔画统计特征能取得更好的识别效果。

Experiments of handwritten legal amount recognition on Chinese check show that the fuzzy sub-stroke statistical feature proposed in this paper is more effective .

针对银行支票图像大写金额的无限制手写体汉字识别问题，进行了基于密度均衡原则的非线性规范化研究，提出了一种改进的非线性规范化方法。

An improved nonlinear normalization method based on density equalization of the exact character area is proposed for recognition of unconstrained handwritten Chinese characters on an image of Chinese cheque .

我国支票大写金额图像背景中存在定位线和背景纹理，还有各式各样的印章对笔画信息的干扰。

Difficulties are derived mainly from the complex backgrounds , including preprinted lines , texture lines and seal images with different types and positions , since they are often dark and stroke-like .

实验结果表明：该方法比其他同类方法效果更佳，可使银行支票图像的大写金额识别系统的识别正确率提高约1.5%。

Experiments show that the nonlinear normalization method can get better shape correction effect than other methods . Application of this method to handwritten legal amount recognition to Chinese cheques showed the rate of correct recognition is improved by around 1.5 % .

大写人民币金额数字的FoxPro自定义函数及其调用

A FoxPro User-Defined Function and its Calling that Transform Amount-of-Money of RMB from Numerals into Capital Form of Chinese Words