手写体

A method of handwritten numeral recognition based on BP network is discussed in this paper.

本文主要研究了一种基于BP网络的手写体数字识别方法。

An algorithm to recognize unconstrained handwritten numerals based on centroid layer feature is proposed in this paper.

采用了基于字符质心的层次特征对无约束手写体数字进行分类识别。

Finally, the proposed method is used to solve the handwritten character feature extraction and recognition problems.

最后，用所提出的方法来解决手写体字符的特征抽取与识别问题。

Handwritten numeral recognition is a hotspot of study for years, and is some especial issue of character recognition.

手写体数字识别是多年来的研究热点，也是字符识别中的一个特别问题。

The character is often broken, conglutination, distorted and redundant, so it is necessary to correct and repair the character in order to removing the unnecessary information and retrieving the essential information which embody the author's intention.

偏微分方程的图像恢复、图像平滑和图像分割等功能，能十分有效的应用于手写体字符的预处理，使处理过的图像在很大程度上反应书写者的书写意图。

This paper discusses how to design and develop a system for recognition of handwritten digits.

本文论述并设计实现了一个手写体数字识别系统。

One of the key techniques in Continuous Handwritten Character Recognition is how to model every word entry in lexicon and every sentence that made up by the words. Due to the HMM′s characteristic of time sequence modeling capability, a Cascaded Hidden Markov Models, which defines model connection probability and state transition probability between HMMs, is proposed in this study.

利用HMM对时间序列的较强的建模能力这一特点，提出了可用于连续字符识别的HMM级联模型；给出了字符HMM模型连接概率和模型间状态转移概率的定义，并通过修正训练算法的重估公式，重估字符模型的连接参数，描述了用于手写体识别的字符HMM的设计方案；给出了级联训练算法重估公式和级联Baum-Welch训练算法描述。

Chinese handwriting characters recognition is the most difficult problem in character recognition field.

摘 要：手写体汉字识别是汉字识别领域中最难的课题。

Because of large variation of handwriting, exact recognition is very difficult.

但是由于手写体笔迹变动非常大，精确识别比较困难。

As feature extraction acts an important role in pattern recognition system, we propose three novel feature extraction methods for HCCR: a、Two structural feature extraction methods, Stroke Cross Counting Features and Peripheral Features are studied. According to the characteristics of Chinese handwriting samples, we extend the SCCF and PF respectively to weighted elastic SCCF and weighted elastic PF. Experiments show that the modified feature extraction approaches are better than original approaches. b、A new statistical feature extraction method——Elastic Meshing Directional Decomposition Feature extraction is proposed. According to the stroke statistical properties of Chinese character, we first decompose a handwritten character pattern into four directional subpatterns. Then a set of elastic meshes are applied to each of the four subpatterns respectively to extract the pixel distribution features.

统计识别方法：利用统计模式识别的经典方法——Bayes分类方法来进行汉字识别的研究，特征提取是统计模式识别的关键，本文着重围绕手写体汉字的特征分析和提取方法进行了研究，提出了三种特征提取的新方法： a、两种改进的结构特征提取方法：在笔划密度特征和外围特征的基础上，结合手写体汉字的特点，提出了加权非均匀笔划密度特征、加权非均匀外围特征的特征提取新方案； b、一种新的统计特征提取方法——弹性网格方向分解特征，根据汉字方块字的特点及笔划分布的统计特征，对手写体汉字进行横竖撇捺四方向的分解，并利用一系列的弹性网格对汉字分解后各分量的象素进行统计而提取特征，实验证明该特征提取方法用来进行手写体汉字识别是十分可行和有效的。

It is also known as one of the most poisonous naturally occurring substances.

它也被称为一个最自然发生的有毒物质。

The greatest stress is found at the location on the cross section where V is the largest.

最大应力出现在横截面上V为最大的地方。