其他网友正在查询： 仿的笔画顺序的翻译结果:
查询用时：0.685秒
&在分类学科中查询
This method not only keeps the advantage of the FDLEF method,but also increases the recognition rate of similar Chinese characters,the recogntion rate of similar Chinese characters can be increased from 78
本方法既保留了原FDLEF方法的优点又提高了对相似字的识别率 ,FDLEF -ANN系统对相似字的识别率由 78 0 9%提高到 82
The recognition rate to similar Chinese characters can be improved from 79.02% to 84.32%, about 5 percent the recognition rate to system can be improved about 1.3 percentage points.
对相似字的识别率由79．02％提高到84．32％，提高了五个百分点，整体识别率提高了1．3个百分点。
Algorithms Research on Thinning, Feature Extracting and Similar Chinese Characters Recognition for Off-line Handwritten Chinese Character Recognition
脱机手写体汉字识别中细化、特征提取和相似字识别算法研究
Handwritten Similar Chinese Characters Recognition Based onCombining Statistics with Neural Networks Method
基于统计与神经元方法相结合的手写体相似字识别
Based on the asymmetry, we propose a method of category-based partial area matching for similar Chinese characters recognition.
基于这种不对称性 ,本文提出了一种分类的部分空间方法来解决相似字的识别问题。
Recognition of Similar Chinese Handwriting
by Support Vector Machine
基于支持向量机的手写体相似字识别
This method not only keeps the advantage of the FDLEF method,but also increases the recognition rate of similar Chinese characters,the recogntion rate of similar Chinese characters can be increased from 78
本方法既保留了原FDLEF方法的优点又提高了对相似字的识别率 ,FDLEF -ANN系统对相似字的识别率由 78 0 9%提高到 82
The recognition rate to similar Chinese characters can be improved from 79.02% to 84.32%, about 5 percent the recognition rate to system can be improved about 1.3 percentage points.
对相似字的识别率由79．02％提高到84．32％，提高了五个百分点，整体识别率提高了1．3个百分点。
Algorithms Research on Thinning, Feature Extracting and Similar Chinese Characters Recognition for Off-line Handwritten Chinese Character Recognition
脱机手写体汉字识别中细化、特征提取和相似字识别算法研究
Handwritten Similar Chinese Characters Recognition Based onCombining Statistics with Neural Networks Method
基于统计与神经元方法相结合的手写体相似字识别
This paper improved the description of Chinese character structure from the perspective of graphic, provided a method to calculate the glyph similarity of Chinese characters based on their structure descriptions, and completed the list of similar characters in the GB2312 standard which includes 6763 Chinese characters.
本文从图形相似角度改进了汉字结构的描述方法,给出了一种基于结构描述的汉字字形相似度计算方法,并完成了GB个汉字的相似字表。
Handwritten Chinese characters are characterized with large vocabulary, complex structure, lots of similar characters and serious irregular variations of shapes.
汉字字符集具有数量大、结构复杂、相似字多和无规则变形严重等特点,使得脱机手写体汉字识别成为字符识别领域中最大的难题和最终的目标之一。
Complex structures and many similar characters make it very hard to use traditional structure analysis and statistical methods to get satisfying classification results.
而结构复杂和相似字多又使得传统的结构分析方法和统计识别方法难以取得满意的效果。
Similar characters are common among Chinese characters,which is a main reason for affecting the recognition rate of off -line handwritten Chinese character.
相似字的普遍存在是影响脱机手写体汉字识别率低的主要原因之一。
By taking advantage of information redundant residing in component combination patterns of Chinese characters and semantic processing ability provided by extended attribute grammars, this method can reduce the requirement for correctness of component drawing, and still can recognize distorted characters and distinguish very similar characters effectively.
由于利用了汉字部件组合关系中的信息冗余及扩展属性文法的语义处理能力,这种方法降低了对部件正确抽取的要求,但仍能识别畸变较大的汉字,并能有效地区分极相似字。
Study on Similitude Characters in Tibetan Character Recognition
藏文识别中相似字丁的区分研究
Study on Handwritten Numeral Recognition Using Neural Networks and SVM
基于SVM的手写数字相似字识别研究
A feature selection approach for similar handwritten Chinese characters recognition is presented, which is based on genetic algorithmsand support vector machines classifier.
在采用支持向量机分类器识别的基础上,提出了一种基于遗传算法进行手写体相似汉字特征选择的方法,解决了相似字中部分空间的自动确定问题。
Because of many complex structures of Chines characters and diverse distortion of handwritten Chinese characters, Off-line handwritten Chinese character recognition is the most difficult issue in Chinese character recognition field.
由于汉字类别多且字形结构复杂、汉字集合中相似字较多以及因不同人书写风格的差异造成手写汉字的变形很大,使得脱机手写体汉字识别最为困难。
This paper presents a method to recognize handwritten Chinese characters based on combining fuzzy directional line element feature(FDLEF)with artificial neural networks(ANN). First,the FDLEF module performs classification.
本文提出了一种基于模糊方向线索特征 (fuzzydirectionallineelementfeature,FDLEF)与人工神经网络 (artificialneuralnetworks,ANN)相结合的手写体汉字识别方法 (FDLEF -ANN) ,解决了单一FDLEF方法对相似字识别率低的问题 .
查询“相似字”译词为用户自定义的双语例句&&&&我想查看译文中含有：的双语例句
为了更好的帮助您理解掌握查询词或其译词在地道英语中的实际用法，我们为您准备了出自英文原文的大量英语例句，供您参考。&&&&&&&&&&&& The work on grammar reductions in Two-Dimensional Extended Attribute Grammars is presented for the recognition of hand-printed Chinese characters. After the components are drawn from the four corners, grammar reductions are conducted according to the attributes of component combinations and the relations of component surrounding boxes. By taking advantage of information redundant residing in component combination patterns of Chinese characters and semantic processing ability provided by extended attribute grammars,... The work on grammar reductions in Two-Dimensional Extended Attribute Grammars is presented for the recognition of hand-printed Chinese characters. After the components are drawn from the four corners, grammar reductions are conducted according to the attributes of component combinations and the relations of component surrounding boxes. By taking advantage of information redundant residing in component combination patterns of Chinese characters and semantic processing ability provided by extended attribute grammars, this method can reduce the requirement for correctness of component drawing, and still can recognize distorted characters and distinguish very similar characters effectively.本文介绍用于识别手写印刷体汉字的二维扩展属性文法方法中文法归约阶段的工作。从四方位取出部件之后,按照部件组合属性和部件框位置关系对部件进行归约。由于利用了汉字部件组合关系中的信息冗余及扩展属性文法的语义处理能力,这种方法降低了对部件正确抽取的要求,但仍能识别畸变较大的汉字,并能有效地区分极相似字。 This paper introduces 2-D EAG method for hand printed Chinese character recognition. The main works are: Propose Two-Dimensional Extended Attribute Grammar (2-D EAG for short) method, in which both bottom-up reduction And top-down deduction are realized for two-way information tran Propose a recognition scheme utilizing directly two dimensional information, to avoid information losses caused by linea Provide polysemous grammars, coexisting grammars and structure inferrings... This paper introduces 2-D EAG method for hand printed Chinese character recognition. The main works are: Propose Two-Dimensional Extended Attribute Grammar (2-D EAG for short) method, in which both bottom-up reduction And top-down deduction are realized for two-way information tran Propose a recognition scheme utilizing directly two dimensional information, to avoid information losses caused by linea Provide polysemous grammars, coexisting grammars and structure inferrings which build special linkages among grammars and distinguish among similar samples b Besides, realize also redundant reduction scheme, stroke segment drawing algorithm with elastic tracing of contour lines, and redundant guided component drawing algorithm. The recognition experiment with 100 categories of hand printed Chinese characters is conducted and very good result is achieved in overcoming large scale structural distortions (including some cursive writings).本文介绍手写印刷体汉字识别方法2-D EAG。主要的工作为:提出了二维扩展属性文法模式识别方法,可实现自底向上归约和自顶向下推导双向信息传递和控制;提出了一种直接利用二维信息进行识别的方式,可避免特征线性化造成的信息丢失;提出了多义文法、共生文法和结构推断三种在文法之间建立联系,利用结构类比区分极相似字的 识别算法;提出了多冗余归约机制,双边缘弹性跟踪笔段抽取算法,多冗余有引导部件抽取算法。用2-D EAG方法对100字种实际手写汉字进行了识别实验,在识别大畸变汉字(包括部分连笔字)方面得到了很好的结果。 Recognition of Similar Chinese Characters is a difficult problem in the computer character recognition. Basing on improving Hopfield artificial neural network, We have presented a New HNN network model, We have used it to recognition similar words and got good results. We're found a New read in this field. 在计算机文字识别中相似汉字识别是一个难题,我们对Hopfielod人工神经网络加以改进,提出了一种新的HNN网络模型,并用它来识另7相似字,取得了良好的效果,为相似汉字识别探索了一条新路。&nbsp&&&&&相关查询
在英文学术搜索中查有关的内容
在知识搜索中查有关的内容
在数字搜索中查有关的内容
在概念知识元中查有关的内容
在学术趋势中查有关的内容
2008 CNKI－中国知网
北京市公安局海淀分局 备案号：110 1081725
&2008中国知网(cnki)
中国学术期刊(光盘版)电子杂志社急需一个和套字写法相似的字
震哥刷粉团90
奁 lián奒 kāi奏 zòu
为您推荐：
其他类似问题
扫描下载二维码}