通过神经网络的最短路径来分割粘连的字符

以神经网络为基础识别打印字符的方法，其主要问题是，如何分割有粘连的字符。在此，本文提出一种混合处理方法，邓以神经网络为基础的延迟分割方案与传统的快速分割技术相结合的方法。在延迟分割过程中，利用神经网络把单个字符和复合字符区分开来。为了寻找可以分割一个复合字符合适原垂直切口，使用一种寻找损失最小的弯曲切口的最短路径算法。     

一种新的粘连字符图像分割方法

针对监控画面采样图像中数字的自动识别问题,提出一种新的粘连字符图像分割方法。该方法以预处理后二值图像的连通状况来判定字符粘连的存在,并对粘连字符图像采用上下轮廓极值法确定候选粘连分割点,以双向最短路径确定合适的图像分割线路。仿真实验表明,该方法能有效解决粘连字符图像的分割问题。     

一种新的货运列车车号分割算法

在对现有的货运列车车号分割算法及相关字符分割算法对比研究的基础上,文中提出并实现了一种新的货运列车车号分割算法。根据上下轮廓特征初步确定车号字符串图像的候选分割位置,然后根据字符尺寸比例和数字的弧特征,对断裂字符进行合并和对粘连字符进行再分割。该方法巧妙地避免了传统的投影分析分割法中处理粘连字符的难题,也避免了噪声对连通域的影响。与传统方法相比,具有较好的鲁棒性,达到了较高的精度和运行效率,为整个车号识别系统的精确性和稳定性提供了保障。     

一种基于前端预测识别的粘连字符分割方法

在字符识别领域,对粘连字符的识别是一个被广泛关注的技术难点,未能准确分割粘连字符是产生识别错误的主要原因之一。在总结已有方法的特点及不足的基础上,提出了基于前端预测识别来分割粘连字符的方法。首先根据粘连字符图像的特征初步确定前端字符的候选字符集,并通过验证候选字符与前端字符图像匹配的必要条件进一步对其筛选,然后使用候选字符的屏蔽码自适应地提取前端字符图像,最后由分类器对提取结果加以验证,达到分割和识别粘连字符的目的。该方法可以适应多种类型的粘连字符,准确性高,且在字符图像质量较差时具有较强的鲁棒性。     

投影和模板匹配相结合分割车牌字符

提出了一种解决断裂、粘连、污损和部分遮挡车牌字符的分割算法.结合字符牌照的特征,对校正后的车牌图像进行投影,处理断裂和粘连的字符,实现字符初次分割.在初次分割的基础上,设计匹配模板对初次分割下来的车牌图像进行模板匹配,寻求误差最小的模板对字符重新分割.实验结果表明,该方法自适应性强,有很强的鲁棒性,可以获得最优的分割效果.     

基于背景分析的手写数字切分方法

考虑到手写数字串的结构特点,提出一种以分析特定背景区域为主,针对具体粘连数字采用不同分割策略的切分方法。文中引入蓄水池的概念来形象描绘出背景区域中字符间的粘连部分,并从中抽取某些特征对字符的具体粘连形态进行了归纳分类。在分割过程中,根据字符的粘连类型选用不同的滴水算法来求得分割路径。实验结果表明了该方法对于手写数字分割的有效性。     

一种基于衬线去除的英文印刷体多字号字符分割算法

小字号英文印刷字符的分割依然是OCR领域中一个富于竞争力的问题.其主要困难在于字符能量小、字符之间存在粘连.本文重点分析衬线粘连的几种类型,并提出衬线去除算法.然后,在此基础上提出一种小字号印刷字符的分割算法.实验结果表明,该方法可以有效分割小字号英文印刷字符.此外,本文方法对大字号字符的分割也是有效的.     

基于字符综合特征的车牌字符分割算法

字符分割技术是车牌识别系统的关键技术之一。字符分割最主要的问题是字符粘连及车牌边框的影响。鉴于车牌字符具有布局规整,字符个数确定,字符大小一致、宽高存在规律等特征,文章提出一种将投影和字符间距相结合的基于字符综合特征的字符分割算法。实验证明该算法那对分割粘连字符具有较好效果。     

基于滴水算法的验证码中粘连字符分割方法

众多研究表明,如果能将验证码中的字符分割开来,用现有的机器学习算法一般都能取得比较好的识别效果。针对字符粘连情况下的验证码的识别问题,提出了一种粘连字符的分割方法。该方法将字符的宽度统计值和竖直投影直方图中的投影极小值点相结合找到分割点,以这些分割点作为滴水算法的起始滴落点对粘连字符进行分割。实验结果证明,该方法用于分割验证码中的粘连字符具有一般性,能够提高验证码识别率。     

一种有效的手写汉字多步分割方法

在字符识别系统中,字符的有效分割是识别的关键。针对手写汉字字间距及字内距无规则可循,字符间极易发生粘连、交错等现象,提出一种多步分割方法。该方法首先利用Viterbi算法将原字符串切分成互不连通的分割块,使非粘连汉字、交错汉字得到正确分割;对于其中宽度较大存在粘连字符的分割块,从候选分割点入手,用非线性分割路径将粘连部分分开;最后再应用A*算法找到全局最佳分割位置,使过分割的字符得到完整合并。实验结果表明,该方法对于手写汉字的分割是可行、有效的。     

工程图纸图像图文自动分割工具SegChar

文章分析了工程图纸图像图文分割的技术特点、关键步骤和基本框架,着重介绍了图文自动分割工具SegChar采用的技术,如:(1) 自动字符尺寸阈值过滤技术,可使图文分割过程自动化和智能化;(2) 任意方向、任意长度字符串检测技术,通过精确HOUGH空间需求、松弛共线、基于字符串的HOUGH域更新等策略,提高了字符分割的处理速度,降低了处理的空间复杂度,能够使复杂的中西文字符串得以完整提取.文章最后给出了性能评价.     

基于决策树的汉语未登录词识别

未登录词识别是汉语分词处理中的一个难点。在大规模中文文本的自动分词处理中,未登录词是造成分词错识误的一个重要原因。本文首先把未登录词识别问题看成一种分类问题。即分词程序处理后产生的分词碎片分为‘合’(合成未登录词)和‘分’(分为两单字词)两类。然后用决策树的方法来解决这个分类的问题。从语料库及现代汉语语素数据库中共统计出六类知识:前字前位成词概率、后字后位成词概率、前字自由度、后字自由度、互信息、单字词共现概率。用这些知识作为属性构建了训练集。最后用C4.5算法生成了决策树。在分词程序已经识别出一定数量的未登录词而仍有分词碎片情况下使用该方法,开放测试的召回率:69.42%,正确率:40.41%。实验结果表明,基于决策树的未登录词识别是一种值得继续探讨的方法。     

Robust Segmentation Method for Doorplate Recognition System

Robot navigation based on character recognition is an effective vision method for com- pensating the disadvantage of ultrasonic and infrared sensors.A typical example of character recog- nition for mobile robot navigation is the doorplate recognition system.The captured doorplate images contain unexpected noise from irregular illumination conditions,various imaging angles,dif- ferent imaging distances,etc.The unexpected noise may still exist after segmentation step.In this paper,a robust segmentation method based on speculating the candidates of the characters and feeding back the classification result to the segmentation process is presented.If the candidates of doorplate characters cannot be determined at the segmentation step,a speculation according to known knowledge is executed.The threshold for character extraction from candidates is adjusted when the corresponding character is rejected after classification.The experimental results indicate that the recognition results are effectively improved with the proposed segmentation method.     

Segmentation of stick text based on sub connected area analysis

A new stick text segmentation method based on the sub connected area analysis is introduced in this paper.The foundation of this method is the sub connected area representation of text image that can represent all connected areas in an image efficiently.This method consists mainly of four steps:sub connected area classification,finding initial boundary following point,finding optimal segmentation point by boundary tracing,and text segmentaton.This method is similar to boundary analysis method but is more efficient than boundary analysis.     

门牌识别系统中的鲁棒性分割方法

Robot navigation based on character recognition is an effective vision method for compensating the disadvantage of ultrasonic and infrared sensors. A typical example of character recognition for mobile robot navigation is the doorplate recognition system. The captured doorplate images contain unexpected noise from irregular illumination conditions, various imaging angles, different imaging distances, etc. The unexpected noise may still exist after segmentation step. In this paper, a robust segmentation method based on speculating the candidates of the characters and feeding back the classification result to the segmentation process is presented. If the candidates of doorplate characters cannot be determined at the segmentation step, a speculation according to known knowledge is executed. The threshold for character extraction from candidates is adjusted when the corresponding character is rejected after classification. The experimental results indicate that the recognition results are effectively improved with the proposed segmentation method.     

层次结构导向下的动画角色模型分割与标记

对三维角色模型进行语义化检索与重组的前提是进行准确的分割和标记。本文针对游戏与影视中应用广泛的三维角色模型,提出了一种基于结构先验知识的角色部件分割和标记方法。总结了动画角色模型的一般性结构规则,并形式化为可以指导分割的层次化知识表达;采用区域生长法逐层剥离模型部件,在此规则下进行末端检测与边界判断,同时对部件进行语义标记。在两足与四足角色模型上进行测试,与其它可标记的角色模型分割方法相比,本方法具有更好的部件化结果,以及对动画角色有良好的扩展性。     

Adaptive document block segmentation and classification

This paper presents an adaptive block segmentation and classification technique for daily-received office documents having complex layout structures such as multiple columns and mixed-mode contents of text, graphics, and pictures. First, an improved two-step block segmentation algorithm is performed based on run-length smoothing for decomposing any document into single-mode blocks. Then, a rule-based block classification is used for classifying each block into the text, horizontal/vertical line, graphics, or-picture type. The document features and rules used are independent of character font and size and the scanning resolution. Experimental results show that our algorithms are capable of correctly segmenting and classifying different types of mixed-mode printed documents.     

Multi-oriented touching text character segmentation in graphical documents using dynamic programming

The touching character segmentation problem becomes complex when touching strings are multi-oriented. Moreover in graphical documents sometimes characters in a single-touching string have different orientations. Segmentation of such complex touching is more challenging. In this paper, we present a scheme towards the segmentation of English multi-oriented touching strings into individual characters. When two or more characters touch, they generate a big cavity region in the background portion. Based on the convex hull information, at first, we use this background information to find some initial points for segmentation of a touching string into possible primitives (a primitive consists of a single character or part of a character). Next, the primitives are merged to get optimum segmentation. A dynamic programming algorithm is applied for this purpose using the total likelihood of characters as the objective function. A SVM classifier is used to find the likelihood of a character. To consider multi-oriented touching strings the features used in the SVM are invariant to character orientation. Experiments were performed in different databases of real and synthetic touching characters and the results show that the method is efficient in segmenting touching characters of arbitrary orientations and sizes.     

最小加权分割路径的古籍手写汉字多步切分方法

针对古籍古文献中部分汉字易发生粘连现象,提出一种古籍手写汉字多步分割方法.该方法继承了以往粗分割和细分割相结合的思想,首先采用投影进行粗分割,将手写汉字分为粘连字符和非粘连字符两类;然后针对粘连字符串抛弃常用的串行模式,直接采用粗分割的统计信息,设置初始分割路径,并基于最短分割路径的思想,在初始分割路径的局部邻域内基于最小权值搜索并修改分割路径,从而获得最佳的加权分割路径.实验证明该方法解决了字符分割不足和多处粘连字符的分割问题,有效的提高了分割的准确率,且算法的时间复杂度较低,算法效率较高.     

Recognition of merged characters based on forepart prediction, necessity-sufficiency matching, and character-adaptive masking.

Merged characters are the major cause of recognition errors. We classify the merging relationship between two involved characters into three types: "linear," "nonlinear," and "overlapped." Most segmentation methods handle the first type well, however, their capabilities of handling the other two types are limited. The weakness of handling the nonlinear and overlapped types results from character segmentation by linear, usually vertical, cuts assumed in these methods. This paper proposes a novel merged character segmentation and recognition method based on forepart prediction, necessity-sufficiency matching and character-adaptive masking. This method utilizes the information obtained from the forepart of merged characters to predict candidates for the leftmost character, and then applies character-adaptive masking and character recognition to verifying the prediction. Therefore, the arbitrary-shaped cutting path will follow the right shape of the leftmost character so as to preserve the shape of the next character. This method handles the first two types well and greatly improves the segmentation accuracy of the overlapped type. The experimental results and the performance comparisons with other methods demonstrate the effectiveness of the proposed method.