On-line handwritten Chinese character recognition via a fuzzy attribute representation

Chinese characters are constructed by strokes according to structural rules. Therefore, the geometric configurations of characters are important features for character recognition. In handwritten characters, stroke shapes and their spatial relations may vary to some extent. The attribute value of a structural identification is then a fuzzy quantity rather than a binary quantity. Recognizing these facts, we propose a fuzzy attribute representation (FAR) to describe the structural features of handwritten Chinese characters for an on-line Chinese character recognition (OLCCR) system. With a FAR. a fuzzy attribute graph for each handwritten character is created, and the character recognition process is thus transformed into a simple graph matching problem. This character representation and our proposed recognition method allow us to relax the constraints on stroke order and stroke connection. The graph model provides a generalized character representation that can easily incorporate newly added characters into an OLCCR system with an automatic learning capability. The fuzzy representation can describe the degree of structural deformation in handwritten characters. The character matching algorithm is designed to tolerate structural deformations to some extent. Therefore, even input characters with deformations can be recognized correctly once the reference dictionary of the recognition system has been trained using a few representative learning samples. Experimental results are provided to show the effectiveness of the proposed method.     

模糊支持向量机情感状态识别的研究*

针对已有的情感生理参数样本类内聚合度低、不同状态较难区分的特点,提出了一种改进的模糊支持向量机识别方法.模糊隶属度函数采用高斯分布形式,高斯分布的参数分别由同类样本数据形成的最小超球体半径和样本之间的紧密程度决定.该方法计算样本模糊隶属度时,不仅考虑样本与类中心的距离关系,还要考虑样本与样本之间的关系.实验显示改进的模...     

Off-line handwritten Korean character recognition based on stroke extraction and representation

In this paper, we propose an off-line recognition method for handwritten Korean characters based on stroke extraction and representation. To recognize handwritten Korean characters, it is required to extract strokes and stroke sequence to describe an input of two-dimensional character as one-dimensional representation. We define 28 primitive strokes to represent characters and introduce 300 stroke separation rules to extract proper strokes from Korean characters. To find a stroke sequence, we use stroke code and stroke relationship between consecutive strokes. The input characters are recognized by using character recognition trees. The proposed method has been tested for the most frequently used 1000 characters by 400 different writers and showed recognition rate of 94.3%.     

基于表格查寻学习算法的自适应模糊分类器

以手写体数字识别问题为背景,提出了一种基于表格查寻学习算法的自适应模糊分类 器,并用Matlab给出了自适应模糊分类器的实现,进而对其进行了仿真。仿真结果表明,该自适应模 糊分类器在手写体数字识别的识别性能、利用语言信息、计算复杂性等方面均优于采用BP算法的三 层前馈分类器,体现了自适应模糊处理技术用于模式识别的优越性和潜力。     

汉字笔段形成规律及其提取方法

该文从点阵图像行(列)连通像素段出发，研究汉字图像的笔段构成，发现汉字点阵图像仅由阶梯型笔段和平行长笔段两种类型的笔段构成，并归纳出阶梯型笔段和平行长笔段的形成规律．以笔段形成规律为基础提出了汉字笔段的提取方法，该方法将像素级汉字图像转变为以笔段为单位的图像，有利于汉字识别、汉字细化及汉字字体的自动生成．最后该文给出了印刷体和手写体汉字笔段提取的实验结果．     

最小二乘向量机在说话人识别中的应用

说话人识别是语音识别的一种,是当前的研究热点之一。而基于统计学习理论的支持向量机(SVM)方法是一种新的机器学习算法,已成为机器学习研究的热点。讨论了一种改进的SVM即最小二乘向量机(LS-SVM)的方法进行说话人识别研究。研究表明,基于LS-SVM的说话人识别比传统的SVM说话人识别计算复杂度小、效率更高、对说话人识别有很强的适应性。     

Thinning and stroke segmentation for handwritten Chinese character recognition

Firstly, a thinning technique by means of stroke tracking is proposed. The method is considered to preserve the straightness of strokes and the length, which is useful for the stroke segmentation procedure on the recognition of handwritten Chinese characters.Secondly, a method for stroke segmentation, i.c. a way of breaking down a character to a set of consecutive partial strokes, is proposed, which works well owing to the favourable properties of the proposed thinning technique. The method consists of five procedures: extraction of feature pixels, calculation of stroke directions, piecewise linear representation of strokes, unification of intersections and extraction of the consecutive partial strokes.     

基于模糊子笔画统计特征的手写体汉字识别

汉字由笔画或子笔画组成,笔画或子笔画特征在手写体汉字识别中得到了广泛应用。论文提出一种模糊子笔画抽取方法,解决了因无限制手写体笔画随意性而使得抽取的子笔画不稳定的问题。计算字符边缘点“横”、“竖”、“撇”、“捺”的模糊子笔画属性特征,并将其与模糊网格相结合,生成模糊子笔画统计特征。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。     

基于基本笔画起收笔和笔压特征的手写汉字的计算机笔迹鉴定

以手写汉字的基本笔画为研究对象,提取笔画的起笔、收笔和笔压作为特征量,进行笔迹鉴定的研究.研究采用了10位书写者,每位书写者各书写70个汉字作为样本,提取4种基本笔画,进行笔迹鉴定的实验,实验取得了较为满意的鉴定率.本研究克服了以往笔迹鉴定中结体依存的不足,适用于所有的汉字.     

On-line recognition of Korean characters using ART neural network and hidden Markov model

This paper proposes an efficient method for on-line recognition of cursive Korean characters. The recognition of cursive strokes and the representation of a large character set are important determinants in the recognition rate of Korean characters. To deal with cursive strokes, we classify them automatically by using an ART-2 neural network. This neural network has the advantage of assembling similar patterns together to form classes in a self-organized manner. To deal with the large character set, we construct a character recognition model by using the hidden Markov model (HMM), which has the advantages of providing an explicit representation of time-varying vector sequence and probabilistic interpretation. Probabilistic parameters of the HMM are initialized using the combination rule for Korean characters and a set of primitive strokes that are classified by the ART stroke classifier, and trained with sample data. This is an efficient means of representing all the 11,172 possible Korean characters. We tested the model on 7500 on-line cursive Korean characters and it proved to perform well in recognition rate and speed.     

脱机手写满文笔画基元的提取和识别

笔画的正确提取对文字识别结果至关重要。该文提出并实现了一种全新的满文笔画提取方法。基于满文文字的结构和特征，首先对处理目标进行预处理，确定笔画主干，创建笔画生长法对满文文字笔画实现自动提取。对提取得到的笔画进行分类，然后对照笔画特征库进行识别。试验表明，该方法对规整手写的满文文字的笔画提取和识别有令人满意的效果，为进一步脱机手写满文识别研究奠定了坚实的基础。     

An expert system for general symbol recognition

An expert system for analysis and recognition of general symbols is introduced. The system uses the structural pattern recognition technique for modeling symbols by a set of straight lines referred to as segments. The system rotates, scales and thins the symbol, then extracts the symbol strokes. Each stroke is transferred into segments (straight lines). The system is shown to be able to map similar styles of the symbol to the same representation. When the system had some stored models for each symbol (an average of 97 models/symbol), the rejection rate was 16.1% and the recognition rate was 83.9% of which 95% was recognized correctly. The system is tested by 5726 handwritten characters from the Center of Excellence for Document Analysis and Recognition (CEDAR) database. The system is capable of learning new symbols by simply adding their models to the system knowledge base.     

支持向量机在小字符集识别中的应用

支持向量机（SVM）是由Vapnik等人提出的一类新型机器学习方法,此方法利用较少的训练样本就可以达到比较理想的识别效果。本文应用SVM对手写数字字符集进行识别,结果表明了该方法在小字符集脱机手写体识别中的实用性。     

基于神经网络的模糊决策树改进算法

传统决策树通过对特征空间的递归划分寻找决策边界,给出特征空间的“硬”划分。但对于处理大数据和复杂模式问题时,这种精确决策边界降低了决策树的泛化能力。为了让决策树算法获得对不精确知识的自动获取,把模糊理论引进了决策树,并在建树过程中,引入神经网络作为决策树叶节点,提出了一种基于神经网络的模糊决策树改进算法。在神经网络模糊决策树中,分类器学习包含两个阶段：第一阶段采用不确定性降低的启发式算法对大数据进行划分,直到节点划分能力低于真实度阈值[ε]停止模糊决策树的增长;第二阶段对该模糊决策树叶节点利用神经网络做具有泛化能力的分类。实验结果表明,相较于传统的分类学习算法,该算法准确率高,对识别大数据和复杂模式的分类问题能够通过结构自适应确定决策树规模。     

手写体汉字特征分析

本文采用结构方法研究汉字手写体识别。通过对手写体汉字结构特征和书写特点的研究，我们发现，以直划和折划来表征笔划特征，以相交字元和基本字元来表征汉字结构特征，大大降低了结构方法中决策判断串行的程度。     

HMM在手写数字结构信息建模中的应用

针对传统隐马尔可夫模型（HMM）在识别对象时没有有效利用所识别对象的结构信息,提出了一种基于原图像分块的HMM。这种模型利用原图像的各个分块作为状态,因此具有相应的拓扑结构,可以为所识别对象的结构信息建模。为了增强模型的描述能力与精确性,采用二阶HMM,引入了终止状态,将其应用在手写数字识别中。考虑到手写数字的结构特点与模型的拓扑结构,提出了一种提取手写数字笔画特征的方法,即根据叉点提取各个笔段的特征向量。对MNIST字库进行测试,平均识别率为95.7%。     

结合姿态估计和时序分段网络分析的羽毛球视频动作识别

目的 为了满足羽毛球教练针对球员单打视频中的动作进行辅助分析,以及用户欣赏每种击球动作的视频集锦等多元化需求,提出一种在提取的羽毛球视频片段中对控球球员动作进行时域定位和分类的方法。方法 在羽毛球视频片段上基于姿态估计方法检测球员执拍手臂,并根据手臂的挥动幅度变化特点定位击球动作时域,根据定位结果生成元视频。将通道—空间注意力机制引入时序分段网络,并通过网络训练实现对羽毛球动作的分类,分类结果包括正手击球、反手击球、头顶击球和挑球4种常见类型,同时基于图像形态学处理方法将头顶击球判别为高远球或杀球。结果 实验结果表明,本文对羽毛球视频片段中动作时域定位的交并比（intersection over union,IoU）值为82.6%,对羽毛球每种动作类别预测的AUC （area under curve）值均在0.98以上,平均召回率与平均查准率分别为91.2%和91.6%,能够有效针对羽毛球视频片段中的击球动作进行定位与分类,较好地实现对羽毛球动作的识别。结论 本文提出的基于羽毛球视频片段的动作识别方法,兼顾了羽毛球动作时域定位和动作分类,使羽毛球动作识别过程更为智能,对体育视频分析提供了重要的应用价值。     

Model matching inclusion for input/state asynchronous sequential machines

The problem of model matching for asynchronous sequential machines consists of finding a feedback controller for a given open-loop machine so that the resulting closed-loop machine matches a desired model. In this paper, the control objective is extended to model matching inclusion in which the behavior of the closed-loop system should be contained in that of the model. The supremal controllable sub-model is characterized as an asynchronous machine with the largest behavior set contained in a given model that can be matched by the closed-loop machine via state feedback control. An effective computational algorithm is developed and an example is provided for illustration.     

Quotient structures of intuitionistic fuzzy finite state machines

Quotient structures of intuitionistic fuzzy finite state machines are discussed. We give congruence relations which can be naturally introduced in such a way that each associates a semigroup with an intuitionistic fuzzy finite state machine. We also introduce the notion of intuitionistic admissible relation, and give its characterization. An isomorphism between an intuitionistic fuzzy finite state machine and the quotient structure of another intuitionistic fuzzy finite state machine is established.     

动态模糊机器学习模型及验证

根据学习系统中存在的动态模糊性,提出了动态模糊机器学习模型,给出了动态模糊机器学习算法和它的几何模型描述,并进行了算法的稳定性分析,最后给出了实例验证。实例结果与BP算法产生结果相比较,优于BP算法的结果。