Neural and fuzzy methods in handwriting recognition

Handwriting recognition requires tools and techniques that recognize complex character patterns and represent imprecise, common-sense knowledge about the general appearance of characters, words and phrases. Neural networks and fuzzy logic are complementary tools for solving such problems. Neural networks, which are highly nonlinear and highly interconnected for processing imprecise information, can finely approximate complicated decision boundaries. Fuzzy set methods can represent degrees of truth or belonging. Fuzzy logic encodes imprecise knowledge and naturally maintains multiple hypotheses that result from the uncertainty and vagueness inherent in real problems. By combining the complementary strengths of neural and fuzzy approaches into a hybrid system, we can attain an increased recognition capability for solving handwriting recognition problems. This article describes the application of neural and fuzzy methods to three problems: recognition of handwritten words; recognition of numeric fields; and location of handwritten street numbers in address images     

Holistic verification of handwritten phrases

In this paper, we describe a system for rapid verification of unconstrained off-line handwritten phrases using perceptual holistic features of the handwritten phrase image. The system is used to verify handwritten street names automatically extracted from live US mail against recognition results of analytical classifiers. Presented with a binary image of a street name and an ASCII street name, holistic features (reference lines, large gaps and local contour extrema) of the street name hypothesis are “predicted” from the expected features of the constituent characters using heuristic rules. A dynamic programming algorithm is used to match the predicted features with the extracted image features. Classes of holistic features are matched sequentially in increasing order of cost, allowing an ACCEPT/REJECT decision to be arrived at in a time-efficient manner. The system rejects errors with 98 percent accuracy at the 30 percent accept level, while consuming approximately 20/msec per image on the average on a 150 MHz SPARC 10     

Handwritten numeral recognition based on simplified structural classification and fuzzy memberships

Previous handwritten numeral recognition algorithms applied structural classification to extract geometric primitives that characterize each image, and then utilized artificial intelligence methods, like neural network or fuzzy memberships, to classify the images. We propose a handwritten numeral recognition methodology based on simplified structural classification, by using a much smaller set of primitive types, and fuzzy memberships. More specifically, based on three kinds of feature points, we first extract five kinds of primitive segments for each image. A fuzzy membership function is then used to estimate the likelihood of these primitives being close to the two vertical boundaries of the image. Finally, a tree-like classifier based on the extracted feature points, primitives and fuzzy memberships is applied to classify the numerals. With our system, handwritten numerals in NIST Special Database 19 are recognized with correct rate between 87.33% and 88.72%.     

Unconstrained handwritten character recognition based on fuzzy logic

This paper presents an innovative approach called box method for feature extraction for the recognition of handwritten characters. In this method, the binary image of the character is partitioned into a fixed number of subimages called boxes. The features consist of vector distance (γ) from each box to a fixed point. To find γ the vector distances of all the pixels, lying in a particular box, from the fixed point are calculated and added up and normalized by the number of pixels within that box. Here, both neural networks and fuzzy logic techniques are used for recognition and recognition rates are found to be around 97 percent using neural networks and 98 percent using fuzzy logic. The methods are independent of font, size and with minor changes in preprocessing, it can be adopted for any language.     

A hybrid approach for image recognition combining type-2 fuzzy logic, modular neural networks and the Sugeno integral

In this paper, a hybrid approach for image recognition combining type-2 fuzzy logic, modular neural networks and the Sugeno integral is described. Interval type-2 fuzzy inference systems are used to perform edge detection and to calculate fuzzy densities for the decision process. A type-2 fuzzy system is used for edge detection, which is a pre-processing applied to the training data for better use in the neural networks. Another type-2 fuzzy system calculates the fuzzy densities necessary for the Sugeno integral, which is used to integrate results of the neural network modules. In this case, fuzzy logic is shown to be a good methodology to improve the results of a neural system facilitating the representation of the human perception. A comparative study is also made to verify that the proposed approach is better than existing approaches and improves the performance over type-1 fuzzy logic.     

Handwritten Chinese Character Recognition Based on Primitive and Fuzzy Features via the SEART Neural Net Model

A handwritten Chinese character recognition method based on primitive and compound fuzzy features using the SEART neural network model is proposed. The primitive features are extracted in local and global view. Since handwritten Chinese characters vary a great deal, the fuzzy concept is used to extract the compound features in structural view. We combine the two categories of features and use a fast classifier, called the Supervised Extended ART (SEART) neural network model, to recognize handwritten Chinese characters. The SEART classifier has excellent performance, is fast, and has good generalization and exception handling abilities in complex problems. Using the fuzzy set theory in feature extraction and the neural network model as a classifier is helpful for reducing distortions, noise and variations. In spite of the poor thinning, a 90.24% recognition rate on average for the 605 test character categories was obtained. The database used is CCL/HCCR3 (provided by CCL, ITRI, Taiwan). The experiment not only confirms the feasibility of the proposed system, but also suggests that applying the fuzzy set theory and neural networks to recognition of handwritten Chinese characters is an efficient and promising approach.     

区间模糊相似性度量的离线签名验证

为优化离线手写签名验证,提出了一种基于区间符号表示和模糊相似性度量的高效离线签名验证方法。在特征提取步骤中,从签名图像及其欠采样位图计算一组基于改进局部二值模式（LBP）与灰度共生矩阵（GLCM）相融合的特征。然后获得每个签名类中每个要素的区间值符号数据。为每个人的手写签名类创建由一组间隔值（对应于特征的数量）组成的签名模型。为了验证测试样本,还提出了一种新的模糊相似性度量来计算测试样本签名和相应的区间值符号模型之间的相似度。为了评估所提出的验证方法,使用了不同类型的中文手写签名笔迹图片进行测试与比对,识别率可以达到92.75%。实验结果表明当训练样本的数目是10或更多时,有效提高了识别率,所提出的方法优点在于当向系统添加新类时不需要被重新训练,并在内存使用和计算时间方面与神经网络比较是廉价的。     

基于模糊控制的十字路口交通灯控制系统

文章描述了一种基于模糊算法的十字路口交通灯控制系统。硬件运用了西门子系列PLC控制器件、软件采用MATLAB模糊逻辑工具箱,同时,提出了一种快速计算模糊控制查询表的方法。     

三级倒立摆的加权变量模糊神经网络控制

为了提高三级倒立摆系统控制的响应速度和稳定性,在设计Mamdani型摸糊推理规则控制器控制倒立摆系统稳定的基础上,设计了一种更有效率的基于Sugeno型模糊推理规则的模糊神经网络控制器。该控制器使用BP神经网络和最小二乘法的混合算法进行参数训练,能够准确归纳输入输出量的模糊隶属度函数和模糊逻辑规则。通过与Mamdani型控制器的仿真对比,表明该Sugeno型模糊神经网络控制器对三级倒立摆系统的控制具有良好的稳定性和快速性,以及较高的控制精度。     

Silicon implementation of a fuzzy neuron

This paper describes a fuzzy neuron chip which is the modification of an ordinary neuron model by fuzzy logic. The algebraic product of scaler input and connective weights in synapse is replaced by a fuzzy inner product. An excitatory connection is represented by a MIN (minimum) operation and an inhibitory connection by fuzzy logic complement followed by a MIN operation. While an ordinary neuron model is established only by leaning, the fuzzy neuron can be designed and optimized by learning. The fuzzy neuron is implemented in silicon wafer by a standard BiCMOS process. The chip is applied to a handwritten character recognition system and it exhibits very high-speed recognition (less than 500 ns)     

神经网络模糊推理系统在火灾探测中的应用

提出了一种用于火灾自动探测的神经网络模糊推理系统，它采用前馈神经网络对火灾探测器信号进行处理，神经网络输出的火灾概率经模糊推理系统判决，输出火灾报警信号。这种方法结合了神经网络和模糊逻辑的优点，实验表明这种系统能够准确探测火灾并减少了误报警。     

随机模糊神经网络的参数学习算法

在输入和输出信号均有噪声污染的情况下,提出随机模糊逻辑神经网络系统及其参数学习算法,给出了参数学习公式;仿真计算表明本文所提出的算法的有效性,它明显优于没有考虑噪声的模糊逻辑神经网络系统。     

补偿模糊神经网络自适应逆控制的仿真研究

该文应用的补偿模糊神经网络（CFNN）是结合补偿模糊逻辑和神经网络的混合系统。由于引入补偿神经元使网络容错性更高,系统更稳定;同时模糊运算采用动态的、全局优化运算,并在神经网络学习算法中动态优化补偿模糊运算,使网络更适应,训练速度更快。将补偿模糊神经网络与白适应逆控制原理结合应用到某位置伺服系统噪声消除控制中,并同用BP网络,传统PID控制和常规模糊神经网络控制效果比较来证明此方法的优越性。仿真结果表明补偿模糊神经网络自适应逆控制在缩短训练时间,提高控制精度等方面都有显著改善。     

A novel fuzzy logic system based on N-version programming

For the consideration of different application systems, modeling the fuzzy logic rule, and deciding the shape of membership functions are very critical issues due to they play key roles in the design of fuzzy logic control system. This paper proposes a novel design methodology of fuzzy logic control system using the neural network and fault-tolerant approaches. The connectionist architecture with the learning capability of neural network and N-version programming development of a fault-tolerant technique are implemented in the proposed fuzzy logic control system. In other words, this research involves the modeling of parameterized membership functions and the partition of fuzzy linguistic variables using neural networks trained by the unsupervised learning algorithms. Based on the self-organizing algorithm, the membership function and partition of fuzzy class are not only derived automatically, but also the preconditions of fuzzy IF-THEN rules are organized. We also provide two examples, pattern recognition and tendency prediction, to demonstrate that the proposed system has a higher computational performance and its parallel architecture supports noise-tolerant capability. This generalized scheme is very satisfactory for pattern recognition and tendency prediction problems     

二级倒立摆的Sugeno型模糊神经网络控制

为了提高二级倒立摆系统实时控制的响应速度和稳定性,在设计Mamdani型模糊推理规则控制器控制倒立摆系统稳定的基础上,设计了一种更有效率的基于Sugeno型模糊推理规则的模糊神经网络控制器.该控制器使用BP神经网络和最小二乘法的混合算法进行参数训练.能够准确归纳输入输出量的模糊隶属度函数和模糊逻辑规则.通过与Mamdani型控制器的仿真对比及实际控制实验结果,表明该Sugeno型模糊神经网络控制器时二级倒立摆实验装置的控制具有良好的稳定性、快速性和较高的控制精度.     

心电图的智能识别技术

模糊逻辑、神经网络是人工智能的重要分支,它们从不同角度、在一定程度上模拟了人类智能。本文先后将模糊逻辑、神经网络以及模糊神经网络技术用于心电图识别,获得了良好的效果。在模糊识别方面,从模糊识别矩阵的建立到模糊输入向量的确定,是针对此类具体问题的多传感器模糊信息融合算法,既综合考虑了各输入变量的作用,又突出了识别的主要依据。本文还给出了神经网络识别的三种试验结果及其与模糊神经网络识别的对比。模糊神经网络既充分发挥了神经网络的学习功能,又充分发挥了模糊逻辑的推理功能,因此具有很高的识别精度。     

基于补偿神经网络的航空电子故障智能诊断系统及应用

针对航空电子系统中故障诊断的问题，提出一种将神经网络中的BP算法与模糊逻辑系统相结合、自动产生并自动修正模糊规则的自适应的模糊逻辑推理机。通过函数逼近仿真分析和航空电子系统故障诊断的实际应用，证明此方法简单有效，故障诊断的精度高，取得了较好的效果，具有一定的应用前景。     

一种基于模糊B样条基函数神经网络控制的磨削加工系统

本文将模糊控制与神经网络相结合。用神经网络来实现模糊推理,提出了一种把B样条函数作为隶属函数的模糊神经网络,并将之用于磨削加工的质量控制。仿真结果表明,该系统具有响应快、稳态精度高、鲁棒性强等优点,能很好地应用于磨削加工的质量控制。     

几种模糊神经网络系统关系的对比研究

本文对几种不同结构形式的模糊神经网络系统 ,从不同的模糊逻辑算式入手,对所具有的功能、不同的表达式及其相互之间的关系式,以 及所表现出来的优缺点进行深入的分析与对比研究,从而揭示模糊逻辑系统的实质内容,为 选择和应用模糊神经网络的设计方法提供一些作者的见解．     

基于修剪策略的D-FNN直接逆控制算法研究

神经网络是模拟人脑结构,它具有大规模并行及分布式信息处理能力,但是不能处理和描述模糊信息.模糊系统具有推理过程容易理解,但它很难实现自适应学习的功能.如果结合神经网络与模糊系统,可以取长补短.基于此,本文提出了一种新型动态模糊神经网络（Dynamic fuzzy neural network,D-FNN）学习算法.因为它具有结构和参数同时调整且学习速度快等优点,所以既可以在模糊逻辑系统中包含低级的神经网络学习和计算功能,也可以为神经网络提供高级的类似人的思维和推理的模糊逻辑系统.此外,本文还开发了生物医学工程应用算法程序,针对药物注射系统的直接逆控制案例进行了仿真,结果表明:D-FNN具有实时学习和控制能力强、参数估计和结构辨识同时进行等优点.