基于粗网格神经网络的车牌字符识别方法
The Recognition of Vehicles＇ License Plates Characters Based on Rough Grid Neural Network
吴成东[1] 刘文涵[1] 傅小菲[2] 丛明[1]
目的为了进一步提高交通车牌字符自动识别能力．方法通过对车牌识别技术国内外现状的分析和对各类车牌识别技术的对比说明，提出了一种基于粗网格神经网络的车牌文字识别方法．该方法先将车牌字符进行预处理，用改进的粗网格法提取字符特征，并用神经网络识别车牌字符．结果在实验过程中所用的字符是从实际拍摄的车辆牌照图像中提取的汉字、英文大写字母和数字．人工提取的汉字种类覆盖了我国现有车辆牌照中出现的大部分汉字，而字母和数字的覆盖率为100％．从实验结果看：数字、字母的识别率比较高，尤其是数字，其识别率达到了99．16％．结论实验表明：数字、字母易于准确地提取特征，粗网格神经网络车牌字符识别方法具有较高的识别精度和实用价值．[著者文摘]
the paper aims to recognizing vehicles＇ license plates characters via analysis of intelligent algorithms deployed on recognition of vehicles＇ license plates. The method of recognizing rough grid features based on neural network are proposed, after literature review and comparison of generally used recognition method on vehicles＇ license plates. In this method, character images are preprocessed at the beginning, then the improved rough grid features are extracted from the original images, and finally the extracted features were used to train the neural network. All the characters used in the case study, such as Chinese characters, capital English letter, number are extracted from real image. The artificially extracted Chinese characters can cover the mostly used Chinese characters on vehicles＇ license plates and the extracted English letter and number totally match the real situation. The recognition rate on number and letter are very high. The recognition rate on number is 99.16 %. The results show that the proposed rough grid features recognition method is feasible and effective.[著者文摘]
基于人工神经网络自适应共振理论的手写字符识别
Handwritten character recognition based on adaptive resonance theory of artificial neural network
韩可轶 周德俭 张烈平 谢晓兰
以人工神经网络中的自适应共振理论为基础，研究了用光标在电脑屏幕上进行手写输入的字符识别方法．根据专业领域文字输入中经常使用特殊字符的特点，程序部分由内核是Unicode的Java实现．采用Unicode编码不但可以方便地实现特殊字符的识别和显示，还有利于跨平台的移植，较好地解决了文字录入中特殊字符不易查找以及某些用户操作键盘不便等实际问题．[著者文摘]
Based on the artificial neural network （ART）, the recognition of handwritten characters inputting at the computer screen with the cursor is developed. As some special characters are often input in professional field, the program is realized in Java in which Kernel Unicode. Adoption of Unicode code can not only realize the recognition and the display of character conveniently, but also benefit transplanting in different system. It will be better to solve some problems of characters inputting, such as special characters that are difficult to find out and some users operate keyboard inconveniently.[著者文摘]
基于BP神经网络的金属材料字符识别研究
the Research of the Character Recognition on the Metal Materials Base on the BP Neural Network
赵巍 邵建龙
字符识别是模式识别领域的一项传统课题．其内容是模式识别领域中很多课题的基本内容。人工神经网络的出现为字符识别的研究提供了一种新的手段，BP神经网络（Back Propagation Neural Network）作为人工神经网络的一个分支，现已成为其最广泛的应用。本文以三层BP网络作为模型．并将其应用于对金属角铁上的字符识别。由于角铁字符为数字与英文字母混合．文中在对传统的BP算法进行了改进的基础上，采用了分组神经网络的设计方法．取得了良好的识别效果。[著者文摘]
Character recognition is a classical problem in the field of the mode recognition and it is also the basal content in the other problem. Artificial Neural Network （short for ANN） provides a new means to study the recognition of the character. Back Propagation Network （short for BP network） as a branch of the ANN, have had a very widely application. This paper introduces a 3-1ayer BP network and applies it to the recognition of the character in the angle iron. Because the characters include the number and the English character, the designing process adopts multi-group neural network system as well as improves the classical BP arithmetic to get well effect.[著者文摘]
一种基于径向基神经网络的车牌字符识别方法
植俊文[1] 戴青云[1] 黄雪贤[2]
径向基函数神经网络具有局部逼近的能力和局部可调的特性，以车牌字符识别为例，构造了一种实用型的径向基神经网络，并与传统的BP神经网络作了对比。实验结果表明，在车牌字符识别中，径向基网络的识别能力、分类能力及识别速度等均优于BP网络。[著者文摘]
基于BP神经网络的数显仪表动态字符识别系统
Recognition system of character of numeral instrument dynamic displayed on BP neural network
唐轶峻 申小阳 朱雯兰 隋成华
在化工、冶金等行业以及较为恶劣的环境场合下进行仪表数据的自动化采集，需要对仪表显示的动态数据进行自动识别，以判断是否满足控制条件。因此根据数字仪表图像的特点，运用区域生长算法定位仪表图像中的数据区域，并取得理想的效果，采用投影法对字符串进行分割，最后应用BP神经网络法进行分类识别数字字符，实验结果表明，其正确识别率达到96％。[著者文摘]
Data displayed by instrument need be usually automatically collected in chemical industry, metallurgy fields and some other dangerous condition, so it＇s important for the data to be recognized, thus the control system can judge whether they satisfied the control condition. According to the feature of numeral instrument image, region growing method is used to locate the data region and which has reached ideal effect, projecting method is applied to segment the string, and the BP neural network to classify recognition numeral characters. The correct rate has reached 96 % by experimentation.[著者文摘]
BP神经网络算法在字符识别中的应用
The Application of BP Neural Network Algorithm in the Character Recognition
贾少锐[1] 李丽宏[1] 安庆宾[2]
介绍了BP学习算法的基本原理及其优缺点，并针对其不足，引入了动量项进行改进，并对BP网络的算法实现作了探讨。[著者文摘]
This paper introduces the basic principles, advantages and disadvantages of BP learning algorithm, in the light of its disadvantages, introduces the momentum item to improve this algorithm, and probes into the implementation of BP network algorithm.[著者文摘]
基于神经网络的机动车号牌字符识别
韩笑 马驷良 张禹 左平
以定位、分割后的机动车号牌字符为研究对象．首先，对机动车号牌图像进行大小、灰度方差、灰度均值的标准化处理．其次，根据机动车号牌字符的特点，抽取字符3种不同的特征，构造3个BP神经网络对机动车号牌字符进行识别．并根据字符在机动车号牌中所处位置的差异，在每个BP神经网络中构造4种不同的子网络分别进行训练和识别．最后，每个BP神经网络的输出通过加权求和的组合方式得到最终识别结果．在组合各网络输出前，采用对字符图像求取局部二阶差分值的方法，将字形相近的字符进行再分类，从而有效地降低误识率．通过分析实验结果，表明本算法在机动车号牌识别应用中达到了理想的识别效果。
基于神经网络的轮胎胎号字符识别
李留格[1] 梁玲[2]
介绍了采用BP神经网络来进行轮胎胎号字符识别的一种尝试性方法。用Matlab来模拟用神经网络进行胎号数字识别这一过程，用投影—变换系数法进行特征提取，确定特征输入、隐含层的神经元和输出后，经训练后可识别胎号，识别率尚可。
基于神经网络的字符识别技术研究
黄瀚敏 易正俊
本文在分析人工神经网络理论和图象处理及其特征提取理论的基础上，探讨了网络结构、特征编码、算法的实现、学习样本的收集、网络参数的选择及ＢＰ算法缺陷等问题，设计并实现了一种基于神经网络的字符识别系统。
基于BP网络的噪声字符识别系统
On the Identification System of Noise Characters Based on BP Net
廖家平 汪媛
介绍了BP网络的基本理论并讲述了怎样运用它来识别带噪声的数字系统．最后使用MATLAB对网络进行仿真，仿真结果，证实系统能够很好地对带噪声的数字进行识别．[著者文摘]
The basic theories of the BP net are introduced in this paper, which shows how to apply these theories to identify the characters which are BP net, according to the result of which the rectly. corrupted. In the end, the MATLAB is BP net is found to be able to identify the used to simulate the noisy characters cor[著者文摘]