基于自适应尺度边缘特征的建筑施工图重叠字符识别方法研究

目前非重叠字符的识别技术已趋于完善,但难以识别建筑工程图纸标注等场景中的重叠字符,阻碍了基于二维扫描图纸的自动建模技术的突破。针对传统字符识别方法无法识别重叠字符的现状,提出了一套基于自适应尺度边缘特征的建筑施工图重叠字符识别新方法。基于像素空间分布特征初步确定重叠字符区域,定义并提取字符的自适应尺度边缘特征;借助双变量匹配概率函数筛选“位置+内容”的结果组合,并以全局最优原则代替绝对阈值作为识别标准,最终输出正确的识别结果。不同于先修复后识别的常规思路,该方法将特征匹配与干扰过滤相结合、字符定位与字符识别相关联,能解决百度等成熟商用OCR无法解决的重叠字符识别问题,且经数据实验证实具备较高的识别准确率。     

应用两级分类实现车牌字符识别

在分析特征提取方法的基础上,提出了一种模拟人类智能的两级分类识别算法。第一级采用描绘字符整体信息的统计特征,利用SVM分类器进行识别;第二级采用描绘字符细节信息的结构特征,依据决策表区分形近字符,使车牌中形近字符的识别率得到提高。算法对提取的统计特征值进行了优化调整,使其有效地克服了字符偏移的影响,并引入可信度评判机制,使SVM分类器的性能得以提高。     

适合特定水表表型的字符识别方法

根据特定水表走字的特点,提出了一种基于模板和神经网络的水表数字字符识别的方法.该方法利用特定表型中待识别区域宽高比例相同的特点,提出用特征模板缩放法来进行待识别区域的定位和字符分割.采用三灰度值加权系数进行模板匹配,提高了特征的利用率;采用自适应学习的BP神经网络训练全字符和半字符样本,用户直接使用训练好的神经网络联结权值进行字符识别.结果表明,充分利用待识别区域的特征有助于提高识别区域定位和字符分割的准确性,在此基础上,采用经典的识别算法能够取得较好的效果.     

BP神经网络在车牌字符识别中的应用研究

研究车牌字符识别问题,针对传统神经网络在车牌字符识别存在识别准确率低、效率低的问题,提出了一种基于改进神经网络的车牌字符识别方法.该方法首先采用Gabor滤波器提取车牌字符的特征,PCA降维处理消除车牌字符特征之间的冗余信息,然后采用改进的神经网络对提取特征进行训练得到最优识别模型,最后利用最优模型对车牌字符进行识别.仿真实验表明,数字及字母的识别准确率达95.0%以上,汉字的识别准确率达93.1%,与传统识别方法相比,识别准确率和识别速度都有了较大的改进,该方法在车牌识别的应用有着广泛的前景.     

基于不变矩和神经网络的常用电气符号自动识别方法研究

工程图纸中电气符号的自动识别是实现电气工程图纸矢量化的基础。提出了提取工程图纸中电气符号的不变特征。把不变特征值输入神经网络进行训练，得到神经网络模型识别旋转、平移、缩放电气元件图元的方法。实验结果表明：所建立的网络模型具有较好的性能。将此方法用于工程图纸的矢量化处理过程，只需识别出电力工程图纸中各个符号的类型，避免了图纸矢量化过程中的跟踪和拟合的过程，因此优化了矢量化流程。     

基于整体特征神经网络数字二次识别方法

根据数字字符整体特征, 提出一种基于字符整体特征的Bp神经网络数字二次识别方法. 该方法首先根据Bp神经网络原理对数字字符进行预识别; 然后对预识别结果中存在混淆的字符按照字符整体特征进行二次识别, 从而准确获得识别结果. 该方法结合了神经网络非线性、自主学习特点和字符整体特征形状结构不变性特点, 有效的在低样本量情况下, 获得较高的字符识别精度.     

车牌超分辨率重建与识别

为了从图片中快速准确地识别车牌,提出一种结合图像超分辨率技术的车牌识别方案。车牌图片具有明显的特定的模式特征,只是具体的字符编码不同。因此车牌图片非常适合做超分辨率重建。本文提出的系统主要由车牌检测定位、车牌超分辨率重建、字符分割、字符识别等模块组成。综合基于边缘、基于颜色和基于最大稳定极值区域三种车牌检测策略并采用并行编程方法来综合检测结果得到候选车牌。采用车牌图片正负样本来训练支持向量机分类器。得到分类器模型后对候选车牌判决得到真正的车牌。随后对真实车牌图片进行超分辨率重建。该部分主要由基于固定邻域回归的方法实现。这种方法综合了稀疏字典学习和领域嵌入的方法,比较好的兼顾了准确率和计算速度。运用OpenCV提供的图像处理库来对重建后的图片做字符分割。得到单独的字符图片后采用人工神经网络进行识别。识别前先使用一定数量的字符图片对网络进行有监督训练获取识别模型。采用一个单隐层的神经网络,运用反向传播算法进行训练得到识别模型。最后提取字符图片的特征并输入网络进行分类完成识别。为了测试系统的表现,在实际场景中采集了一百张车牌图片作为测试集。实验表明,该系统具有较高识别准确率和较快的处理速度。     

快速精确识别车牌字符的方法

提出了一种利用车牌字符集特征来优化字符骨骼处理、改进骨骼变长编码的新方法,并把其用于车牌字符精确识别.该方法先利用车牌字符集特征优化处理标准车牌字符骨骼,再将"替换规则"与8方向链码相结合对其进行变长编码的结果作为模板,然后用同样方法得到待识别的车牌字符编码,将该编码与模板进行最佳匹配,实验结果表明,该方法具有实现简单、处理数据量小、抗旋转和对低分辨率车牌字符识别性能好等优点.     

基于特征行必要-充分性匹配的字符识别方法

字符识别系统的性能在很大程度上依赖于所选取的字符特征.提出了一种基于特征行必要-充分性匹配的OCR(optical character recognition)方法.该方法使用字符模板的特征行集,通过对待识字符位图进行必要性和充分性双向匹配来识别字符.并采用基线对齐归一化方法在特征匹配时准确定位,使识别率和识别速度都较为理想.同时,对字符位图特征行的交互选择、测试和调整等方法做了详细介绍.另外,还提出了字符骨架与位图重叠显示的方案,有效地提高了对识别结果校对的速度.最后,通过测试和比较,对识别效率进行了分析.     

一个基于扫描串的统一整体矢量化算法

工程图纸扫描识别和字符笔画提取一直是模式识别中的难点问题.为克服细化算法逐象素处理的局部特性,已提出了一些整体算法.基于图段的整体识别算法突破了细化算法在象素层次做局部操作的局限,力图抓住图象的宏观特征进行整体识别;但它在处理小线素、曲线及字符图象时仍有较大局限性.本文采用扫描串（行程编码）作为基本处理单元,动态扫描整个图象数据,利用预先建立的信息头指导后续跟踪,得到了更精确的矢量化结果.本文提出的算法可适用于各种不同工程图纸的处理,用来提取汉字笔画也得到了满意的结果.     

基于科技文档的AutoCAD 插图精准出图方法

插图中的文字高度、图线线宽和图纸比例的精准打印输出,对制图类教材或教学 课件等科技文档十分重要。为了能精确出图,在分析文字信息版面占优势的科技文档中 AutoCAD 插图制作方法的基础上,从几个绘图概念出发,研究了插图的显示特性、图形对象的 图线宽度和图中文字高度的属性特征。研究表明,只需将Word 软件所测得的插图原始尺寸看 成制作AutoCAD 图形的绘图画布和物理纸张的图幅尺寸,精准设置图形的打印出图比例、线 宽和文字高度的属性值,就能通过科技文档打印输出既精准又符合制图规范的插图。     

试谈卡通漫画人物的绘制

随着科技的发展,卡通漫画的绘制已经不仅仅局限于传统绘制,还包括用数位板在绘图软件里直接绘制漫画作品。介绍了使用数位板在图像处理软件PhotoShop中绘制卡通漫画人物的方法。     

字符粘连及字线相交的分割与识别方法

描述了工程图纸矢量化中多向粘连字符及字线相交的分割算法与识别方法.提出不同情况下字串的定向计算方法,通过粘连字块的特征矢量计算和迭代计算实现字块的分割.运用波形投影方法解决了粘连字符及字线相交情况下的字间切割问题,使工程图多向字符识别精度显著提高,该算法对局部退化状态下的字符识别具有良好的抗干扰性.     

Pitch-based segmentation and recognition of dot-matrix text

Dot-matrix text recognition is a difficult problem, especially when characters are broken into several disconnected components. We present a dot-matrix text recognition system which uses the fact that dot-matrix fonts are fixed-pitch, in order to overcome the difficulty of the segmentation process. After finding the most likely pitch of the text, a decision is made as to whether the text is written in a fixed-pitch or proportional font. Fixed-pitch text is segmented using a pitch-based segmentation process that can successfully segment both touching and broken characters. We report performance results for the pitch estimation, fixed-pitch decision and segmentation, and recognition processes. Received October 18, 1999 / Revised April 21, 2000     

CHITRA: Cognitive handprinted input-trained recursively analyzing system for recognition of alphanumeric characters

A novel system for recognition of handprinted alphanumeric characters has been developed and tested. The system can be employed for recognition of either the alphabet or the numeral by contextually switching on to the corresponding branch of the recognition algorithm. The two major components of the system are the multistage feature extractor and the decision logic tree-type catagorizer. The importance of good features over sophistication in the classification procedures was recognized, and the feature extractor is designed to extract features based on a variety of topological, morphological and similar properties. An information feedback path is provided between the decision logic and the feature extractor units to facilitate an interleaved or recursive mode of operation. This ensures that only those features essential to the recognition of a particular sample are extracted each time. Test implementation has demonstrated the reliability of the system in recognizing a variety of handprinted alphanumeric characters with close to 100% accuracy.Most of this work was carried out at the School of Automation, Indian Institute of Science, Bangalore, India.     

VxWorks下PCI9054显卡图形开发库的实现

介绍了一种基于VxWorks操作系统的PCI9054显卡的图形开发库,实现了基本绘图功能,汉字和字符的显示功能,以及贴图存图的功能,满足综合显示的需求。     

基于AutoCAD工程图形评判中文本判别的研究

AutoCAD环境下工程图学的作业和试卷的智能化评阅中,文本的自动判别是重要的一部分,为了解决这一问题,文中根据AutoCAD中一般图形识别的原理和文本特有的属性特征,对AutoCAD环境下工程图形中文本判别可能出现的“漏填”、“错填”、“多填”、“位置不对”等情况作了分类讨论和研究,并在AutoCAD内嵌的VBA编程环境中,进行了程序实现,可广泛应用于基于AutoCAD的工程图学的智能化作业或是智能化考试软件中。     

Automatic generation of fabrication drawings for façade mullions and transoms through BIM models

Fabrication drawings are essential for manufacturing, design evaluation and inspection of building components, especially for building façade structural components. In order to clearly represent the physical characteristics of the façade structural components, a large number of section views need to be produced, which is very time-consuming and labor intensive. Therefore, automatic generation of fabrication drawings for building façade components (such as mullions and transoms) is of paramount importance. In this paper, attempts have been made to develop an efficient framework in order to automatically generate fabrication drawings for building façade structural components, including mullions and transoms. To represent the complex physical characteristics (such as holes and notches) on mullions and transoms using minimum number of drawing views, a computational algorithm based on graph theory is developed to eliminate duplicated section views. Another methodology regarding the generation of breaks for top views is also proposed to further improve the quality of drawing layouts. The obtained drawing views are then automatically arranged using a developed approach. In addition, primary dimensions of the drawing views focusing on the physical features are also generated. Furthermore, in order to maintain the consistency of drawing formats across multiple drawings, a methodology is proposed to determine the scaling factors of the drawings by using clustering technique. In an illustrative example, the proposed framework is used to generate the fabrication drawings for a typical BIM model containing façade structural components, and saving in time is observed.     

Image-based pencil drawing synthesized using convolutional neural network feature maps

In most cases, the conventional pencil-drawing-synthesized methods were in terms of geometry and stroke, or only used classic edge detection method to extract image edge characters. In this paper, we propose a new method to produce pencil drawing from natural image. The synthesized result can not only generate pencil sketch drawing, but also can save the color tone of natural image and the drawing style is flexible. The sketch and style are learned from the edge of original natural image and one pencil image exemplar of artist’s work. They are accomplished through using the convolutional neural network feature maps of a natural image and an exemplar pencil drawing style image. Large-scale bound-constrained optimization (L-BFGS) is applied to synthesize the new pencil sketch whose style is similar to the exemplar pencil sketch. We evaluate the proposed method by applying it to different kinds of images and textures. Experimental results demonstrate that our method is better than conventional method in clarity and color tone. Besides, our method is also flexible in drawing style.     

参数化桩帽自动绘图系统的设计与实现

港口工程中有大量标准化构件。将这些标准化构件的制图进行参数化、程序化不但可以减少大量重复性劳动,还可以大幅度提高工程制图的效率和质量。利用Auto CAD 内嵌的具有强大功能的VBA开发出带有人性化用户界面的参数化桩帽结构配筋自动绘图系统。该系统中集成了参数化设计和图库管理,显著提高了桩帽设计过程中的绘图质量和效率。