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．     

文字相关的单字符字体识别方法

汉字具有丰富的字体类型,并且不同的字体在汉字结构上有显著的不同,现在的OCR技术侧重字的识别,而对字体识别的关注较少。提出文字相关的单字符字体识别方法,利用文字相关的先验信息及字体结构特征,对字体的相似性度量采用向量空间模型,并针对常用66款简体字进行实验,得到了较好的平均识别率。     

完全基于结构知识的汉字笔画抽取方法

从汉字结构知识出发,提出了一种从汉字图像直接抽取笔画的算法,给出了抽取横、竖、撇、捺４种笔画的完全量化的昨去除不同字体的笔画修饰噪声的规则,该方法较好地解决了各笔画的相交、相连及噪声排队等总理２,综在汉字识别及字体自动生成等汉字信息处理方面有重要作用。     

基于蚁群算法的现代藏文字符轮廓提取技术研究

由于对字符提取骨架往往会失去受污损部位的重要信息,因此本文提出了一种基于蚁群算法的现代藏文字符轮廓提取算法,旨在用字符的轮廓线代替骨架线来表征字符。本算法用于印刷体藏文轮廓提取,取得了良好的效果,避免了传统细化算法造成的畸变,提高了轮廓提取的抗干扰能力,并且减小了计算量,加快了特征提取的速度。     

基于形态学的新的汉字字形自动生成方法

电子印刷,桌面出版,艺术,广告等领域对不同风格汉字的需求,迫切需求一种自动的汉字字形生成方法。传统方法只适用于两种字形相关不大的字体进行合成,并且需人干预,本文通过对字体的凸剖分,并建立两种不同字体的子凸集映射,提出了一种全新的基于形态变换的汉字形自动生成方法,     

车辆牌照上英文和数字字符的结构特征分析及提取

为了研制高性能的车辆牌照自动识别系统，在详细分析车辆牌照上英文和数字字符结构特点的基础上，选择字符图象中的闭合曲线作为其整体特征，将笔画端点，三叉点和四叉点作为其细节特征，同时将笔画中的拐角点作为其辅助结构特征，三者可分别用于字符的粗分类，细分类和相似字符区分，进而提基于图论和细节点特征的闭合曲线检测算法以及基于二值图象外边缘轮廓线的笔画拐角点检测算法，将上述结构特征用于车辆牌照上英文和数字字符识别，测得识别率达96％，用PⅢ550计算机完成结构特征抽取和字符识别所用时间约20ms／字符，表明这些结构特征适用于车辆牌照上英文和数字字符的快速识别。     

Direction histogram: novel discriminative global feature for Thai offline handwritten OCR

The image feature used for classification is a crucial part of a character recognition system. To achieve a high accuracy of offline handwriting recognition, the feature should capture the essence of differences including the differences between different characters and the differences between different drawings of the same character. In this paper, we present a novel image feature called direction histogram (DH) and a feature extraction algorithm called bag of histogram (BoH). Unlike the traditional pre-defined feature, DH was designed based on the nature of language and the variation of writing styles. DH is, therefore, a global feature that represents pixel density in all directions around each center. BoH was introduced as it tolerates to thickness and curve variation and ignores the curve connectivity (if any). Fifty-two datasets, each containing 30 drawings of 80 Thai characters, are used for training our neural network, and the original, thick, and distorted handwriting datasets are used for testing. The recognition system with our proposed DH and BoH feature extraction algorithm yielded higher recognition accuracy compared to the convolutional neural network.     

Generating Chinese characters based on stroke splitting and feature extraction

There is a large demand for more fashionable style Chinese characters in advertising, art designing and publishing markets. However, it becomes challenging to create a new font style for so many Chinese characters (over 10,000). To solve this problem, a comprehensive Chinese fonts generating scheme is proposed in this paper. Firstly, a decomposition database for stroke splitting and feature extraction is proposed. Secondly, stroke segmentation rules are defined based on splitting, merging and structural model, location definition and minimum feature extraction. Thirdly, a radical searching algorithm based on stroke splitting is presented. Finally, it is realized that the generated characters can be zoomed, rotated and moved. Experimental result shows that Chinese characters with a new style can be generated rapidly with the proposed scheme. The created characters fit the real ones well with a high fidelity of 96.4%. The usability tests are run and participants’ subjective report show that the performance from the generated characters is similar to the original characters in both recognizability test and style-consistency test. The fonts generating method is also reliable for the other stroke constructed block characters such as Japanese and Korean characters.     

基于霍夫变换和弹性网格的手写汉字识别方法

特征提取是手写体汉字识别的关键环节.弹性网格特征是一种较好的手写体汉字特征,但是无法体现汉字的整体结构信息,为此提出了一种采用复合特征进行手写体汉字识别的方法.该方法采用霍夫变换提取汉字图像的全局特征,并把这些全局特征与用弹性网格方法提取出的局部特征联合起来,这样得到的混合特征完整地反映了汉字全局特征和局部特征.最后通过实验证明,在进行大类别手写体汉字识别时,在特征值维数相同的情况下,采用这种复合特征的识别率明显高于单一的弹性网格特征,因此该方法是行之有效的.     

An investigation of the modified direction feature for cursive character recognition

This paper describes and analyses the performance of a novel feature extraction technique for the recognition of segmented/cursive characters that may be used in the context of a segmentation-based handwritten word recognition system. The modified direction feature (MDF) extraction technique builds upon the direction feature (DF) technique proposed previously that extracts direction information from the structure of character contours. This principal was extended so that the direction information is integrated with a technique for detecting transitions between background and foreground pixels in the character image.In order to improve on the DF extraction technique, a number of modifications were undertaken. With a view to describe the character contour more effectively, a re-design of the direction number determination technique was performed. Also, an additional global feature was introduced to improve the recognition accuracy for those characters that were most frequently confused with patterns of similar appearance. MDF was tested using a neural network-based classifier and compared to the DF and transition feature (TF) extraction techniques. MDF outperformed both DF and TF techniques using a benchmark dataset and compared favourably with the top results in the literature. A recognition accuracy of above 89% is reported on characters from the CEDAR dataset.     

复杂彩色文本图像中字符的提取

从复杂彩色文本图像中提取和识别字符已经成为一个既困难又有趣的问题。本文给出了一个具有创新性和实用性的区域生长算法用于彩色图像的分割:彩色图像游程邻接算法CRAG(color run-length adjacency graph algorithm)。我们将该算法用于彩色文本图像,首先得到图像的彩色连通域,再对这些连通域的平均颜色进行颜色聚类,可得到若干个聚类中心,然后根据不同的颜色中心将图像分为相应的彩色层面,最后通过连通域分析判断所需的文字层。该生长算法修改并扩展了传统的BAG算法,并将其运用于彩色印刷体文本图像中,充分利用了彩色图像的颜色和位置信息。实验结果表明新的方法能很好的从彩色印刷图像中提取多种常见的艺术字,并具有较高的提取速度,同时保留了文字和背景图像的原始色彩,便于将来的图像恢复。     

A deep learning based bank card detection and recognition method in complex scenes

With the widespread use of mobile Internet, mobile payment has become a part of daily life, and bank card recognition in natural scenes has become a hot topic. Although printed character recognition has achieved remarkable success in recent years, bank card recognition is not limited to traditional printed character recognition. There are two types of bank cards: unembossed bank cards, such as most debit cards which usually use printed characters, and embossed bank cards, such as most credit cards which mainly use raised characters. Recognition of raised characters is very challenging due to its own characteristics, and there is a lack of fast and good methods to handle it. To better recognize raised characters, we propose an effective method based on deep learning to detect and recognize bank cards in complex natural scenes. The method can accurately recognize the card number characters on embossed and unembossed bank cards. First, to break the limitation that YOLOv3 algorithm is usually used for object detection, we propose a novel approach that enables YOLOv3 to be used not only for bank card detection and classification, but also for character recognition. The CANNYLINES algorithm is used for rectification and the Scharr operator is introduced to locate the card number region. The proposed method can satisfy bank card detection, classification and character recognition in complex natural scenes, such as complex backgrounds, distorted card surfaces, uneven illumination, and characters with the same or similar color to the background. To further improve the recognition accuracy, a printed character recognition model based on ResNet-32 is proposed for the unembossed bank cards. According to the color and morphological characteristics of embossed bank cards, raised character recognition model combining traditional morphological methods and LeNet-5 convolutional neural network is proposed for the embossed bank cards. The experimental results on the collected bank card dataset and bank card number dataset show that our proposed method can effectively detect and identify different types of bank cards. The accuracy of the detection and classification of bank cards reaches 100%. The accuracy of the raised characters recognition on the embossed bank card is 99.31%, and the accuracy of the printed characters recognition on the unembossed bank card reaches 100%.

     

基于单字符注意力的全品类鲁棒车牌识别

复杂场景下的高精度车牌识别仍然存在着许多挑战,除了光照、分辨率不可控和运动模糊等因素导致的车牌图像质量低之外,还包括车牌品类多样产生的行数不一和字数不一等困难,以及因拍摄角度多样出现的大倾角等问题.针对这些挑战,提出了一种基于单字符注意力的场景鲁棒的高精度车牌识别算法,在无单字符位置标签信息的情况下,使用注意力机制对车牌全局特征图进行单字符级特征分割,以处理多品类车牌和倾斜车牌中的二维字符布局问题.另外,该算法通过使用共享参数的多分支结构代替现有算法的串行解码结构,降低了分类头参数量并实现了并行化推理.实验结果表明,该算法在公开车牌数据集上实现了超越现有算法的精度,同时具有较快的识别速度.     

Outline字体结构式压缩算法及其实现

针对CJK Outline字体在存储量上存在的不足,本文提出一种结构式压缩算法。算法对CJK字体进行集合变换,得到笔划集合元素;并利用聚类算法得到模板笔划;对相似数据进行统一存储与调用。同时,本文还提出了一种基于笔划段的笔划抽取算法,从图论角度实现了集合变换。结果显示,算法取得了较好的效果,而且适用于多种字体。     

基于BP神经网络的印刷字符识别系统

光字符识别对人类是很简单的,但对计算机来说显得非常困难。自动字符识别在银行、航运、商业、通信、车牌识别等重要领域应用相当广泛。该文的主要任务是开发一个能识别机器印刷英文字符的系统,该系统采用基于反向传播的多层神经网络监督训练算法。通过系统进行多次测试和调试,不断优化网络参数并取得最佳结果,使得构建的新系统能够识别多种字体的字符。实验结果表明,该系统具有较高的识别率和优越的性能。     

局部关联度最优的手写汉字骨架提取

目的 研究手写汉字图像时,骨架是最为常见的切入点之一。利用传统细化算法提取手写汉字骨架,容易在笔画交叉等情况复杂的区域产生形变。针对此问题,提出一种基于局部关联度的手写汉字骨架提取算法。方法 首先对手写汉字图像进行细化以获取原始骨架,按照端点、普通点和复杂点3种类别标注骨架点;利用8邻域窗口扫描相互连通的复杂点,检测并提取复杂区域;删除复杂区域,将原始骨架拆分为若干简单笔画段,形变部分在此过程中被一并移除;提取局部子段,根据笔画段间的方向差异程度和曲率变化程度,计算局部关联度;制定一种局部关联度最优的连接策略,对满足连接条件的笔画段进行插值补偿,从而修正形变,并得到完整的汉字骨架。结果 对于600个实验样本,从骨架直接检测复杂区域所得结果十分接近理想情况,而轮廓法所得数量是理论值的2.5倍;基于局部关联度重组笔画段,绝大多数形变得到修正,重组后的骨架符合真实拓扑结构;以标准骨架为参考,骨架提取准确率达到了98.41%。结论 局部关联度最优的手写汉字骨架提取算法,能够有效检测复杂区域,对形变具有良好的修正作用,提取所得骨架能够正确反映复杂笔画间的位置结构关系,是一种实用有效的骨架提取方法。     

基于字符图像分割的打印文件识别方法

针对目前的打印文件识别方法受限于样本中必须有相同字符的问题,提出一种基于字符图像分割的打印文件识别方法。通过k-means算法对字符图像进行分割,分别对不同区域提取局部二值模式纹理特征,从而消除字符结构对识别结果的影响。研究了单一区域的特征集和组合特征集的分类识别效果,实验结果表明,该方法在样本中无相同字符的情况下,能够得到较高的识别准确率。     

High accuracy optical character recognition using neural networkswith centroid dithering

Optical character recognition (OCR) refers to a process whereby printed documents are transformed into ASCII files for the purpose of compact storage, editing, fast retrieval, and other file manipulations through the use of a computer. The recognition stage of an OCR process is made difficult by added noise, image distortion, and the various character typefaces, sizes, and fonts that a document may have. In this study a neural network approach is introduced to perform high accuracy recognition on multi-size and multi-font characters; a novel centroid-dithering training process with a low noise-sensitivity normalization procedure is used to achieve high accuracy results. The study consists of two parts. The first part focuses on single size and single font characters, and a two-layered neural network is trained to recognize the full set of 94 ASCII character images in 12-pt Courier font. The second part trades accuracy for additional font and size capability, and a larger two-layered neural network is trained to recognize the full set of 94 ASCII character images for all point sizes from 8 to 32 and for 12 commonly used fonts. The performance of these two networks is evaluated based on a database of more than one million character images from the testing data set     

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.