基于卷积神经网络和Transformer的手写体英文文本识别

手写体文本识别技术可以将手写文档转录成可编辑的数字文档。但由于手写的书写风格迥异、文档结构千变万化和字符分割识别精度不高等问题,基于神经网络的手写体英文文本识别仍面临着许多挑战。针对上述问题,提出基于卷积神经网络（CNN）和Transformer的手写体英文文本识别模型。首先利用CNN从输入图像中提取特征,而后将特征输入到Transformer编码器中得到特征序列每一帧的预测,最后经过链接时序分类（CTC）解码器获得最终的预测结果。在公开的IAM（Institut für Angewandte Mathematik）手写体英文单词数据集上进行了大量的实验结果表明,该模型获得了3.60%的字符错误率（CER）和12.70%的单词错误率（WER）,验证了所提模型的可行性。     

Text line and word segmentation of handwritten documents

In this paper, we present a segmentation methodology of handwritten documents in their distinct entities, namely, text lines and words. Text line segmentation is achieved by applying Hough transform on a subset of the document image connected components. A post-processing step includes the correction of possible false alarms, the detection of text lines that Hough transform failed to create and finally the efficient separation of vertically connected characters using a novel method based on skeletonization. Word segmentation is addressed as a two class problem. The distances between adjacent overlapped components in a text line are calculated using the combination of two distance metrics and each of them is categorized either as an inter- or an intra-word distance in a Gaussian mixture modeling framework. The performance of the proposed methodology is based on a consistent and concrete evaluation methodology that uses suitable performance measures in order to compare the text line segmentation and word segmentation results against the corresponding ground truth annotation. The efficiency of the proposed methodology is demonstrated by experimentation conducted on two different datasets: (a) on the test set of the ICDAR2007 handwriting segmentation competition and (b) on a set of historical handwritten documents.     

A novel SVM-based handwritten Tamil character recognition system

This paper describes a system for recognizing offline handwritten Tamil characters using support vector machine (SVM). Data samples are collected from different writers on A4 sized documents. They are scanned using a flat bed scanner at a resolution of 300 dpi and stored as gray-scale images. Various preprocessing operations are performed on the digitized image to enhance the quality of the image. Pixel densities are calculated for 64 different zones of the image and these values are used as the features of a character. These features are used to train the SVM. The SVM is tested for the first time to recognize handwritten Tamil characters. The system has achieved a very good recognition accuracy of 82.04% on the handwritten Tamil character database.     

东巴象形文字文档图像的文本行自动分割算法研究

以卷积神经网络(CNN)为代表的深度学习技术在图像分类和识别领域表现出了非常优异的性能。但东巴象形文字未有标准、公开的数据集,无法借鉴或使用已有的深度学习算法。为了快速建立权威、有效的东巴文字库,分析已出版东巴文档的版面结构,从文档中提取文本行、东巴字成为了当前的首要任务。因此,结合东巴象形文字文档图像的结构特点,给出了东巴文档图像的文本行自动分割算法。首先利用基于密度和距离的k-均值聚类算法确定了文本行的分类数量和分类标准;然后,通过文字块的二次处理矫正了分割中的错误结果,提高了算法的准确率。在充分利用东巴字文档结构特征的同时,保留了机器学习模型客观、无主观经验影响的优势。通过实验表明,该算法可用于东巴文档图像、脱机手写汉字、东巴经的文本行分割,以及文本行中东巴字和汉字的分割,具有实现简单、准确性高、适应性强的特点,从而为东巴文字库的建立奠定基础。     

A method for combining complementary techniques for document image segmentation

Image segmentation is a major task of handwritten document image processing. Many of the proposed techniques for image segmentation are complementary in the sense that each of them using a different approach can solve different difficult problems such as overlapping, touching components, influence of author or font style etc. In this paper, a combination method of different segmentation techniques is presented. Our goal is to exploit the segmentation results of complementary techniques and specific features of the initial image so as to generate improved segmentation results. Experimental results on line segmentation methods for handwritten documents demonstrate the effectiveness of the proposed combination method.     

傅立叶变换在粘连文字图像切分中的应用

对于已具有相当识别率的手写体文字识别系统来说切分算法已成为一个关键技术之一,它的正确率对系统性能有着极大影响。该文主要对文字图像的傅立叶变换的性质进行了讨论,提出了消除交换中笔画宽度影响的算法。在此基础上建立了基于傅立叶变换的单／多字图像的判定的基本准则以及基于此准则的粘连文字判别算法。实验表明该算法的粘连文字判断正确率达到９６％。为粘连文字的正确切分开辟了新的途径。     

A Bayesian-based method of unconstrained handwritten offline Chinese text line recognition

This paper presents a new Bayesian-based method of unconstrained handwritten offline Chinese text line recognition. In this method, a sample of a real character or non-character in realistic handwritten text lines is jointly recognized by a traditional isolated character recognizer and a character verifier, which requires just a moderate number of handwritten text lines for training. To improve its ability to distinguish between real characters and non-characters, the isolated character recognizer is negatively trained using a linear discriminant analysis (LDA)-based strategy, which employs the outputs of a traditional MQDF classifier and the LDA transform to re-compute the posterior probability of isolated character recognition. In tests with 383 text lines in HIT-MW database, the proposed method achieved the character-level recognition rates of 71.37% without any language model, and 80.15% with a bi-gram language model, respectively. These promising results have shown the effectiveness of the proposed method for unconstrained handwritten offline Chinese text line recognition.     

基于多尺度的蒙古文脱机手写识别方法

蒙古文的一大特点是字符无缝连接,因此一个蒙古文单词有多种字符划分方式。根据蒙古文这一特点,该文提出了多尺度蒙古文脱机手写识别方法,即让一个手写蒙古文单词图像对应多种目标序列,用多个目标序列同时约束训练模型,使得模型更加精准地学习手写图像的细节信息和蒙古文构词规则。该文提出了“十二字头”码、变形显现码和字素码3种字符划分方法,且拥有相互包含关系,即“十二字头”码可以分解为变形显现码、变形显现码可以进一步分解为字素码。多尺度模型首先用多层双向长短时记忆网络对序列化手写图像进行处理,之后加入第一层连接时序分类器做“十二字头”码序列的映射,然后是第二层连接时序分类器做变形显现码序列的映射,最后是第三层连接时序分类器做字素码序列的映射。用三个连接时序分类器损失函数的和作为模型的总损失函数。实验结果表明,该模型在公开的蒙古文脱机手写数据集MHW上表现出了最佳性能,在简单的最佳路径解码方式下,测试集Ⅰ上的单词识别准确率为66.22%、测试集Ⅱ上为63.97%。     

基于改进inception的脱机手写汉字识别

由于字形的复杂多变,脱机手写汉字的识别一直是模式识别的难题,深度卷积神经网络的发展为其提供了一种直接有效的解决方案。研究基于inceptions 结构神经网络的脱机手写汉字识别,提出了一种inception结构的改进方法,它具有结构更加简单、网络深度扩展更加容易、需要的训练参数量更少的优点。该方法在数据集CISIA-HWDB1.1 上进行了实验验证,采用随机梯度下降优化算法,模型达到了96.95%的平均准确率。实验结果表明,使用改进的inception结构在图像分类上具有更好的鲁棒性,更容易扩展到其他应用领域。     

特征离散点计算在手写文本行分割中的应用

将图像分析实践中的经验知识与粒计算的基本思想相结合,总结形成了特征离散点计算,并将其应用于自然手写汉字文本行分割当中。在特征离散点计算的结构化问题求解框架下,提出了一种反馈式分列行投影文本行分割方法,分为特征离散点选择、特征离散点采样与优化、特征离散点编组与反馈以及行边缘优化四个环节。该方法在哈尔滨工业大学多人手写数据库上取得了相对以往算法较好的实验结果,同时分割速度较快。     

A new scheme for unconstrained handwritten text-line segmentation

Variations in inter-line gaps and skewed or curled text-lines are some of the challenging issues in segmentation of handwritten text-lines. Moreover, overlapping and touching text-lines that frequently appear in unconstrained handwritten text documents significantly increase segmentation complexities. In this paper, we propose a novel approach for unconstrained handwritten text-line segmentation. A new painting technique is employed to smear the foreground portion of the document image. The painting technique enhances the separability between the foreground and background portions enabling easy detection of text-lines. A dilation operation is employed on the foreground portion of the painted image to obtain a single component for each text-line. Thinning of the background portion of the dilated image and subsequently some trimming operations are performed to obtain a number of separating lines, called candidate line separators. By using the starting and ending points of the candidate line separators and analyzing the distances among them, related candidate line separators are connected to obtain segmented text-lines. Furthermore, the problems of overlapping and touching components are addressed using some novel techniques. We tested the proposed scheme on text-pages of English, French, German, Greek, Persian, Oriya and Bangla and remarkable results were obtained.     

多知识综合判决的字符切分算法

高性能的印刷体文字识别系统中,在单字识别技术比较成熟的条件下,字符切分成为比较关键的环节。字符切分可以看作是对字符边界正确切分位置的一个决策过程,该决策需要同时考虑字符局部的识别情况和全局的上下文关系。该文通过对中日韩三国文字字符切分的研究,提出一种基于多知识综合判决的字符切分算法。该算法成功应用于AsiaOCR项目,对于东方文字中常见的混排英文问题也能很好处理。实验结果表明,和以前的算法相比,新算法在中日韩三国文字识别系统中的切分错误率平均下降50%。