Detection and analysis of table of contents based on content association

As a special type of table understanding, the detection and analysis of tables of contents (TOCs) play an important role in the digitization of multi-page documents. Most previous TOC analysis methods only concentrate on the TOC itself without taking into account the other pages in the same document. Besides, they often require manual coding or at least machine learning of document-specific models. This paper introduces a new method to detect and analyze TOCs based on content association. It fully leverages the text information throughout the whole multi-page document and can be directly applied to a wide range of documents without the need to build or learn the models for individual documents. In addition, the associations of general text and page numbers are combined to make the TOC analysis more accurate. Natural language processing and layout analysis are integrated to improve the TOC functional tagging. The applications of the proposed method in a large-scale digital library project are also discussed.     

Error tolerant document structure analysis

Successful applications of digital libraries require structured access to sources of information. This paper presents an approach to extract the logical structure of text documents. The extracted structure is explicated by means of SGML (Standard Generalized Markup Language). Consequently, the extraction is achieved on the basis of grammars that extend SGML with recognition rules. From these grammars parsing automata are generated. These automata are used to partition a flat text document into its elements, to discard formatting information, and to insert SGML markups. Complex document structures and fallback rules needed for error tolerant parsing make such automata highly ambiguous. A novel parsing strategy has been developed that ranks and prunes ambiguous parsing paths.     

Exploratory analysis of concept and document spaces with connectionist networks

Exploratory analysis is an area of increasing interest in the computational linguistics arena. Pragmatically speaking, exploratory analysis may be paraphrased as natural language processing by means of analyzing large corpora of text. Concerning the analysis, appropriate means are statistics, on the one hand, and artificial neural networks, on the other hand. As a challenging application area for exploratory analysis of text corpora we may certainly identify text databases, be it information retrieval or information filtering systems. With this paper we present recent findings of exploratory analysis based on both statistical and neural models applied to legal text corpora. Concerning the artificial neural networks, we rely on a model adhering to the unsupervised learning paradigm. This choice appears naturally when taking into account the specific properties of large text corpora where one is faced with the fact that input-output-mappings as required by supervised learning models cannot be provided beforehand to a satisfying extent. This is due to the fact of the highly changing contents of text archives. In a nutshell, artificial neural networks count for their highly robust behavior regarding the parameters for model optimization. In particular, we found statistical classification techniques much more susceptible to minor parameter variations than unsupervised artificial neural networks. In this paper we describe two different lines of research in exploratory analysis. First, we use the classification methods for concept analysis. The general goal is to uncover different meanings of one and the same natural language concept. A task that, obviously, is of specific importance during the creation of thesauri. As a convenient environment to present the results we selected the legal term of neutrality, which is a perfect representative of a concept having a number of highly divergent meanings. Second, we describe the classification methods in the setting of document classification. The ultimate goal in such an application is to uncover semantic similarities of various text documents in order to increase the efficiency of an information retrieval system. In this sense, document classification has its fixed position in information retrieval research from the very beginning. Nowadays renewed massive interest in document classification may be witnessed due to the appearance of large-scale digital libraries.     

Hybrid neural document clustering using guided self-organization and WordNet

Document clustering is text processing that groups documents with similar concepts. It's usually considered an unsupervised learning approach because there's no teacher to guide the training process, and topical information is often assumed to be unavailable. A guided approach to document clustering that integrates linguistic top-down knowledge from WordNet into text vector representations based on the extended significance vector weighting technique improves both classification accuracy and average quantization error. In our guided self-organization approach we integrate topical and semantic information from WordNet. Because a document-training set with preclassified information implies relationships between a word and its preference class, we propose a novel document vector representation approach to extract these relationships for document clustering. Furthermore, merging statistical methods, competitive neural models, and semantic relationships from symbolic Word-Net, our hybrid learning approach is robust and scales up to a real-world task of clustering 100,000 news documents.     

Table form document analysis based on the document structure grammar

Structure analysis of table form documents is an important issue because a printed document and even an electronic document do not provide logical structural information but merely geometrical layout and lexical information. To handle these documents automatically, logical structure information is necessary. In this paper, we first analyze the elements of the form documents from a communication point of view and retrieve the grammatical elements that appear in them. Then, we present a document structure grammar which governs the logical structure of the form documents. Finally, we propose a structure analysis system of the table form documents based on the grammar. By using grammar notation, we can easily modify and keep it consistent, as the rules are relatively simple. Another advantage of using grammar notation is that it can be used for generating documents only from logical structure. In our system, documents are assumed to be composed of a set of boxes and they are classified as seven box types. Then the box relations between the indication box and its associated entry box are analyzed based on the semantic and geometric knowledge defined in the document structure grammar. Experimental results have shown that the system successfully analyzed several kinds of table forms.     

基于PDF文档结构的数字水印算法

在数字产品日益普及的今天,PDF文档的版权保护问题已成为信息安全领域研究的热点。通过分析PDF文档的结构及相关数字水印算法,针对当前一些大容量文本水印算法存在增加文档大小的缺陷,提出了一种基于PDF文档结构的数字水印算法。该算法利用行末标识符不会在文档中显示的特性,通过等量替换PDF文档中具有固定格式的交叉引用表的行末标识符,来实现水印信息的间接嵌入。实验结果表明,该算法水印容量能满足数字版权保护的要求,隐蔽性好,能抵抗统计等攻击。     

Machine printed text and handwriting identification in noisy document images

In this paper, we address the problem of the identification of text in noisy document images. We are especially focused on segmenting and identifying between handwriting and machine printed text because: 1) Handwriting in a document often indicates corrections, additions, or other supplemental information that should be treated differently from the main content and 2) the segmentation and recognition techniques requested for machine printed and handwritten text are significantly different. A novel aspect of our approach is that we treat noise as a separate class and model noise based on selected features. Trained Fisher classifiers are used to identify machine printed text and handwriting from noise and we further exploit context to refine the classification. A Markov Random Field-based (MRF) approach is used to model the geometrical structure of the printed text, handwriting, and noise to rectify misclassifications. Experimental results show that our approach is robust and can significantly improve page segmentation in noisy document collections.     

基于空白条方向拟合的复杂文本图像倾斜检测

针对扫描背景不定且含有图表信息的复杂文本图像,提出了一种有效的倾斜检测方法。该方法首先通过对梯度图像的统计分析,自适应地选取到了包含文字的特征子区;在特征子区内,论文把文字行间的空白条带看作一条隐含的线,用优化理论计算出空白条带的倾斜角度,这也就是文本的倾斜角度。实验结果表明,该倾斜检测方法不受扫描背景、边界大小、文本布局及行间距等情况的限制,具有速度快、精度高、适应性强的特点。     

Automatic generation of structured hyperdocuments from document images

As sharing documents through the World Wide Web has been recently and constantly increasing, the need for creating hyperdocuments to make them accessible and retrievable via the internet, in formats such as HTML and SGML/XML, has also been rapidly rising. Nevertheless, only a few works have been done on the conversion of paper documents into hyperdocuments. Moreover, most of these studies have concentrated on the direct conversion of single-column document images that include only text and image objects. In this paper, we propose two methods for converting complex multi-column document images into HTML documents, and a method for generating a structured table of contents page based on the logical structure analysis of the document image. Experiments with various kinds of multi-column document images show that, by using the proposed methods, their corresponding HTML documents can be generated in the same visual layout as that of the document images, and their structured table of contents page can be also produced with the hierarchically ordered section titles hyperlinked to the contents.     

一种概念空间自生成方法

文章提出一种自动生成概念空间的方法。首先通过SOM神经网络,对文本进行聚类,之后从结果中提取反映各类文本内容的概念,用于标注文本的类别,再通过模糊聚类进行概念自动抽象与归纳形成概念空间,用于文本的管理。SOM本身是无监督的学习方式,在设定好参数后,经过训练自动生成文本空间与概念空间的映射图。相关试验和结果表明概念空间对文本有很好的分类管理功能,便于文本检索。     

Knowledge-guided unsupervised rhetorical parsing for text summarization

Automatic text summarization (ATS) has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale corpora. However, there is still no guarantee that the generated summaries are grammatical, concise, and convey all salient information as the original documents have. To make the summarization results more faithful, this paper presents an unsupervised approach that combines rhetorical structure theory, deep neural model, and domain knowledge concern for ATS. This architecture mainly contains three components: domain knowledge base construction based on representation learning, the attentional encoder–decoder model for rhetorical parsing, and subroutine-based model for text summarization. Domain knowledge can be effectively used for unsupervised rhetorical parsing thus rhetorical structure trees for each document can be derived. In the unsupervised rhetorical parsing module, the idea of translation was adopted to alleviate the problem of data scarcity. The subroutine-based summarization model purely depends on the derived rhetorical structure trees and can generate content-balanced results. To evaluate the summary results without golden standard, we proposed an unsupervised evaluation metric, whose hyper-parameters were tuned by supervised learning. Experimental results show that, on a large-scale Chinese dataset, our proposed approach can obtain comparable performances compared with existing methods.     

基于二次余数的Word文档数字水印

目前电子文档的使用越来越广泛,尤其是Word文档.由此提出了一种基于二次余数的Word文档数字水印算法.由于中文文本自身的特点,使字移编码不太适合于中文文本水印.该算法依据二次余数理论来自适应的嵌入水印信息,在中文文本中实现了字移编码,并且有较大的信息隐藏容量;提取水印时不需要对比原始文本,实现了盲提取;结合非线性动力学系统的Logistic映射产生的混沌序列,对原始水印图像进行了改进的魔方变换,置乱效果更好,从而进一步提高了鲁棒性.实验表明,该算法具有良好的不可见性;Word文档常见的格式调整等并不会破坏水印.     

一种快速的文本倾斜检测方法

文本的倾斜检测是将文本转换成数字形式的过程中的第一步工作,也是很重要的一步工作。因为后续的很多工作都是基于摆正的文本。文章提出了一种全新的倾斜检测与纠正方法。其特点在于:一、与文本的纹理无关,从而适应各种图文混排及各种书写方向并存等复杂情形;二、运算量小,只需进行一次旋转和四次对图像的部分投影。     

基于汉字结构知识的鲁棒性公开文本水印

针对中文文本存在的版权保护问题,文章提出了一种新的文本水印算法。该方法通过汉字数学表达式,获取汉字的结构类型和笔画数,利用汉字的结构类型将整个文档分成两块,在各块中由汉字笔画数和水印比特位共同确定水印加载的位置,通过设置字体下划线以嵌入水印。水印提取时不需要原始文档和原始水印,通过块校验和海明校验可将破坏的水印比特位进行恢复。实验结果表明该算法具有较好的透明性和鲁棒性。     

String alignment for automated document versioning

The automated analysis of documents is an important task given the rapid increase in availability of digital texts. Automatic text processing systems often encode documents as vectors of term occurrence frequencies, a representation which facilitates the classification and clustering of documents. Historically, this approach derives from the related field of data mining, where database entries are commonly represented as points in a vector space. While this lineage has certainly contributed to the development of text processing, there are situations where document collections do not conform to this clustered structure, and where the vector representation may be unsuitable for text analysis. As a proof-of-concept, we had previously presented a framework where the optimal alignments of documents could be used for visualising the relationships within small sets of documents. In this paper we develop this approach further by using it to automatically generate the version histories of various document collections. For comparison, version histories generated using conventional methods of document representation are also produced. To facilitate this comparison, a simple procedure for evaluating the accuracy of the version histories thus generated is proposed.     

基于层次混合注意力机制的文本分类模型

文本分类是自然语言处理领域的核心任务之一,深度学习的发展给文本分类带来更广阔的发展前景.针对当前基于深度学习的文本分类方法在长文本分类中的优势和不足,该文提出一种文本分类模型,在层次模型基础上引入混合注意力机制来关注文本中的重要部分.首先,按照文档的层次结构分别对句子和文档进行编码;其次,在每个层级分别使用注意力机制....     

A video-based framework for the analysis of presentations/posters

Detection and recognition of textual information in an image or video sequence is important for many applications. The increased resolution and capabilities of digital cameras and faster mobile processing allow for the development of interesting systems. We present an application based on the capture of information presented at a slide-show presentation or at a poster session. We describe the development of a system to process the textual and graphical information in such presentations. The application integrates video and image processing, document layout understanding, optical character recognition (OCR), and pattern recognition. The digital imaging device captures slides/poster images, and the computing module preprocesses and annotates the content. Various problems related to metric rectification, key-frame extraction, text detection, enhancement, and system integration are addressed. The results are promising for applications such as a mobile text reader for the visually impaired. By using powerful text-processing algorithms, we can extend this framework to other applications, e.g., document and conference archiving, camera-based semantics extraction, and ontology creation.Received: 18 December 2003, Revised: 1 November 2004, Published online: 2 February 2005     

Text Mining in the SOMLib Digital Library System: The Representation of Topics and Genres

With the increasing amount of textual information available in electronic form, more powerful methods for exploring, searching, and organizing the available mass of information are needed to cope with this situation. This paper presents the SOMLIb digital library system, built on neural networks to provide text mining capabilities. At its foundation we use the Self-Organizing Map to provide content-based clustering of documents. By using an extended model, i.e. the Growing Hierarchical Self-Organizing Map, we can further detect subject hierarchies in a document collection, with the neural network adapting its size and structure automatically during its unsupervised training process to reflect the topical hierarchy. By mining the weight vector structure of the trained maps our system is able to select keywords describing the various topical clusters. Text mining has to incorporate more than the mere analysis of content. Structural and genre information are key in organizing and locating information. Using color-coding techniques we can integrate a structural analysis of documents based on Self-Organizing Maps into the subject-based clustering relying on metaphor graphics for intuitive visualization. We demonstrate the capabilities of the SOMLib system using collections of articles from various newspapers and magazines.