We present a document analysis system able to assign logical labels and extract reading order in a broad set of documents. All information sources, from geometric features and spatial relations to the textual features and content are employed in the analysis. To deal effectively with these information sources, we define a document representation general and flexible enough to represent complex documents. To handle such a broad document class, it uses generic document knowledge only. The generic document knowledge used is identified explicitly. Our system integrates components based on computer vision, artificial intelligence, and natural language processing techniques. Experimental results for each component and for the entire system are presented. The performance of the system is good, especially when considering the

Document structure analysis can be regarded as a syntactic analysis problem. The order and containment relations among the physical or logical components of a document page can be described by an ordered tree structure and can be modeled by a tree grammar which describes the page at the component level in terms of regions or blocks. This paper provides a detailed survey of past work on document structure analysis algorithms and summarize the limitations of past approaches. In particular, we survey past work on document physical layout representations and algorithms, document logical structure representations and algorithms, and performance evaluation of document structure analysis algorithms. In the last section, we summarize this work and point out its limitations.

Abstract—We introduce a novel rich local descriptor of an image point, we call the (labeled) distance set, which is determined by the spatial arrangement of image features around that point. We describe a two-dimensional (2-D) visual object by the set of (labeled) distance sets associated with the feature points of that object. Based on a dissimilarity measure between (labeled) distance sets and a dissimilarity measure between sets of (labeled) distance sets, we address two problems that are often encountered in object recognition: object segmentation, for which we formulate a distance sets shape filter, and shape matching. The use of the shape filter is illustrated on printed and handwritten character recognition and detection of traffic signs in complex scenes. The shape comparison procedure is illustrated on handwritten character classification, COIL-20 database object recognition and MPEG-7 silhouette database retrieval. Index Terms—Character recognition, distance set, image database retrieval, MPEG-7, object recognition, segmentation, shape descriptor, shape filter, traffic sign recognition. I.

Table characteristics vary widely. Consequently, a great variety of computational approaches have been applied to table recognition. In this survey, the table recognition literature is presented as an interaction of table models, observations, transformations and inferences. A table model defines the physical and logical structure of tables; the model is used to detect tables, and to analyze and decompose the detected tables. Observations perform feature measurements and data lookup, transformations alter or restructure data, and inferences generate and test hypotheses. This presentation clarifies the decisions that are made by a table recognizer, and the assumptions and inferencing techniques that underlie these decisions.

PDF became a very common format for exchanging printable documents. Further, it can be easily generated from the major documents formats, which make a huge number of PDF documents available over the net. However its use is limited to displaying and printing, which considerably reduces the search and retrieval capabilities. For this reason, additional tools have recently appeared that allow to extract the textual content. However their practical use is limited in the sense that the text’s reading order is not necessary preserved, especially when handling multi-column documents, or in presence of complex layout. Our thesis is that those tools do not consider the hidden layout and logical structures of documents, which could greatly improve their results. We propose a novel approach to overcome the document content extraction, by merging a) low-level extraction methods applied on PDF files with b) layout analysis performed on a synthetically generated TIFF image. The paper describes the various steps necessary to achieve this task. Finally, we present a first experiment on the restitution of the newspapers ’ reading order which shows encouraging results. 1.

Abstract—This paper addresses a problem of restoring handwritten archival documents by recovering their contents from the interfering handwriting on the reverse side caused by the seeping of ink. We present a novel method that works by first matching both sides of a document such that the interfering strokes are mapped with the corresponding strokes originating from the reverse side. This facilitates the identification of the foreground and interfering strokes. A wavelet reconstruction process then iteratively enhances the foreground strokes and smears the interfering strokes so as to strengthen the discriminating capability of an improved Canny edge detector against the interfering strokes. The method has been shown to restore the documents effectively with average precision and recall rates for foreground text extraction at 84 percent and 96 percent, respectively. Index Terms—Document image analysis, wavelet enhancement, wavelet smearing, Canny edge detector, text extraction, image segmentation, bleedthrough, show-through, noise cancellation, denoising. 1

Searching and indexing historical handwritten collections is a very challenging problem. We describe an approach called word spotting which involves grouping word images into clusters of similar words by using image matching to find similarity. By annotating “interesting ” clusters, an index that links words to the locations where they occur can be built automatically. Image similarities computed using a number of different techniques including dynamic time warping are compared. The word similarities are then used for clustering

In this paper we propose a method for network intrusion detection based on language models. Our method proceeds by extracting language features such as n-grams and words from connection payloads and applying unsupervised anomaly detection – without prior learning phase or presence of labeled data. The essential part of this procedure is linear-time computation of similarity measures between language models of connection payloads. Particular patterns in these models decisive for differentiation of attacks and normal data can be traced back to attack semantics and utilized for automatic generation of attack signatures. Results of experiments conducted on two datasets of network traffic demonstrate the importance of higher-order n-grams and variable-length language models for detection of unknown network attacks. An implementation of our system achieved detection accuracy of over 80 % with no false positives on instances of recent remote-to-local attacks in HTTP, FTP and SMTP traffic.

This paper discusses the design of intelligent sketch editing tools exploiting intermediate levels of visual interpretation known as Perceptual Organization.

Artificial neural networks have been extensively applied to document analysis and recogni-tion. Most efforts have been devoted to the recognition of isolated handwritten and printed characters with widely recognized successful results. However, many other document pro-cessing tasks like pre-processing, layout analysis, character segmentation, word recognition, and signature verification have been effectively faced with very promising results. This paper surveys most significant problems in the area of off-line document image processing where connectionist-based approaches have been applied. Similarities and differences between ap-proaches belonging to different categories are discussed. A particular emphasis is given on the crucial role of the prior knowledge for the conception of both appropriate architectures and learning algorithms. Finally, the paper provides a critical analysis on the reviewed approaches and depicts most promising research guidelines in the field. In particular, a sec-ond generation of connectionist-based models are foreseen which are based on appropriate graphical representations of the learning environment.