Document Analysis System Research Articles

Document binarization with automatic parameter tuning

Document analysis systems often begin with binarization as a first processing stage. Although numerous techniques for binarization have been proposed, the results produced can vary in quality and often prove sensitive to the settings of one or more control parameters. This paper examines a promising approach to binarization based upon simple principles, and shows that its success depends most significantly upon the values of two key parameters. It further describes an automatic technique for setting these parameters in a manner that tunes them to the individual image, yielding a final binarization algorithm that can cut total error by one-third with respect to the baseline version. The results of this method advance the state of the art on recent benchmarks.

Canadian exceptionalism: shareholder proposals, filer identities, and voting outcomes

PurposeThe purpose of this paper is to study filer identities and voting outcomes of Canadian shareholder proposals and their impact on shareholders' wealth during the period from 2001 to 2008.Design/methodology/approachIn total, 762 Canadian shareholder proposals and related information on targeted firms were collected from the Shareholder Association for Research and Education (SHARE) and the System for Electronic Document Analysis and Retrieval (SEDAR) databases. Statistical analyses are carried out on the features of shareholder proposals. Regression analyses are performed on voting outcomes, and an event study is conducted to test the impact of shareholder proposals on stock prices.FindingsThe authors' analyses show that proposals submitted by institutions or coordinated shareholder groups receive stronger support than those submitted by individuals and religious groups. Targeted firms are more willing and more likely to reach agreements with institutional investors, which in turn prompts activists to withdraw their proposals. The voting behavior of the Ontario Teachers' Pension Plan (OTPP) has a significant impact on voting outcomes. The targeted firms' stock prices respond substantially to news on proposals submitted by institutional and coordinated investors and proposals on social and environmental issues.Originality/valueIn addition to in‐depth analyses (issues, filers, voting outcomes, and impacts on stock price) of Canadian shareholder proposals, this paper explores the voting behaviour and impact of a large institutional shareholder that has been passive in filing shareholder proposals. Special attention is paid to Canadian features of shareholder activism, and differences between Canadian and US shareholder proposals are highlighted and discussed. The paper thus extends shareholder activism studies from focusing on open shareholder activists to investigating passive institutional shareholders.

Inter-Corporate Ownership, Taxes, and Corporate Payout Choices Between Dividends and Share Repurchases

This paper examines whether corporate payout policies are associated with inter-corporate ownership. Using the System for Electronic Document Analysis and Retrieval (SEDAR) and the Inter-Corporate Ownership (ICO) from Statistics Canada databases, we find that inter-corporate ownership is positively associated with a firm’s propensity to pay dividends and is negatively associated with a firm’s propensity to repurchase shares. Our findings are robust to the endogeneity of inter-corporate ownership and the inclusion of various control variables, such as firm size, liquidity, growth, and profitability. Overall, our results suggest that corporate shareholders’ tax positions affect firms’ payout decisions.

Skew detection in document images based on rectangular active contour

The digitalization processes of documents produce frequently images with small rotation angles. The skew angles in document images degrade the performance of optical character recognition (OCR) tools. Therefore, skew detection of document images plays an important role in automatic document analysis systems. In this paper, we propose a Rectangular Active Contour Model (RAC Model) for content region detection and skew angle calculation by imposing a rectangular shape constraint on the zero-level set in Chan–Vese Model (C-V Model) according to the rectangular feature of content regions in document images. Our algorithm differs from other skew detection methods in that it does not rely on local image features. Instead, it uses global image features and shape constraint to obtain a strong robustness in detecting skew angles of document images. We experimented on different types of document images. Comparing the results with other skew detection algorithms, our algorithm is more accurate in detecting the skews of the complex document images with different fonts, tables, illustrations, and layouts. We do not need to pre-process the original image, even if it is noisy, and at the same time the rectangular content region of a document image is also detected.

Efficiently extracting and classifying objects for analyzing color documents

Conventional objects extraction method are not efficient for color document image with large graphics. For example, the projection profile and connected component based methods scanning the large graphics many times. To display the large graphics are extracted, conventional methods use rectangle to represent it. Thus, scanning into the large graphics is time-consuming. In this paper, a novel system for efficiently analyzing color documents is proposed to solve above mentioned problem. The proposed system includes color transformation, background color determination, objects extraction by top-down method, and objects classification without parameters. The proposed color document analysis system is efficient because it scans only background pixels such that the temporal complexity is O (NB), where NB is the total number of background color pixels. Results of this study demonstrate that this system is more effective and efficient than other methods. Moreover, the proposed algorithm can be run in an embedded environment (such as a mobile device) and processed in real-time system due to its simplicity and efficiency.

Document cleanup using page frame detection

When a page of a book is scanned or photocopied, textual noise (extraneous symbols from the neighboring page) and/or non-textual noise (black borders, speckles, ...) appear along the border of the document. Existing document analysis methods can handle non-textual noise reasonably well, whereas textual noise still presents a major issue for document analysis systems. Textual noise may result in undesired text in optical character recognition (OCR) output that needs to be removed afterwards. Existing document cleanup methods try to explicitly detect and remove marginal noise. This paper presents a new perspective for document image cleanup by detecting the page frame of the document. The goal of page frame detection is to find the actual page contents area, ignoring marginal noise along the page border. We use a geometric matching algorithm to find the optimal page frame of structured documents (journal articles, books, magazines) by exploiting their text alignment property. We evaluate the algorithm on the UW-III database. The results show that the error rates are below 4% each of the performance measures used. Further tests were run on a dataset of magazine pages and on a set of camera captured document images. To demonstrate the benefits of using page frame detection in practical applications, we choose OCR and layout-based document image retrieval as sample applications. Experiments using a commercial OCR system show that by removing characters outside the computed page frame, the OCR error rate is reduced from 4.3 to 1.7% on the UW-III dataset. The use of page frame detection in layout-based document image retrieval application decreases the retrieval error rates by 30%.

A novel boundary growing approach for accurate skew estimation of binary document images

Skew angle estimation is an important component of optical character recognition (OCR) systems and document analysis systems (DAS). In this paper, a novel and an efficient method to estimate the skew angle of a scanned document image is proposed. The proposed method has two stages. In first stage, using boundary-growing approach, text lines containing characters of the scanned document image are extracted. From each text line, coordinates of the positions of the characters are obtained. In second stage, the obtained coordinates are fed to linear regression analysis (LRA) for the purpose of computation of skew angle. Several experiments have been conducted on various types of documents such as documents containing different language texts, documents with different fonts and documents with noise to reveal the robustness of the proposed method. A comparative study with the well-known methods is presented to show that the proposed method is superior in terms of accuracy and computational efficiency.

A novel technique for estimation of skew in binary text document images based on linear regression analysis

When a document is scanned either mechanically or manually for digitization, it often suffers from some degree of skew or tilt. Skew-angle detection plays an important role in the field of document analysis systems and OCR in achieving the expected accuracy. In this paper, we consider skew estimation of Roman script. The method uses the boundary growing approach to extract the lowermost and uppermost coordinates of pixels of characters of text lines present in the document, which can be subjected to linear regression analysis (LRA) to determine the skew angle of a skewed document. Further, the proposed technique works fine for scaled text binary documents also. The technique works based on the assumption that the space between the text lines is greater than the space between the words and characters. Finally, in order to evaluate the performance of the proposed methodology we compare the experimental results with those of well-known existing methods.

Reports of the DAS02 working groups

This document is a collection of four working group reports in the areas of digital libraries, document image retrieval, layout analysis, and Web document analysis. These reports were the outcome of discussions by participants at the Fifth IAPR International Workshop on Document Analysis Systems held in Princeton, NJ on 19-21 August 2002.

Realisation of high-performance bilingual English/Arabic articulated document analysis and understanding system

Document analysis and understanding (DAU) systems aim not only at the recognition of text but also at the extraction of relevant information out of a scanned document. Numerous studies have introduced efficient algorithms for document analysis, some of these studies proposed an articulated and/or a translation stage. Also, little work has been done in the English/Arabic (E/A) translation area. The main objective of this paper is to introduce a combination between the three trends (document understanding, E/A translation, and handling the output in an articulated voice). This paper focuses on the realisation of a bilingual articulated E/A system based on optical character recognition (OCR). The input of the proposed system will be an English or Arabic text through scanner or video camera; the output will be an articulated voice. The proposed scheme consists of two phases. The first phase consists of many processes, beginning with converting scanned document into an electronically processable form. Then, in the segmentation step, the essential problem in Arabic OCR, that is, how to cope with the various shapes of the same character, is solved. A new methodology for segmenting Arabic characters is presented. At the end of this phase, an efficient method of text recognition based on hybrid description (ANN, FFT) is used. In order to verify the performance of this phase, experiments with printed text were performed. The error rates were less than 0.1%. Results showed that the proposed scheme in this phase is very robust. In the second phase, a database with 3000 audio files was encapsulated to convert each word from the input text (the output of the first phase) to its correspondence. This research can help in many real-time applications such as immediate translation, a machine reader for blind people, and learning.

Document understanding for a broad class of documents

We present a document analysis system able to assign logical labels and extract the 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, which is identified explicitly. The proposed system integrates components based on computer vision, artificial intelligence, and natural language processing techniques. The system is fully implemented and experimental results on heterogeneous collections of documents for each component and for the entire system are presented.

Document image analysis: A primer

Document image analysis refers to algorithms and techniques that are applied to images of documents to obtain a computer-readable description from pixel data. A well-known document image analysis product is the Optical Character Recognition (OCR) software that recognizes characters in a scanned document. OCR makes it possible for the user to edit or search the document’s contents. In this paper we briefly describe various components of a document analysis system. Many of these basic building blocks are found in most document analysis systems, irrespective of the particular domain or language to which they are applied. We hope that this paper will help the reader by providing the background necessary to understand the detailed descriptions of specific techniques presented in other papers in this issue.

Extracting curved text lines using local linearity of the text line

In order to enhance the ability of document analysis systems, we need a text line extraction method which can handle not only straight text lines but also text lines in various shapes. This paper proposes a new method called Extended Linear Segment Linking (ELSL for short), which is able to extract text lines in arbitrary orientations and curved text lines. We also consider the existence of both horizontally and vertically printed text lines on the same page. The new method can produce text line candidates for multiple orientations. We verify the ability of the method by some experiments as well.

An improved document skew angle estimation technique

When a document is fed to a scanner either mechanically or by a human operator for digitization, it suffers from some degrees of skew or tilt. Skew angle detection is an important component of any Optical Character Recognition (OCR) and document analysis system. In this letter we consider skew estimation of Roman script. The method considers the lowermost and uppermost pixels of some selected characters of the text which may be subject to Hough transform for skew angle detection. A fast approach is also proposed which works almost as accurately as Hough transform. Experimental results are presented and compared with results on several other skew detection methods.

Performance evaluation for document analysis

A framework for evaluating the performance of a document analysis system is presented. This framework takes into account the task definition for the document analysis system, a data base on which that system is evaluated, the metrics used to evaluate performance, and the generalization of the results achieved beyond the confines of the test. Several recent significant efforts in evaluating document analysis systems are surveyed. How these efforts fit the general framework is discussed. The specific task that was evaluated, the data base used for the evaluation, and the generalization of the derived performance is presented. Most of these projects were designed for limited applications in which the translation of images of text into ASCII was the primary consideration. However, this is only part of what a document analysis system must often calculate. Other, less easily measured tasks, such as the subdivision of a document image into zones that represent regions of graphics, photographs, and text, must also be performed. Generally accepted solutions for measuring the performance of such tasks often do not exist. Several of them are mentioned as areas for future research. © 1996 John Wiley & Sons, Inc.

Page segmentation and identification for intelligent signal processing

Document analysis plays an important role in office automation, especially in intelligent signal processing. In this paper, we propose an intelligent document analysis system to achieve the document segmentation and identification goal. The proposed system consists of two modules: block segmentation and block identification. In our approach, we first segment a document into several non-overlapping blocks by utilizing a novel recursive segmentation technique, then extract the features embedded in each segmented block. Two kinds of features, connectivity histogram and multiresolution features, are extracted. The features are verified to be effective in characterizing document blocks. Last, a two-layer perceptron is adopted in the identification module to determine the identity of the considered block. Experiments with a wide varity of documents verify the feasibility of our approach.

Segmentation and classification of mixed text/graphics/image documents

In this paper, a feature-based document analysis system is presented which utilizes domain knowledge to segment and classify mixed text/graphics/image documents. In our approach, we first perform a run-length smearing operation followed by the stripe merging procedure to segment the blocks embedded in a document. The classification task is then performed based on the domain knowledge induced from the primitives associated with each type of medium. Proper use of domain knowledge is proved to be effective in accelerating the segmentation speed and decreasing the classification error. The experimental study reveals the feasibility of the new technique in segmenting and classifying mixed text/graphics/image documents.

A hierarchical method for block segmentation and classification of general document images

AbstractIn a document analysis system, block segmentation and block classification are very important. The former segments a particular document image into homogeneous rectangular blocks. The latter classifies the segmented blocks into categories. These classified blocks may then be processed by suitable recognition systems. In this paper, we formalize the structure styles of general documents, and then propose both a robust hierarchical method of block segmentation and a simple method of block classification. The proposed block segmentation method takes a top‐down hierarchical approach based on the spatial features and formalized concepts of document structure. This method is essentially independent of the document style, and can perform a type of structural analysis of the document image. The classification approach is based on a new scheme of statistical textual features, and classifies the segmented blocks into four categories: text blocks, title letter blocks, line drawing (or graphics) blocks, and halftone phonograph blocks. The proposed approaches were implemented using the C programming language in an X‐Window environment under the UNIX operating system. The performance of each approach was experimentally evaluated, for both effectiveness and computational efficiency, using actual test images.

DRS: a workstation-based document recognition system for text entry

Document recognition system (DRS), a workstation-based prototype document analysis system that uses optical character recognition (OCR), is described. The system provides functions for image capture, block segmentation, page structure analysis, and character recognition with contextual postprocessing, as well as a user interface for error correction. All the functions except image capture and character recognition have been implemented by means of software for the Japanese edition of OS/2. >

From paper to office document standard representation

The principles of the model-based document analysis system called Pi ODA (paper interface to office document architecture), which was developed as a prototype for the analysis of single-sided business letters in German, are presented. Initially, Pi ODA extracts a part-of hierarchy of nested layout objects such as text-blocks, lines, and words based on their presentation on the page. Subsequently, in a step called logical labeling, the layout objects and their compositions are geometrically analyzed to identify corresponding logical objects that can be related to a human perceptible meaning, such as sender, recipient, and date in a letter. A context-sensitive text recognition for logical objects is then applied using logical vocabularies and syntactic knowledge. As a result, Pi ODA produces a document representation that conforms to the ODA international standard. >