Traditionally, page images undergo pre-processing before the later stages of document analysis are applied. One common pre-processing step is to calculate and correct for the presence of simple page skew through a compensating rotation. Such operations modify the original input image, however, and in doing so may discard or obscure useful information. In this paper, we examine the impact of page deskewing on the task of writer identification for complicated handwritten documents. As an alternative to rotating the page image, we demonstrate a method that compensates for page skew during feature extraction. Experimental evaluation involving 61 Arabic writers and 610 page images show that handling page skew during feature extraction can benefit writer ID with a significant 1.4% gain in accuracy. In addition, we also obtain a 4.7% gain after improving an existing contour-based feature extraction method.

The Document Analysis and Exploitation platform is a sophisticated technical environment that consists of a repository containing document images, implementations of document analysis algorithms, and the results of these algorithms when applied to data in the repository. The use of a web services model makes it possible to set up document analysis pipelines that form the basis for reproducible protocols. Since the platform keeps track of all intermediate results, it becomes an information resource for the analysis of experimental data. This paper provides a tutorial on how to get started using the platform. It covers the technical details needed to overcome the initial hurdles and have a productive experience with DAE.

We propose to adapt Turing's seminal 1950 test for machine intelligence to evaluating progress in document analysis systems. Our premise is that a problem can be considered solved if automated and human solutions to the underlying task are indistinguishable to a skeptical human judge. For the domain-specific problems of concern here, we reformulate the test to keep the interaction between judges and human/machine participants to graphical user interfaces that do not require natural language processing, a notable difference from Turing's original formulation. Examples of tasks that may lend themselves to such tests include detecting or identifying specific document components such as logos, photographs, tables, as well as writer and language identification. The administration of the test would be facilitated by commercial crowd-sourcing systems such as Amazon Mechanical Turk, as well as research platforms such as the Lehigh Document Analysis Engine (DAE) that accept arbitrary documents for input, record test results, and provide for trusted execution of submitted programs.

Table detection can be a valuable step in the analysis of unstructured documents. Although much work has been conducted in the domain of machine-print including books, scientific papers, etc., little has been done to address the case of handwritten inputs. In this paper, we study table detection in scanned handwritten documents subject to challenging artifacts and noise. First, we separate text components (machine-print, handwriting) from the rest of the page using an SVM classifier. We then employ a correlation-based approach to measure the coherence between adjacent text lines which may be part of the same table, solving the resulting page decomposition problem using dynamic programming. A report of preliminary results from ongoing experiments concludes the paper.

Ruling lines are commonly used to help people write neatly on paper. In document image analysis, however, they create challenges for handwriting recognition and writer identification. In this paper, we model ruling line detection as a multi-line linear regression problem and then derive a globally optimal solution giving the Least Square Error. We demonstrate the efficacy of the technique on both synthetic and real datasets. A comparative study shows that our algorithm outperforms a previously published method on the public Germana dataset.

In this paper, we present a fully operational, scalable and open architecture allowing end-to-end document analysis benchmarking without needing to develop the whole pipeline. By decomposing the analysis process into coarse-grained tasks, and by building upon community provided state-of-the art algorithms, our architecture allows any combination of elementary document analysis algorithms, regardless their running system environment, programming language or data structures. Its flexible structure makes it straightforward to plug in new algorithms, compare them to other algorithms, and observe the effects on end-to-end tasks without need to install, compile or otherwise interact with any other software than one's own.

This contest aims to provide a metric giving indications on the influence of individual document analysis stages to overall end-to-end applications. Contestants are provided with a full, working pipeline which operates on a page image to extract useful information. The pipeline is built with clearly identified analysis stages (e.g. binarization, skew detection, layout analysis, OCR) that have a formalized input and output. Contestants are invited to contribute their own algorithms as an alternative to one or more of the initially provided stages. The evaluation measures the overall impact of the contributed algorithm on the final (end-of-pipeline) output.

Open problems are defined differently in document image analysis than in the physical sciences, theoretical computer science, or mathematics. Instead of a formal definition, problems in DIA are stated in terms of automation of an application area (e.g., postal address reading) or a scientific sub field (e.g., image compression). The notion of a successful solution may be based on (1) the relative accuracy of automated vs. expert solutions (given specific data and degree of manual tuning), (2) the distinguish ability of automated output from human output (a Turing Test), (3) the degree of current community interest (via conferences and journals), and/or (4) economic considerations. Because of the lack of formal definition for DIA problems, heuristics predominate over provably correct algorithms, and full disclosure of implementation details as well as populations and samples is essential. Results on available test sets are often only tangentially related to motivating applications. In addition, interest in automating certain tasks has been evolving rapidly as a result of advances in technology. Further community discussion of these issues may accelerate progress and symbiosis with allied disciplines.

Vote counting accuracy has become a well-known issue in the vote collection process. Digital image processing techniques can be incorporated in the analysis of printed election ballots. Current image processing techniques in the vote collection process are heavily dependent on the anticipated, geometric positioning of the vote. These techniques don't account for markings made outside of the requested field of input. Using various form dropout techniques, however, every mark on the form can be extracted and used by the machine to make an intelligent decision. Most methods will still miss a few marks and result in a few false alarms. This paper explores methods of voting between the results of the different mark extraction methods to improve recognition. To provide diversity a simple image subtraction technique is paired with a distance transform and a morphology based algorithm. The result has a higher detection rate and a lower false alarm rate.

Resources are presented for fostering paper-based election technology. They comprise a diverse collection of real and simulated ballot and survey images, and software tools for ballot synthesis, registration, segmentation, and ground truthing. The grids underlying the designated location of voter marks are extracted from 13,315 degraded ballot images. The actual skew angles of sample ballots, recorded as part of complete ballot descriptions compiled with the interactive ground-truthing tool, are compared with their automatically extracted parameters. The average error is 0.1 degrees. These results provide a baseline for the application of digital image analysis to the scrutiny of electoral ballots.

No abstract available.

Optical scan voting is considered by many to be the most trustworthy option for conducting elections because it provides an independently verifiable record of each voter’s intent. While op-scan technology has been in use for decades, attempts to improve the machine reading of ballots raises a range of interesting issues in document image analysis. Work thus far has been hindered by a lack of real-world data, since ballots associated with actual elections are kept secure from the public and normally destroyed after a period time. Fortunately, as a result of a recent challenged election in the State of Minnesota, a large collection of op-scan ballot images was made available for public inspection on the World Wide Web. In this paper, we present this unique resource to the document analysis community. We also describe our efforts to annotate the collection, including the latest version of a graphical tool we have developed for collecting ground-truth interpretations, along with the protocol now being employed. The collection, consisting of ballot images, file formats, and associated truth data, is being made openly available to facilitate research in this important area.

Recent work has shown that certain handwriting biometrics are susceptible to forgery attacks, both human- and machine-based. In this paper, we examine a new scheme for using handwritten input that attempts to address such concerns. Pseudo-signatures are intended to be easy for users to create and reproduce while being resilient to forgeries. Here we evaluate their feasibility in terms of usability and security through several user studies. Our initial experiments suggest that, when well-chosen, pseudo-signatures may prove to be an attractive biometric,although more research is required.

Recent developments have resulted in dramatic changes in the way elections are conducted, both in the United States and around the world. Well-publicized flaws in the security of electronic voting systems have led to a push for the use of verifiable paper records in the election process. In this paper, we describe the application of document analysis techniques to facilitate the manual auditing of elections,both to assure the reliability of the final outcome as well as to help reconcile the differences that may arise between repeated scans of the same ballot. We show how techniques developed for document duplicate detection can be applied to this problem, and present experimental results that demonstrate the efficacy of our approach. Related issues concerning machine support for the auditing of elections are also discussed.

Portable ballot counters using camera technology and manual paper feed are potentially more reliable and less expensive than scanner based systems. We show that the spatial sampling rate, geometric linearity, point spread function, and photometric transfer function of off-the-shelf consumer cameras are acceptable for ballot imaging. However, scanner illumination is much more uniform than can be economically accomplished for variable size ballots. Therefore flat-field compensation must be designed into the image processing software. We illustrate the mechanical design of a prototype camera based ballot reader based on our comparative observations.

The push toward voting via hand marked paper ballots has focused attention on the limitations of current optical scan systems. Discrepancies between human and machine interpretations of ballot markings can lead to a loss of trust in the election process. In this paper, a style-based approach to ballot recognition is proposed in which marks are recognized collectively rather than in isolation. The consistency of a voter's style is leveraged to improve the overall accuracy of the system. We compare style-based recognition to various kinds of singlet classifiers and show that it outperforms them by a substantial margin.

As a result of well-publicized security concerns with direct recording electronic (DRE) voting, there is a growing call for systems that employ some form of paper artifact to provide a verifiable physical record of a voter's choices. In this paper, we present a system we are developing to support a multi-institution, cross-disciplinary research project examining issues that arise when paper ballots are used in elections. We survey the motivating factors behind our work, discuss the special constraints raised in processing ballots as opposed to more general document images, and describe the current status of our system.

The principle that for every document analysis task there exists a mechanism for creating well-defined ground-truth is a widely held tenet. Past experience with standard datasets providing ground-truth for character recognition and page segmentation tasks supports this belief. In the process of attempting to evaluate several table recognition algorithms we have been developing, however, we have uncovered a number of serious hurdles connected with the ground-truthing of tables. This problem may, in fact, be much more difficult than it appears. We present a detailed analysis of why table ground-truthing is so hard, including the notions that there may exist more than one acceptable "truth" and/or incomplete or partial "truths".

While techniques for evaluating the performance of lower-level document analysis tasks such as optical character recognition have gained acceptance in the field, attempts to formalize the problem for higher-level algorithms that incorporate more complex structure have been less successful. We describe an intuitive, easy-to-implement scheme for the problem of performance evaluation when document recognition results are represented in the form of a directed acyclic graph. We present results from two simulation studies based on different graph models and one experiment using a well known page segmentation algorithm to demonstrate the applicability of the approach.

This paper introduces a framework for clarifying and formalizing the duplicate document detection problem. Four distinct models are presented, each with a corresponding algorithm for its solution derived from the realm of approximate string matching. The robustness of these techniques is demonstrated through a set of experiments using data reflecting real-world degradation effects.

The authors examine the problem of locating and extracting text from images on the World Wide Web. They describe a text detection algorithm which is based on color clustering and connected component analysis. The algorithm first quantizes the color space of the input image into a number of color classes using a parameter-free clustering procedure. It then identifies text-like connected components in each color class based on their shapes. Finally, a post-processing procedure aligns text-like components into text lines. Experimental results suggest this approach is promising despite the challenging nature of the input data.

In this paper we examine the effects of random-phase spatial sampling on the optical character recognition process. We start by presenting a detailed analysis in the case of 1-dimensional patterns. Empirical data demonstrate that our model is accurate. We then give experimental results for more complex, 2-dimensional patterns (i.e. printed, scanned characters). Spatial sampling seems to account for a significant amount of the variability seen in practice.

A general-purpose approach for enhancing the accuracy of optical character recognition is described. By taking the view that the printed page is a data transmission channel, the authors raise the possibility of error detecting/correcting codes designed specifically for the OCR process. They present experimental results that demonstrate the feasibility of fully automated, 100% accurate OCR for computer typeset documents.>