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.

This paper plans an end-to-end method for extracting information from tables embedded in documents; input format is ASCII, to which any richer format can be converted, preserving all textual and much of the layout information. We start by defining table. Then we describe the steps involved in extracting information from tables and analyse table-related research to: place the contribution of different authors, find the paths research is following, and identify issues that are still unsolved. We then analyse current approaches to evaluating table processing algorithms and propose two new metrics for the task of segmenting cells/columns/rows. We proceed to design our own end-to-end method, where there is a higher interaction between the different steps; we indicate how back loops in the usual order of the steps can reduce the possibility of errors and contribute to solving previously unsolved problems. Finally we explore how the actual interpretation of the table not only allows inferring the accuracy of the overall extraction process but also contributes to actually improving its quality. In order to do so, we believe interpretation has to consider context specific knowledge; we explore how the addition of this knowledge can be made in a plug-in/out manner, such that the overall method will maintain its operability in different contexts.

Table recognition algorithms may be described by models of table location and struc-ture, and decisions made relative to these models. These algorithms are usually defined informally as a sequence of decisions with supporting data observations and transformations. In this investigation, we formalize these algorithms as strategies in an imitation game, where the goal of the game is to match table interpretations from a chosen procedure as closely as possible. The chosen procedure may be a person or persons producing ‘ground truth, ’ or an algorithm. To describe table recognition strategies we have defined the Recognition Strat-egy Language (RSL). RSL is a simple functional language for describing strategies as sequences of abstract decision types whose results are determined by any suit-able decision method. RSL defines and maintains interpretation trees, a simple data structure for describing recognition results. For each interpretation in an interpreta-tion tree, we annotate hypothesis histories which capture the creation, revision, and rejection of individual hypotheses, such as the logical type and structure of regions. We present a proof-of-concept using two strategies from the literature. We demon-strate how RSL allows strategies to be specified at the level of decisions rather than ii algorithms, and we compare results of our strategy implementations using new tech-niques. In particular, we introduce historical recall and precision metrics. Con-ventional recall and precision characterize hypotheses accepted after a strategy has finished. Historical recall and precision provide additional information by describing all generated hypotheses, including any rejected in the final result. iii

This thesis develops a mathematical basis for understanding the structure of on-line handwritten documents and explores some of the related problems in detail. With the increase in popularity of portable computing devices, such as PDAs and handheld computers, non-keyboard based methods for data entry are receiving more attention in the research communities and commercial sector. The most promising options are pen-based and speech-based inputs. Pen-based input devices generate handwritten documents which have on-line or dynamic (temporal) information encoded in them. Digitizing devices like Smart-Boards and computing platforms, which use pen-based input such as the IBM Thinkpad TransNote and Tablet PCs, create on-line documents. As these devices become available and affordable, large volumes of digital handwritten data will be generated and the problem of archiving and retrieving such data becomes an important concern. This thesis addresses the problem of on-line document understanding, which is an essential component of an effective retrieval algorithm. This thesis describes a mathematical model for representation of on-line handwritten

People want to know! And so do government agencies, information providers, search-andretrieval companies, electronic publishers, corporate enterprises, and business-intelligence professionals. But they’re swamped with volumes of data spewed forth from search engines,

An important step towards the goal of table understanding is a method for reliable table detection. This paper describes a general solution for detecting tables based on computing an optimal partitioning of a document into some number of tables. A dynamic programming algorithm is given to solve the resulting optimization problem. This high-level framework is independent of any particular table quality measure and independent of the document medium. Moreover, it does not rely on the presence of ruling lines or other table delimiters. We also present table quality measures based on white space correlation and vertical connected component analysis. These measures can be applied equally well to ASCII text and scanned images. We report on some preliminary experiments using this method to detect tables in both ASCII text and scanned images, yielding promising results. We present detailed evaluation of these results using three different criteria which by themselves pose interesting research...

this paper, we describe a technique for detecting tables that does not rely on ruling lines and has the desirable property that an identical high-level approach can be applied to tables expressed as ASCII text and those in image format. We also present the results of a preliminary experimental evaluation.

We present a hierarchical approach for extracting homogeneous regions in on-line documents. The problem of identifying and processing ruled and unruled tables, text and drawings is addressed. The on-line document is first segmented into regions with only text strokes and regions with both text and non-text strokes. The text region is further classified as unruled table or plain text. Stroke clustering is used to segment the non-text regions. Each nontext segment is then classified as drawing, ruled table or underlined keyword using stroke properties. The individual regions are processed and the results are assembled to identify the structure of the on-line document.

A segmentation algorithm, which can detect different regions of a handwritten document such as text lines, tables and sketches will be extremely useful in a variety of applications such as retrieval, translation and genre classification. However, this task is extremely challenging for handwritten documents, which vary considerably in their structure and content. In this paper, we describe a robust segmentation method to detect the regions in an unstructured on-line handwritten document. We utilize the temporal information in on-line documents along with its spatial layout to improve the segmentation results. The properties of handwritten strokes are computed using a spline-based representation. We compute the most likely segmentation of the handwritten page using a Stochastic Context Free Grammar based parser. The regions considered in this work include paragraphs, text lines, words, and non-text regions.

Abstract—We propose a novel method to evaluate table segmentation results based on a table image ground truther. In the ground-truthing process, we first extract connected components from a given table image and connect them into an atom graph with weighed edges. Edge weight takes neighboring connected components ’ size similarities and distances into consideration. Then the ground truther semi-automatically determines the locations and spans of row/column separators according to projection profiles, under human supervision. We evaluate a given table segmentation by computing edit distance from its row and column separator assertions relative to ground truth. The edit distance is the sum of all the edit operation costs that correct wrong row and column separators. Each edit operation cost is a function of the sum of the weights of the edges that the separator cuts through. Thus, separator errors incur different costs depending on the severity of the error, where severity roughly corresponds to how forgivable the error would be considered by a human observer. Experimental results demonstrate that the proposed evaluation method is not only efficient, but also useful in formalizing the intuitive quality of different segmentations.