Applying the T-Recs table recognition system to the business letter domain

Kieninger, Thomas; Dengel, Andreas

doi:10.1109/icdar.2001.953843

Cited by 62 publications

(37 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Details on principles of T-Recs can be found in [15,16]. It has since then undergone one major and several mi- Table 1: Results of evaluating a T-Recs system on 120 binary 300-dpi scanned UW-3 dataset pages containing table zones.…”

Section: T-recs Evaluation Resultsmentioning

confidence: 99%

“…The very early approaches focused on the detection of table delineation, significantly large column spacing or known column headings and have thus been applicable only to a fraction of table models [18]. An early model free approach was described by Kieninger et al [15,16]. Their approach performed a bottom up clustering of blocks and potential column candidates based on overlapping words segments in adjacent lines.…”

Section: Introductionmentioning

confidence: 99%

“…Hu et al [13] used a dataset consisting of 26 Wall Street Journal article in text format and 25 email messages. Kieninger et al [16] used a proprietary dataset of invoices of a purchasing department. Gatos et al [8] evaluated their algorithm on a test corpus consisting of scanned forms, news papers, magazines, scientific papers, tickets, bank cheques etc.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An open approach towards the benchmarking of table structure recognition systems

Shahab

Shafait

Kieninger

et al. 2010

Proceedings of the 9th IAPR International Workshop on Document Analysis Systems

View full text Add to dashboard Cite

Table spotting and structural analysis are just a small fraction of tasks relevant when speaking of table analysis. Today, quite a large number of different approaches facing these tasks have been described in literature or are available as part of commercial OCR systems that claim to deal with tables on the scanned documents and to treat them accordingly.However, the problem of detecting tables is not yet solved at all. Different approaches have different strengths and weak points. Some fail in certain situations or layouts where others perform better. How shall one know, which approach or system is the best for his specific job? The answer to this question raises the demand for an objective comparison of different approaches which address the same task of spotting tables and recognizing their structure. This paper describes our approach towards establishing a complete and publicly available, hence open environment for the benchmarking of table spotting and structural analysis. We provide free access to the ground truthing tool and evaluation mechanism described in this paper, describe the ideas behind and we also provide ground truth for the 547 documents of the UNLV and UW-3 datasets that contain tables.In addition, we applied the quality measures to the results that were generated by the T-Recs system which we developed some years ago and which we started to further advance since a few months.

show abstract

Section: T-recs Evaluation Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An open approach towards the benchmarking of table structure recognition systems

Shahab

Shafait

Kieninger

et al. 2010

Proceedings of the 9th IAPR International Workshop on Document Analysis Systems

View full text Add to dashboard Cite

show abstract

“…All the methods can be divided into three categories: pre-defined layout based [22], heuristics based [17,6,9,8], and statistical based. Pre-defined layout based algorithms usually work well for one domain, but is difficult to extend.…”

Section: Related Work On Table Detectionmentioning

confidence: 99%

Identifying table boundaries in digital documents via sparse line detection

Liu

Mitra

Giles

2008

Proceedings of the 17th ACM Conference on Information and Knowledge Management

View full text Add to dashboard Cite

Most prior work on information extraction has focused on extracting information from text in digital documents. However, often, the most important information being reported in an article is presented in tabular form in a digital document. If the data reported in tables can be extracted and stored in a database, the data can be queried and joined with other data using database management systems. In order to prepare the data source for

show abstract

“…For example, black-box analysis is standard practice in the document recognition community [1][8] [10][11] [14][16] [17]. Diagnosis of failures is difficult, since blackbox observations provide little insight into the causes of poor recognition results.…”

Section: Introductionmentioning

confidence: 99%

White-Box Evaluation of Computer Vision Algorithms through Explicit Decision-Making

Zanibbi

Blostein

Cordy

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Traditionally computer vision and pattern recognition algorithms are evaluated by measuring differences between final interpretations and ground truth. These black-box evaluations ignore intermediate results, making it difficult to use intermediate results in diagnosing errors and optimization. We propose "opening the box," representing vision algorithms as sequences of decision points where recognition results are selected from a set of alternatives. For this purpose, we present a domain-specific language for pattern recognition tasks, the Recognition Strategy Language (RSL). At run-time, an RSL interpreter records a complete history of decisions made during recognition, as it applies them to a set of interpretations maintained for the algorithm. Decision histories provide a rich new source of information: recognition errors may be traced back to the specific decisions that caused them, and intermediate interpretations may be recovered and displayed. This additional information also permits new evaluation metrics that include false negatives (correct hypotheses that the algorithm generates and later rejects), such as the percentage of ground truth hypotheses generated (historical recall), and the percentage of generated hypotheses that are correct (historical precision). We illustrate the approach through an analysis of cell detection in two published table recognition algorithms.

show abstract

Applying the T-Recs table recognition system to the business letter domain

Cited by 62 publications

References 6 publications

An open approach towards the benchmarking of table structure recognition systems

An open approach towards the benchmarking of table structure recognition systems

Identifying table boundaries in digital documents via sparse line detection

White-Box Evaluation of Computer Vision Algorithms through Explicit Decision-Making

Contact Info

Product

Resources

About