A visual and interactive tool for optimizing lexical postcorrection of OCR results

Strohmaier, Christian; Ringlstetter, Christoph; Schulz, Klaus U.; Mihov, Stoyan

doi:10.1109/cvprw.2003.10031

Cited by 9 publications

(8 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other interactive systems for post-correction of OCRed texts are described in [12], which was based on Ispell and [13], who describe an elaborate system for training an interactive OCR post-correction tool. The digitization project underway at the National Library comprises an estimated 8 million pages of newspaper text, good for an estimated 25 billion words of running text.…”

Section: Historical Text Collections: Prior Workmentioning

confidence: 99%

Non-interactive OCR Post-correction for Giga-Scale Digitization Projects

Reynaert

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

Abstract. This paper proposes a non-interactive system for reducing the level of OCR-induced typographical variation in large text collections, contemporary and historical. Text-Induced Corpus Clean-up or ticcl (pronounce 'tickle') focuses on high-frequency words derived from the corpus to be cleaned and gathers all typographical variants for any particular focus word that lie within the predefined Levenshtein distance (henceforth: ld). Simple text-induced filtering techniques help to retain as many as possible of the true positives and to discard as many as possible of the false positives. ticcl has been evaluated on a contemporary OCR-ed Dutch text corpus and on a corpus of historical newspaper articles, whose OCR-quality is far lower and which is in an older Dutch spelling. Representative samples of typographical variants from both corpora have allowed us not only to properly evaluate our system, but also to draw effective conclusions towards the adaptation of the adopted correction mechanism to OCR-error resolution. The performance scores obtained up to ld 2 mean that the bulk of undesirable OCR-induced typographical variation present can fully automatically be removed.

show abstract

Section: Historical Text Collections: Prior Workmentioning

confidence: 99%

Non-interactive OCR Post-correction for Giga-Scale Digitization Projects

Reynaert

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

show abstract

“…We then compared the correction accuracy reached when using the five distinct distance measures described above in a system for automated text correction. The correction strategy can be summarized as follows (see [13] for details):…”

Section: Tests With Open Source Ocr Systemsmentioning

confidence: 99%

“…When faced with an unknown token, text correction systems typically fetch the most similar words from a given background dictionary. Word similarity and additional scores are used to produce a ranked list of correction suggestions for the input token [16,14,13]. The resulting correction accuracy heavily depends on how close the word similarity measure reflects the characteristics of the error channel.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deriving Symbol Dependent Edit Weights for Text Correction_The Use of Error Dictionaries

Ringlstetter

Reffle

Gotscharek

et al. 2007

Ninth International Conference on Document Analysis and Recognition (ICDAR 2007) Vol 2

View full text Add to dashboard Cite

Most systems for correcting errors in texts make use of specific word distance measures such as the Levenshtein distance. In many experiments it has been shown that correction accuracy is improved when using edit weights that depend on the particular symbols of the edit operation. However, most proposed approaches so far rely on high amounts of training data where errors and their corrections are collected. In practice, the preparation of suitable ground truth data is often too costly, which means that uniform edit costs are used. In this paper we evaluate approaches for deriving symbol dependent edit weights that do not need any ground truth training data, comparing them with methods based on ground truth training. We suggest a new approach where special error dictionaries are used to estimate weights. The method is simple and very efficient, needing one pass of the document to be corrected. Our experiments with different OCR systems and textual data show that the method consistently improves correction accuracy in a significant way, often leading to results comparable to those achieved with ground truth training.

show abstract

“…Spell-checkers integrated into text editors and office systems try to recognize and remove typing and spelling errors [Damerau 1964;Angell et al 1983;Bentley 1985]. Related systems aim to eliminate errors resulting from optical character recognition [Ho et al 1992;Weigel et al 1995;Hoch and Kieninger 1996;Dengel et al 1997;Taghva and Stofsky 2001;Strohmaier et al 2003aStrohmaier et al , 2003b. Due to the enormous practical relevance, these and similar applications have been intensively studied for decades [Kukich 1992], and they still attract much attention [Taghva et al 2004].…”

Section: Introductionmentioning

confidence: 99%

Adaptive text correction with Web-crawled domain-dependent dictionaries

Ringlstetter

Schulz²,

Mihov

2007

ACM Trans. Speech Lang. Process.

Self Cite

View full text Add to dashboard Cite

For the success of lexical text correction, high coverage of the underlying background dictionary is crucial. Still, most correction tools are built on top of static dictionaries that represent fixed collections of expressions of a given language. When treating texts from specific domains and areas, often a significant part of the vocabulary is missed. In this situation, both automated and interactive correction systems produce suboptimal results. In this article, we describe strategies for crawling Web pages that fit the thematic domain of the given input text. Special filtering techniques are introduced to avoid pages with many orthographic errors. Collecting the vocabulary of filtered pages that meet the vocabulary of the input text, dynamic dictionaries of modest size are obtained that reach excellent coverage values. A tool has been developed that automatically crawls dictionaries in the indicated way. Our correction experiments with crawled dictionaries, which address English and German document collections from a variety of thematic fields, show that with these dictionaries even the error rate of highly accurate texts can be reduced, using completely automated correction methods. For interactive text correction, more sensible candidate sets for correcting erroneous words are obtained and the manual effort is reduced in a significant way. To complete this picture, we study the effect when using word trigram models for correction. Again, trigram models from crawled corpora outperform those obtained from static corpora.

show abstract

A visual and interactive tool for optimizing lexical postcorrection of OCR results

Abstract: Abstract

Cited by 9 publications

References 18 publications

Non-interactive OCR Post-correction for Giga-Scale Digitization Projects

Non-interactive OCR Post-correction for Giga-Scale Digitization Projects

Deriving Symbol Dependent Edit Weights for Text Correction_The Use of Error Dictionaries

Adaptive text correction with Web-crawled domain-dependent dictionaries

Contact Info

Product

Resources

About