Character-Level Alignment Using WFST and LSTM for Post-processing in Multi-script Recognition Systems - A Comparative Study

Azawi, Mayce Al; Hasan, Adnan ul; Liwicki, Marcus; Breuel, Thomas M.

doi:10.1007/978-3-319-11758-4_41

Cited by 5 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, the version of reCAPTCHA allowing post-correction has been shutdown since March 2018. 8 Collaborative post-OCR processing approaches prove their benefits with relatively high accuracy, and are cost effective. In addition, they can be easily applied to other digitisation projects.…”

Section: Manual Approachesmentioning

confidence: 99%

“…Instead of aligning OCR versions of the same scan, an approach of Wemhoener et al [163] enables to create a sequence alignment of OCR outputs with the scans of different copies of the same book, or its different editions. Al Azawi et al [4,8] apply Line-to-Page alignment that aligns each line of the 1st OCR with the whole page of the second OCR using Weighted Finite-State Transducers (WFST).…”

Section: Isolated-word Approachesmentioning

confidence: 99%

“…In the last step, several techniques are applied to choose the best sequence. Lopresti et al [91], Lin [87], Wemhoener et al [163], and Reul et al [129] utilize voting policy, Al Azawi et al [4,8] use Long Short-Term Memory (LSTM) [64] to decide the most relevant output. Different kinds of features (voting, number, dictionary, gazetteer, and lexical feature) are used in learning decision list, maximum entropy classification or conditional random fields (CRF) methods to choose the best possible correction by Lund et al [92,[94][95][96].…”

Section: Isolated-word Approachesmentioning

confidence: 99%

See 2 more Smart Citations

Survey of Post-OCR Processing Approaches

et al. 2021

View full text Add to dashboard Cite

Optical character recognition (OCR) is one of the most popular techniques used for converting printed documents into machine-readable ones. While OCR engines can do well with modern text, their performance is unfortunately significantly reduced on historical materials. Additionally, many texts have already been processed by various out-of-date digitisation techniques. As a consequence, digitised texts are noisy and need to be post-corrected. This article clarifies the importance of enhancing quality of OCR results by studying their effects on information retrieval and natural language processing applications. We then define the post-OCR processing problem, illustrate its typical pipeline, and review the state-of-the-art post-OCR processing approaches. Evaluation metrics, accessible datasets, language resources, and useful toolkits are also reported. Furthermore, the work identifies the current trend and outlines some research directions of this field.

show abstract

Section: Manual Approachesmentioning

confidence: 99%

Section: Isolated-word Approachesmentioning

confidence: 99%

Section: Isolated-word Approachesmentioning

confidence: 99%

See 1 more Smart Citation

Survey of Post-OCR Processing Approaches

et al. 2021

View full text Add to dashboard Cite

show abstract

“…(Reul et al, 2018) make use of a voting based approach to post-correct OCR-ed early printed books in which multiple models are trained and then a decision based on confidences values for recognized characters and their alternatives is made. (Wemhoener, Yalniz, & Manmatha, 2013) also rely on a voting based decision based on the alignment of multiple OCR outputs derived from copies of the same source documents, while (Al Azawi, Ul Hasan, Liwicki, & Breuel, 2014;Al Azawi, Liwicki, & Breuel, 2015) utilize LSTM networks to determine the final output tokens and evaluate their method on a data set consisting of more modern documents (Guyon, Haralick, Hull, & Phillips, 1997). Another approach which is based on the recognition of text reuse and the alignment of these repeated passages is that of (Xu & Smith, 2017) which was tested on a collection of 19th century newspapers.…”

Section: General Models -Cross-validation Experiments For a Large Doc...mentioning

confidence: 99%

Optimizing the Training of Models for Automated Post-Correction of Arbitrary OCR-ed Historical Texts

Englmeier

Fink²,

Springmann³

et al. 2022

JLCL

View full text Add to dashboard Cite

Systems for post-correction of OCR-results for historical texts are based on statistical correction models obtained by supervised learning. For training, suitable collections of ground truth materials are needed. In this paper we investigate the dependency of the power of automated OCR post-correction on the form of ground truth data and other training settings used for the computation of a post-correction model. The post-correction system A-PoCoTo considered here is based on a profiler service that computes a statistical profile for an OCR-ed input text. We also look in detail at the influence of the profiler resources and other settings selected for training and evaluation. As a practical result of several fine-tuning steps, a general post-correction model is achieved where experiments for a large and heterogeneous collection of OCR-ed historical texts show a consistent improvement of base OCR accuracy. The results presented are meant to provide insights for libraries that want to apply OCR post-correction to a larger spectrum of distinct OCR-ed historical printings and ask for "representative" results.

show abstract

“…The LSTM networks configuration will be explained in detail in Section IV-C. The trained language model using LSTM networks was implemented by Al Azawi et al [12]. The trained language model was applied on single OCR output.…”

Section: B Strings Encodingmentioning

confidence: 99%

Combination of multiple aligned recognition outputs using WFST and LSTM

Azawi

Liwicki

Breuel

2015

2015 13th International Conference on Document Analysis and Recognition (ICDAR)

Self Cite

View full text Add to dashboard Cite

The contribution of this paper is a new strategy of integrating multiple recognition outputs of diverse recognizers. Such an integration can give higher performance and more accurate outputs than a single recognition system. The problem of aligning various Optical Character Recognition (OCR) results lies in the difficulties to find the correspondence on character, word, line, and page level. These difficulties arise from segmentation and recognition errors which are produced by the OCRs. Therefore, alignment techniques are required for synchronizing the outputs in order to compare them. Most existing approaches fail when the same error occurs in the multiple OCRs. If the corrections do not appear in one of the OCR approaches are unable to improve the results. We design a Line-to-Page alignment with edit rules using Weighted Finite-State Transducers (WFST). These edit rules are based on edit operations: insertion, deletion, and substitution. Therefore, an approach is designed using Recurrent Neural Networks with Long Short-Term Memory (LSTM) to predict these types of errors. A Character-Epsilon alignment is designed to normalize the size of the strings for the LSTM alignment. The LSTM returns best voting, especially when the heuristic approaches are unable to vote among various OCR engines. LSTM predicts the correct characters, even if the OCR could not produce the characters in the outputs. The approaches are evaluated on OCR's output from the UWIII and historical German Fraktur dataset which are obtained from state-of-the-art OCR systems. The experiments shows that the error rate of the LSTM approach has the best performance with around 0.40%, while other approaches are between 1.26% and 2.31%.

show abstract

Character-Level Alignment Using WFST and LSTM for Post-processing in Multi-script Recognition Systems - A Comparative Study

Cited by 5 publications

References 8 publications

Survey of Post-OCR Processing Approaches

Survey of Post-OCR Processing Approaches

Optimizing the Training of Models for Automated Post-Correction of Arbitrary OCR-ed Historical Texts

Combination of multiple aligned recognition outputs using WFST and LSTM

Contact Info

Product

Resources

About