OCR Accuracy Prediction Method Based on Blur Estimation

Kieu, Van-Cuong; Cloppet, Florence; Vincent, Nicole

doi:10.1109/das.2016.50

Cited by 8 publications

(4 citation statements)

References 18 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Blando et al [1995] inspect specific typeface properties, while Lu et al [2020] aim to discover physical image distortions. Other examples include quantifying image degradation (Peng et al [2015]) and estimating the amount of blur (Kieu et al [2016]). Finally, a recent work from Singh et al [2018] uses surrogate models to learn document quality based on ground truth images.…”

Section: Related Workmentioning

confidence: 99%

Rerunning OCR: A Machine Learning Approach to Quality Assessment and Enhancement Prediction

Schneider

Maurer

2022

Journal of Data Mining &Amp; Digital Humanities

View full text Add to dashboard Cite

Iterating with new and improved OCR solutions enforces decision making when it comes to targeting the right candidates for reprocessing. This especially applies when the underlying data collection is of considerable size and rather diverse in terms of fonts, languages, periods of publication and consequently OCR quality. This article captures the efforts of the National Library of Luxembourg to support those targeting decisions. They are crucial in order to guarantee low computational overhead and reduced quality degradation risks, combined with a more quantifiable OCR improvement. In particular, this work explains the methodology of the library with respect to text block level quality assessment. Through extension of this technique, a regression model, that is able to take into account the enhancement potential of a new OCR engine, is also presented. They both mark promising approaches, especially for cultural institutions dealing with historical data of lower quality.

show abstract

Section: Related Workmentioning

confidence: 99%

Rerunning OCR: A Machine Learning Approach to Quality Assessment and Enhancement Prediction

Schneider

Maurer

2022

Journal of Data Mining &Amp; Digital Humanities

View full text Add to dashboard Cite

show abstract

“…Other direct quality measures concentrate on the gradient of the image [28,29]. To date, no NR-IQA-based OCR accuracy predictors [30][31][32][33][34][35] pick up on the four major sources of OCR accuracy reduction: noise, blur, contrast and brightness. SEDIQA builds on the D-IQA findings, using entropy, gradient and median intensity to combine measures of the four main sources of error, creating a robust and directly measurable NR-IQA for documents.…”

Section: Introductionmentioning

confidence: 99%

SEDIQA: Sound Emitting Document Image Quality Assessment in a Reading Aid for the Visually Impaired

Courtney

2021

J. Imaging

View full text Add to dashboard Cite

For visually impaired people (VIPs), the ability to convert text to sound can mean a new level of independence or the simple joy of a good book. With significant advances in optical character recognition (OCR) in recent years, a number of reading aids are appearing on the market. These reading aids convert images captured by a camera to text which can then be read aloud. However, all of these reading aids suffer from a key issue—the user must be able to visually target the text and capture an image of sufficient quality for the OCR algorithm to function—no small task for VIPs. In this work, a sound-emitting document image quality assessment metric (SEDIQA) is proposed which allows the user to hear the quality of the text image and automatically captures the best image for OCR accuracy. This work also includes testing of OCR performance against image degradations, to identify the most significant contributors to accuracy reduction. The proposed no-reference image quality assessor (NR-IQA) is validated alongside established NR-IQAs and this work includes insights into the performance of these NR-IQAs on document images. SEDIQA is found to consistently select the best image for OCR accuracy. The full system includes a document image enhancement technique which introduces improvements in OCR accuracy with an average increase of 22% and a maximum increase of 68%.

show abstract

“…Lately, Kieu et al [29] proposed a local blur estimation based on fuzzy‐C‐means clustering approach after a binarisation step. They combine this local estimation with the character size in a learning‐based strategy, in order to predict the OCR accuracy.…”

Section: Introductionmentioning

confidence: 99%

Local multiscale blur estimation based on toggle mapping for sharp region extraction

Gillibert

Chabardès

Marcotegui

2018

IET Image Processing

View full text Add to dashboard Cite

In this paper a multiscale local blur estimation is proposed based on the existing local focus measure that combines gradient and toggle mapping. This method evaluates the quality of images regardless of their content (not in an autofocus context) and can predict OCR accuracy based on local blur. The resulting approach outperforms state of the art blur detection methods. Quantitative results are given on DIQA database. Moreover we demonstrate its usefulness for extracting a region of interest from partially blurry images. Results are shown on images acquired by a project devoted to smartphone based text extraction for visually impaired people. In this context sharp region extraction is essential since it allows warning the users when their picture is unusable. Moreover it saves computing time.

show abstract

OCR Accuracy Prediction Method Based on Blur Estimation

Cited by 8 publications

References 18 publications

Rerunning OCR: A Machine Learning Approach to Quality Assessment and Enhancement Prediction

Rerunning OCR: A Machine Learning Approach to Quality Assessment and Enhancement Prediction

SEDIQA: Sound Emitting Document Image Quality Assessment in a Reading Aid for the Visually Impaired

Local multiscale blur estimation based on toggle mapping for sharp region extraction

Contact Info

Product

Resources

About