OCR Accuracy Improvement on Document Images Through a Novel Pre-Processing Approach

Harraj, A. El; Raissouni, Naoufal

doi:10.5121/sipij.2015.6401

Cited by 13 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Koistinen et al [23] improved word level by 27.5% compared to FineReader 7 or 8 and 9.2% for FineReader 11. Harraj and Raissouni [21] registered an improvement in OCR accuracy between 2% to 6.8%. Bui et al [6] succeeded in proving the performance of engines with their automatic pre-processing method selection, with Tesseract OCR having an improvement of 25%.…”

Section: Related Workmentioning

confidence: 94%

“…In the literature, various approaches combine image processing algorithms. Harraj and Raissouni [21] applied illumination adjustment, grayscale conversion, unsharp masking, and Otsu binarization to counteract image distortions and improve OCR accuracy. Similarly, Ntogas and Ventzas [33] trained a model for Finnish Fraktur fonts and analyzed different combinations of pre-processing image algorithms.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Optimization of Image Processing Algorithms for Character Recognition in Cultural Typewritten Documents

Dias

Lopes

2023

J. Comput. Cult. Herit.

View full text Add to dashboard Cite

Linked Data is used in various fields as a new way of structuring and connecting data. Cultural heritage institutions have been using linked data to improve archival descriptions and facilitate the discovery of information. Most archival records have digital representations of physical artifacts in the form of scanned images that are non-machine-readable. Optical Character Recognition (OCR) recognizes text in images and translates it into machine-encoded text. This paper evaluates the impact of image processing methods and parameter tuning in OCR applied to typewritten cultural heritage documents. The approach uses a multi-objective problem formulation to minimize Levenshtein edit distance and maximize the number of words correctly identified with a non-dominated sorting genetic algorithm (NSGA-II) to tune the methods’ parameters. Evaluation results show that parameterization by digital representation typology benefits the performance of image pre-processing algorithms in OCR. Furthermore, our findings suggest that employing image pre-processing algorithms in OCR might be more suitable for typologies where the text recognition task without pre-processing does not produce good results. In particular, Adaptive Thresholding, Bilateral Filter, and Opening are the best-performing algorithms for the theatre plays’ covers, letters, and overall dataset, respectively, and should be applied before OCR to improve its performance.

show abstract

Section: Related Workmentioning

confidence: 94%

Section: Related Workmentioning

confidence: 99%