A Fast Prediction of the OCR Results Based on Binary Image Quality Assessment Methods

Mateusz Kopytek; Krzysztof Piotr Okarma

doi:10.17388/wut.2024.0002.mini

A Fast Prediction of the OCR Results Based on Binary Image Quality Assessment Methods

Abstract

Since the first step of the Optical Character Recognition (OCR) procedure is usually image binarization and the execution of the OCR process takes longer time than image quality assessment (IQA) of binary images, a fast prediction of the OCR results before text recognition would be interesting for non-uniformly illuminated document images, also for applications in mobile devices. Since IQA methods for binary images usually require the presence of a reference image, an important problem is to avoid this necessity as proposed in the paper. Experimental results, obtained by applying mutual comparisons for various binarization methods, are promising and confirm the validity of the proposed approach.

Citations

0

CrossRef
0

Web of Science
0

Scopus

Authors (2)

Mateusz Kopytek mgr
- Doctoral School
- West Pomeranian University of Technology in Szczecin
Krzysztof Piotr Okarma prof. dr hab. inż.
- Faculty of Electrical Engineering
- West Pomeranian University of Technology in Szczecin

Cite as

Full text

full text is not available in portal

full content of the article see on external site open in new tab

Keywords

Details

Category:: Other publications
Type:: Other publications
Title of issue:: Progress in Polish Artificial Intelligence Research 5 - Proceedings of the 5th Polish Conference on Artificial Intelligence, PP-RAI'2024 strony 242 - 248
Publication year:: 2024
DOI:: Digital Object Identifier (open in new tab) 10.17388/wut.2024.0002.mini
Verified by:: No verification