Improved Tesseract optical character recognition performance on Thai document datasets

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Big Data Research Pub Date : 2025-02-08 DOI:10.1016/j.bdr.2025.100508

Noppol Anakpluek, Watcharakorn Pasanta, Latthawan Chantharasukha, Pattanawong Chokratansombat, Pajaya Kanjanakaew, Thitirat Siriborvornratanakul

{"title":"Improved Tesseract optical character recognition performance on Thai document datasets","authors":"Noppol Anakpluek, Watcharakorn Pasanta, Latthawan Chantharasukha, Pattanawong Chokratansombat, Pajaya Kanjanakaew, Thitirat Siriborvornratanakul","doi":"10.1016/j.bdr.2025.100508","DOIUrl":null,"url":null,"abstract":"<div><div>This research aims to improve the accuracy and efficiency of Optical Character Recognition (OCR) technology for the Thai language, specifically in the context of Thai government documents. OCR enables the conversion of text from images into machine-readable format, facilitating document storage and further processing. However, applying OCR to the Thai language presents unique challenges due to its complexity. This study focuses on enhancing the performance of the Tesseract OCR engine, a widely used free OCR technology, by implementing various image preprocessing techniques such as masking, adaptive thresholds, median filtering, Canny edge detection, and morphological operators. A dataset of Thai documents is utilized, and the OCR system's output is evaluated using word error rate (WER) and character error rate (CER) metrics. To improve text extraction accuracy, the research employs the original U-Net architecture [<span><span>19</span></span>] for image segmentation. Furthermore, the Tesseract OCR engine is finetuned, and image preprocessing is performed to optimize OCR system accuracy. The developed tools automate workflow processes, alleviate constraints on model training, and enable the effective utilization of information from official Thai documents for various purposes.</div></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"39 ","pages":"Article 100508"},"PeriodicalIF":3.5000,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Big Data Research","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2214579625000036","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

Abstract

This research aims to improve the accuracy and efficiency of Optical Character Recognition (OCR) technology for the Thai language, specifically in the context of Thai government documents. OCR enables the conversion of text from images into machine-readable format, facilitating document storage and further processing. However, applying OCR to the Thai language presents unique challenges due to its complexity. This study focuses on enhancing the performance of the Tesseract OCR engine, a widely used free OCR technology, by implementing various image preprocessing techniques such as masking, adaptive thresholds, median filtering, Canny edge detection, and morphological operators. A dataset of Thai documents is utilized, and the OCR system's output is evaluated using word error rate (WER) and character error rate (CER) metrics. To improve text extraction accuracy, the research employs the original U-Net architecture [19] for image segmentation. Furthermore, the Tesseract OCR engine is finetuned, and image preprocessing is performed to optimize OCR system accuracy. The developed tools automate workflow processes, alleviate constraints on model training, and enable the effective utilization of information from official Thai documents for various purposes.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

求助全文

约1分钟内获得全文去求助

来源期刊

Big Data Research Computer Science-Computer Science Applications

CiteScore

8.40

自引率

3.00%

发文量

期刊介绍： The journal aims to promote and communicate advances in big data research by providing a fast and high quality forum for researchers, practitioners and policy makers from the very many different communities working on, and with, this topic. The journal will accept papers on foundational aspects in dealing with big data, as well as papers on specific Platforms and Technologies used to deal with big data. To promote Data Science and interdisciplinary collaboration between fields, and to showcase the benefits of data driven research, papers demonstrating applications of big data in domains as diverse as Geoscience, Social Web, Finance, e-Commerce, Health Care, Environment and Climate, Physics and Astronomy, Chemistry, life sciences and drug discovery, digital libraries and scientific publications, security and government will also be considered. Occasionally the journal may publish whitepapers on policies, standards and best practices.

期刊最新文献

Modeling meaningful volatility events to classify monetary policy announcements Predicting option prices: From the Black-Scholes model to machine learning methods Editorial Board Efficient training: Federated learning cost analysis Improved Tesseract optical character recognition performance on Thai document datasets