Automatic Information Extraction from Scanned Documents

Bureš, Lukáš; Neduchal, Petr; Müller, Luděk

doi:10.1007/978-3-030-60276-5_9

Cited by 4 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In some cases, preprocessing tasks, such as image contrast improvement, noise reduction, binarization, and image deskewing, are required to get a visual improvement of the scanned documents [3]. High accuracy and low latency for processing large numbers of documents are required to have the best result of OCR [1].…”

Section: Related Workmentioning

confidence: 99%

“…Nguyen et al in 2020 [2] used a rapid and convenient text-mining method to automatically extract pathology features from complex text-based scanned photocopies of Australian typewritten clinical pathology reports drawn from multiple different sources. Bures et al in 2020 [3] proposed a system design to extract information from several countries structured scanned invoice documents by an ordinary office scanner device. Rastogi et al in 2020 [4] used knowledge graph and Formal Concept Analysis (FCA) template detection to extract information from 1,400 scanned trade finance documents.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Optical Character Recognition Engines Performance Comparison in Information Extraction

Ramdhani

Budi²,

Purwandari³

2021

IJACSA

View full text Add to dashboard Cite

Named Entity Recognition (NER) is often used to acquire important information from text documents as a part of the Information Extraction (IE) process. However, the text documents quality affects the accuracy of the data obtained, especially for text documents acquired involving the Optical Character Recognition (OCR) process, which never reached 100% accuracy. This research tried to examine which OCR engine with the highest performance for IE using NER by comparing three OCR engines (Foxit, PDF2GO, Tesseract) over 8,562 government human resources documents within six document categories, two document structures, and four measurements. Several essential entities such as name, employee ID, document number, document publishing date, employee rank, and family member's name were trying to be extracted automatically from the documents. NER processes were done using Python programming language, and the preprocessing tasks were done separately for Foxit, PDF2GO, and Tesseract. In summary, each OCR engine has its drawbacks and benefit, such as Tesseract has better NER extraction and conversion time with better accuracy but lack in the number of entities acquired.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%