Development of a new image-to-text conversion system for Pashto, farsi and traditional Chinese

Marek Rychlik; Dwight Nwaigwe; Yan Han; Dylan Murphy

Development of a new image-to-text conversion system for Pashto, farsi and traditional Chinese

Marek Rychlik, Dwight Nwaigwe, Yan Han, Dylan Murphy

Mathematics

Research output: Contribution to journal › Article › peer-review

Abstract

We report upon the results of a research and prototype building project Worldly OCR dedicated to developing new, more accurate image-to-text conversion software for several languages and writing systems. These include the cursive scripts Farsi and Pashto, and Latin cursive scripts. We also describe approaches geared towards Traditional Chinese, which is non-cursive, but features an extremely large character set of 65,000 characters. Our methodology is based on Machine Learning, especially Deep Learning, and Data Science, and is directed towards vast quantities of original documents, exceeding a billion pages. The target audience of this paper is a general audience with interest in Digital Humanities or in retrieval of accurate full-text and metadata from digital images.

MSC Codes 68T10, 68T07

Original language	English (US)
Journal	Unknown Journal
State	Published - May 8 2020

ASJC Scopus subject areas

General

Fingerprint Dive into the research topics of 'Development of a new image-to-text conversion system for Pashto, farsi and traditional Chinese'. Together they form a unique fingerprint.

Cite this

@article{5732f63b7ea4461faca5c1188934d944,

title = "Development of a new image-to-text conversion system for Pashto, farsi and traditional Chinese",

abstract = "We report upon the results of a research and prototype building project Worldly OCR dedicated to developing new, more accurate image-to-text conversion software for several languages and writing systems. These include the cursive scripts Farsi and Pashto, and Latin cursive scripts. We also describe approaches geared towards Traditional Chinese, which is non-cursive, but features an extremely large character set of 65,000 characters. Our methodology is based on Machine Learning, especially Deep Learning, and Data Science, and is directed towards vast quantities of original documents, exceeding a billion pages. The target audience of this paper is a general audience with interest in Digital Humanities or in retrieval of accurate full-text and metadata from digital images.MSC Codes 68T10, 68T07",

author = "Marek Rychlik and Dwight Nwaigwe and Yan Han and Dylan Murphy",

year = "2020",

month = may,

day = "8",

language = "English (US)",

journal = "Nuclear Physics A",

issn = "0375-9474",

publisher = "Elsevier",

}

TY - JOUR

T1 - Development of a new image-to-text conversion system for Pashto, farsi and traditional Chinese

AU - Rychlik, Marek

AU - Nwaigwe, Dwight

AU - Han, Yan

AU - Murphy, Dylan

PY - 2020/5/8

Y1 - 2020/5/8

N2 - We report upon the results of a research and prototype building project Worldly OCR dedicated to developing new, more accurate image-to-text conversion software for several languages and writing systems. These include the cursive scripts Farsi and Pashto, and Latin cursive scripts. We also describe approaches geared towards Traditional Chinese, which is non-cursive, but features an extremely large character set of 65,000 characters. Our methodology is based on Machine Learning, especially Deep Learning, and Data Science, and is directed towards vast quantities of original documents, exceeding a billion pages. The target audience of this paper is a general audience with interest in Digital Humanities or in retrieval of accurate full-text and metadata from digital images.MSC Codes 68T10, 68T07

AB - We report upon the results of a research and prototype building project Worldly OCR dedicated to developing new, more accurate image-to-text conversion software for several languages and writing systems. These include the cursive scripts Farsi and Pashto, and Latin cursive scripts. We also describe approaches geared towards Traditional Chinese, which is non-cursive, but features an extremely large character set of 65,000 characters. Our methodology is based on Machine Learning, especially Deep Learning, and Data Science, and is directed towards vast quantities of original documents, exceeding a billion pages. The target audience of this paper is a general audience with interest in Digital Humanities or in retrieval of accurate full-text and metadata from digital images.MSC Codes 68T10, 68T07

UR - http://www.scopus.com/inward/record.url?scp=85094771149&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85094771149&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85094771149

JO - Nuclear Physics A

JF - Nuclear Physics A

SN - 0375-9474

ER -