Rendered pdf
This commit is contained in:
@@ -3,12 +3,12 @@
|
||||
|
||||
\subsection{Texterkennungssysteme}
|
||||
|
||||
Optische Texterkennung wird in der Informationstechnik eingesetzt, um Textinhalte aus gedruckten oder digital reasterisierten Medien zu extrahieren. Dieses Verfahren kann für diverse Anwendungsgebiete genutzt werden, wie beispielsweise für Handschrifterkennung oder für das Ablesen von Nummernschildern eines Autos \mcite{asif2014overview}. Auf dem Markt gibt es dafür bereits viele kommerzielle Komplettlösungen wie "IronOCR", "Google Cloud Vision", "Amazon Textract" oder "Microsoft Azure Computer Vision", die oftmals sehr gute Ergebnisse erzielen und sich gut in bestehende Prozesse oder Anwendungen integrieren lassen \mcite{the_old_bailey_and_ocr} \mcite{cc_platforms_comparison}.
|
||||
Optische Texterkennung wird in der Informationstechnik eingesetzt, um Textinhalte aus gedruckten oder digital reasterisierten Medien zu extrahieren. Dieses Verfahren kann für diverse Anwendungsgebiete genutzt werden, wie beispielsweise für Handschrifterkennung oder für das Ablesen von Nummernschildern eines Autos \mcite{asif2014overview}. Auf dem Markt gibt es dafür bereits viele kommerzielle Komplettlösungen wie "IronOCR", "Google Cloud Vision", "Amazon Textract" oder "Microsoft Azure Computer Vision", die oftmals sehr gute Ergebnisse erzielen und sich gut in bestehende Prozesse oder Anwendungen integrieren lassen \mcite{the_old_bailey_and_ocr, cc_platforms_comparison}.
|
||||
|
||||
Heutige Texterkennungssysteme arbeiten oft mit neuralen Netzwerken sowie fortgeschrittenen Bildverarbeitungsalgorithmen, um Text in Bilddateien zu erkennen und zu extrahieren. Während es zahlreiche wissenschaftliche Werke zur grundlegenden Funktionsweise von optischen Texterkennungswerkzeugen gibt (siehe beispielsweise \bibentry{eikvil1993optical} oder \bibentry{islam2017survey}), werden die genauen Schritte zur richtigen Vorbereitung der Bilddaten -- besonders in Bezug auf Screenshots -- oftmmals nur oberflächlich behandelt.
|
||||
Heutige Texterkennungssysteme arbeiten oft mit neuralen Netzwerken sowie fortgeschrittenen Bildverarbeitungsalgorithmen, um Text in Bilddateien zu erkennen und zu extrahieren. Während es zahlreiche wissenschaftliche Werke zur grundlegenden Funktionsweise von optischen Texterkennungswerkzeugen gibt (siehe beispielsweise \textcite{eikvil1993optical, islam2017survey}), werden die genauen Schritte zur richtigen Vorbereitung der Bilddaten -- besonders in Bezug auf Screenshots -- oftmmals nur oberflächlich behandelt.
|
||||
|
||||
\subsection{Filterung der Ergebnisdaten}
|
||||
|
||||
Das Themengebiet des Natural Language Processing beschäftigt sich mit der Interaktion zwischen menschlicher Sprache und Computern. Techniken aus der Informatik, Linguistik und dem maschinellen Lernen werden kombiniert, um mit menschlicher Sprache umzugehen und beispielsweise Textanalyse, Übersetzungen, Spracherkennung oder Dialogsysteme möglich zu machen \mcite{chowdhary2020natural}. Durch die große Aufmerksamkeit und die vielseitige Nutzung der Technologien -- angefanen von automatischer Rechtschreibkontrolle bis hin zu digitalen Sprachassistenten -- sowie dem Aufkommen von neuronalen Netzwerken wurden in diesem Forschungsgebiet in den letzten Jahren immer wieder Fortschritte erzielt \mcite{kalyanathaya2019advances} \mcite{10.1145/219717.219778}.
|
||||
Das Themengebiet des Natural Language Processing beschäftigt sich mit der Interaktion zwischen menschlicher Sprache und Computern. Techniken aus der Informatik, Linguistik und dem maschinellen Lernen werden kombiniert, um mit menschlicher Sprache umzugehen und beispielsweise Textanalyse, Übersetzungen, Spracherkennung oder Dialogsysteme möglich zu machen \mcite{chowdhary2020natural}. Durch die große Aufmerksamkeit und die vielseitige Nutzung der Technologien -- angefanen von automatischer Rechtschreibkontrolle bis hin zu digitalen Sprachassistenten -- sowie dem Aufkommen von neuronalen Netzwerken wurden in diesem Forschungsgebiet in den letzten Jahren immer wieder Fortschritte erzielt \mcite{kalyanathaya2019advances, 10.1145/219717.219778}.
|
||||
|
||||
Dadurch gibt es zahlreiche wissenschaftliche Ressourcen, die als Grundlage für die in dieser Bachelorarbeit verwendeten Vorgehensweise zur Interpretation und Extraktion relevanter Schlagworte aus den erkannten Freitextdaten dienen.
|
||||
@@ -4,9 +4,9 @@
|
||||
\subsection{Texterkennungssystem}
|
||||
\label{texterkennungssystem}
|
||||
|
||||
Die Nutzung der in \autoref{einleitung} erwähnten Anwendungen \bzw Dienstleistungen ist kostenpflichtig und die genaue innere Vorgehensweise dieser Programme ist nicht öffentlich bekannt \mcite{textract_pricing}\mcite{gcv_pricing}\mcite{azurevision_pricing}.
|
||||
Die Nutzung der in \autoref{einleitung} erwähnten Anwendungen \bzw Dienstleistungen ist kostenpflichtig und die genaue innere Vorgehensweise dieser Programme ist nicht öffentlich bekannt \mcite{textract_pricing, gcv_pricing, azurevision_pricing}.
|
||||
|
||||
Aufgrund dieser Tatsachen ist die Wahl des Texterkennungssystems für die prototypische Implementierung dieser Bachelorarbeit auf die seit 2005 unter der Freie-Software-Lizenz "Apache 2.0" veröffentlichten "Tesseract Open Source OCR Engine" (kurz: Tesseract) gefallen \mcite{Smith2007}. Diese basiert seit der Major-Version 4 auf einem neuronalen Netz, durch welches mithilfe von sprachspezifischen Trainingsdaten Texte in Bildern erkannt werden können. Außerdem stellt sie mit mittlerweile über 50.000 Sternen auf der Repository-Hosting-Plattform GitHub eines der beliebtesten Texterkennungssysteme dar \mcite{tessdoc} \mcite{tessrepo}.
|
||||
Aufgrund dieser Tatsachen ist die Wahl des Texterkennungssystems für die prototypische Implementierung dieser Bachelorarbeit auf die seit 2005 unter der Freie-Software-Lizenz "Apache 2.0" veröffentlichten "Tesseract Open Source OCR Engine" (kurz: Tesseract) gefallen \mcite{Smith2007}. Diese basiert seit der Major-Version 4 auf einem neuronalen Netz, durch welches mithilfe von sprachspezifischen Trainingsdaten Texte in Bildern erkannt werden können. Außerdem stellt sie mit mittlerweile über 50.000 Sternen auf der Repository-Hosting-Plattform GitHub eines der beliebtesten Texterkennungssysteme dar \mcite{tessdoc}{tessrepo}.
|
||||
|
||||
\subsection{Bildbearbeitungswerkzeug}
|
||||
\label{bildbearbeitungswerkzeug}
|
||||
|
||||
+249
-292
@@ -1,364 +1,321 @@
|
||||
% todo add copa data image source
|
||||
% @image{CocaCola1940,
|
||||
% author={Wolcott, Marion Post},
|
||||
% title={Natchez, Miss.},
|
||||
% note={Library of Congress Prints and Photographs Division Washington, Farm Security Administration/Office of War Information Color Photographs},
|
||||
% date={1940-08},
|
||||
% url={https://www.loc.gov/pictures/item/2017877479/},
|
||||
% langid={english}
|
||||
% }
|
||||
|
||||
@book{2007Crs,
|
||||
isbn = {9780471415701},
|
||||
year = {2007},
|
||||
title = {Character recognition systems : a guide for students and practioners},
|
||||
language = {eng},
|
||||
author = {Cheriet, Mohamed},
|
||||
keywords = {Optical character recognition devices},
|
||||
url = {https://permalink.obvsg.at/fho/AC06408992},
|
||||
urldate = {2023-06-12}
|
||||
title = {Character recognition systems : a guide for students and practioners},
|
||||
author = {Cheriet, Mohamed},
|
||||
year = 2007,
|
||||
isbn = 9780471415701,
|
||||
url = {https://permalink.obvsg.at/fho/AC06408992},
|
||||
urldate = {2023-06-12},
|
||||
language = {eng},
|
||||
keywords = {Optical character recognition devices}
|
||||
}
|
||||
|
||||
@book{2022Scas,
|
||||
series = {Advances in Intelligent Systems and Computing ;},
|
||||
isbn = {981-16-7088-9},
|
||||
year = {2022},
|
||||
title = {Soft computing and signal processing : : proceedings of 4th ICSCSP 2021},
|
||||
language = {eng},
|
||||
author = {Reddy, V. Sivakumar},
|
||||
keywords = {Signal processing ; Congresses},
|
||||
url = {https://search-fho.obvsg.at/permalink/f/19351jn/FHO_alma5134174850004527},
|
||||
urldate = {2023-06-12}
|
||||
title = {Soft computing and signal processing : : proceedings of 4th ICSCSP 2021},
|
||||
author = {Reddy, V. Sivakumar},
|
||||
year = 2022,
|
||||
series = {Advances in Intelligent Systems and Computing ;},
|
||||
isbn = {981-16-7088-9},
|
||||
url = {https://search-fho.obvsg.at/permalink/f/19351jn/FHO_alma5134174850004527},
|
||||
urldate = {2023-06-12},
|
||||
language = {eng},
|
||||
keywords = {Signal processing ; Congresses}
|
||||
}
|
||||
|
||||
@book{BlahaMichael2013U:dm,
|
||||
isbn = {9781935504511},
|
||||
year = {2013},
|
||||
title = {UML : database modeling workbook},
|
||||
edition = {1. print..},
|
||||
language = {eng},
|
||||
author = {Blaha, Michael},
|
||||
url = {https://permalink.obvsg.at/fho/AC11105171},
|
||||
urldate = {2023-06-12}
|
||||
title = {UML : database modeling workbook},
|
||||
author = {Blaha, Michael},
|
||||
year = 2013,
|
||||
isbn = 9781935504511,
|
||||
url = {https://permalink.obvsg.at/fho/AC11105171},
|
||||
urldate = {2023-06-12},
|
||||
edition = {1. print..},
|
||||
language = {eng}
|
||||
}
|
||||
|
||||
@book{BoochGrady1999Tuml,
|
||||
series = {Addison-Wesley object technology series},
|
||||
isbn = {0201571684},
|
||||
year = {1999},
|
||||
title = {The unified modeling language user guide : UML},
|
||||
edition = {3. print..},
|
||||
language = {eng},
|
||||
author = {Booch, Grady},
|
||||
keywords = {Computer software ; Development},
|
||||
url = {https://permalink.obvsg.at/fho/AC08768402},
|
||||
urldate = {2023-06-12}
|
||||
title = {The unified modeling language user guide : UML},
|
||||
author = {Booch, Grady},
|
||||
year = 1999,
|
||||
series = {Addison-Wesley object technology series},
|
||||
isbn = {0201571684},
|
||||
url = {https://permalink.obvsg.at/fho/AC08768402},
|
||||
urldate = {2023-06-12},
|
||||
edition = {3. print..},
|
||||
language = {eng},
|
||||
keywords = {Computer software ; Development}
|
||||
}
|
||||
|
||||
@book{ChaudhuriArindam2017OCRS,
|
||||
series = {Studies in Fuzziness and Soft Computing 352},
|
||||
isbn = {9783319502526},
|
||||
year = {2017},
|
||||
title = {Optical Character Recognition Systems for Different Languages with Soft Computing},
|
||||
language = {eng},
|
||||
author = {Chaudhuri, Arindam},
|
||||
keywords = {Engineering},
|
||||
url = {https://permalink.obvsg.at/fho/AC12323924},
|
||||
urldate = {2023-06-12}
|
||||
title = {Optical Character Recognition Systems for Different Languages with Soft Computing},
|
||||
author = {Chaudhuri, Arindam},
|
||||
year = 2017,
|
||||
series = {Studies in Fuzziness and Soft Computing 352},
|
||||
isbn = 9783319502526,
|
||||
url = {https://permalink.obvsg.at/fho/AC12323924},
|
||||
urldate = {2023-06-12},
|
||||
language = {eng},
|
||||
keywords = {Engineering}
|
||||
}
|
||||
|
||||
@book{DingXiaoqing2012AiCR,
|
||||
abstract = {This book presents advances in character recognition, and it consists of 12 chapters that cover wide range of topics on different aspects of character recognition. Hopefully, this book will serve as a reference source for academic research, for professionals working in the character recognition field and for all interested in the subject.},
|
||||
publisher = {IntechOpen},
|
||||
isbn = {953-51-5669-1},
|
||||
year = {2012},
|
||||
title = {Advances in Character Recognition},
|
||||
language = {eng},
|
||||
author = {Ding, Xiaoqing},
|
||||
keywords = {Optical character recognition},
|
||||
urldate = {2023-06-12},
|
||||
doi = {10.5772/2575},
|
||||
url = {https://www.intechopen.com/books/2182}
|
||||
title = {Advances in Character Recognition},
|
||||
author = {Ding, Xiaoqing},
|
||||
year = 2012,
|
||||
publisher = {IntechOpen},
|
||||
doi = {10.5772/2575},
|
||||
isbn = {953-51-5669-1},
|
||||
url = {https://www.intechopen.com/books/2182},
|
||||
urldate = {2023-06-12},
|
||||
abstract = {This book presents advances in character recognition, and it consists of 12 chapters that cover wide range of topics on different aspects of character recognition. Hopefully, this book will serve as a reference source for academic research, for professionals working in the character recognition field and for all interested in the subject.},
|
||||
language = {eng},
|
||||
keywords = {Optical character recognition}
|
||||
}
|
||||
|
||||
@book{HayDavidC2011U,
|
||||
isbn = {1935504193},
|
||||
year = {2011},
|
||||
title = {UML \& data modeling : a reconciliation},
|
||||
language = {eng},
|
||||
author = {Hay, David C},
|
||||
keywords = {Data structures (Computer science)},
|
||||
url = {https://permalink.obvsg.at/fho/YC00337386},
|
||||
urldate = {2023-06-12}
|
||||
title = {UML \& data modeling : a reconciliation},
|
||||
author = {Hay, David C},
|
||||
year = 2011,
|
||||
isbn = 1935504193,
|
||||
url = {https://permalink.obvsg.at/fho/YC00337386},
|
||||
urldate = {2023-06-12},
|
||||
language = {eng},
|
||||
keywords = {Data structures (Computer science)}
|
||||
}
|
||||
|
||||
@inproceedings{Hyyr2003PracticalMF,
|
||||
title = {Practical Methods for Approximate String Matching},
|
||||
author = {Heikki Hyyr{\"o}},
|
||||
year = {2003},
|
||||
url = {https://www.semanticscholar.org/paper/Practical-Methods-for-Approximate-String-Matching-Hyyr%C3%B6/3b2227ae166cbe90b20408da3f2feb75f95afd9c},
|
||||
urldate = {2023-06-12}
|
||||
title = {Practical Methods for Approximate String Matching},
|
||||
author = {Heikki Hyyr{\"o}},
|
||||
year = 2003,
|
||||
url = {https://www.semanticscholar.org/paper/Practical-Methods-for-Approximate-String-Matching-Hyyr%C3%B6/3b2227ae166cbe90b20408da3f2feb75f95afd9c},
|
||||
urldate = {2023-06-12}
|
||||
}
|
||||
|
||||
@book{KemperAlfons2015D:eE,
|
||||
series = {De-Gruyter-Oldenbourg-Studium},
|
||||
isbn = {9783110443752},
|
||||
year = {2015},
|
||||
title = {Datenbanksysteme : eine Einführung},
|
||||
edition = {10., aktualisierte u. erw. Aufl..},
|
||||
language = {ger},
|
||||
author = {Kemper, Alfons},
|
||||
keywords = {Datenbanksystem},
|
||||
url = {https://permalink.obvsg.at/fho/AC12661940},
|
||||
urldate = {2023-06-12}
|
||||
title = {Datenbanksysteme : eine Einführung},
|
||||
author = {Kemper, Alfons},
|
||||
year = 2015,
|
||||
series = {De-Gruyter-Oldenbourg-Studium},
|
||||
isbn = 9783110443752,
|
||||
url = {https://permalink.obvsg.at/fho/AC12661940},
|
||||
urldate = {2023-06-12},
|
||||
edition = {10., aktualisierte u. erw. Aufl..},
|
||||
language = {ger},
|
||||
keywords = {Datenbanksystem}
|
||||
}
|
||||
|
||||
@article{Navarro2000,
|
||||
author = {Navarro, Gonzalo},
|
||||
year = {2000},
|
||||
month = {04},
|
||||
title = {A Guided Tour to Approximate String Matching},
|
||||
volume = {33},
|
||||
journal = {ACM Computing Surveys},
|
||||
doi = {10.1145/375360.375365},
|
||||
url = {https://www.researchgate.net/publication/2375410_A_Guided_Tour_to_Approximate_String_Matching},
|
||||
urldate = {2023-06-12}
|
||||
title = {A Guided Tour to Approximate String Matching},
|
||||
author = {Navarro, Gonzalo},
|
||||
year = 2000,
|
||||
month = {04},
|
||||
journal = {ACM Computing Surveys},
|
||||
volume = 33,
|
||||
doi = {10.1145/375360.375365},
|
||||
url = {https://www.researchgate.net/publication/2375410_A_Guided_Tour_to_Approximate_String_Matching},
|
||||
urldate = {2023-06-12}
|
||||
}
|
||||
|
||||
@book{SaakeGunter2011D-I:,
|
||||
isbn = {9783826691560},
|
||||
year = {2011},
|
||||
title = {Datenbanken - Implementierungstechniken : [Architekturprinzipien, Datenstrukturen und Algorithmen, Transaktionsverwaltung und Recovery]},
|
||||
edition = {3. Aufl..},
|
||||
language = {ger},
|
||||
author = {Saake, Gunter},
|
||||
keywords = {Datenbanksystem},
|
||||
url = {https://permalink.obvsg.at/fho/AC08815950},
|
||||
urldate = {2023-06-12}
|
||||
title = {Datenbanken - Implementierungstechniken : [Architekturprinzipien, Datenstrukturen und Algorithmen, Transaktionsverwaltung und Recovery]},
|
||||
author = {Saake, Gunter},
|
||||
year = 2011,
|
||||
isbn = 9783826691560,
|
||||
url = {https://permalink.obvsg.at/fho/AC08815950},
|
||||
urldate = {2023-06-12},
|
||||
edition = {3. Aufl..},
|
||||
language = {ger},
|
||||
keywords = {Datenbanksystem}
|
||||
}
|
||||
@inproceedings{Smith2007,
|
||||
author = {Smith R.},
|
||||
title = {An Overview of the Tesseract OCR Engine},
|
||||
date = {2007},
|
||||
langid = {ngerman},
|
||||
url = {https://ieeexplore.ieee.org/document/4376991},
|
||||
urldate = {2023-06-12}
|
||||
title = {An Overview of the Tesseract OCR Engine},
|
||||
author = {Smith R.},
|
||||
url = {https://ieeexplore.ieee.org/document/4376991},
|
||||
urldate = {2023-06-12},
|
||||
date = 2007,
|
||||
langid = {ngerman}
|
||||
}
|
||||
|
||||
@online{tessdoc,
|
||||
title = {Tesseract Documentation},
|
||||
url = {https://tesseract-ocr.github.io/},
|
||||
date = {2023-05-23},
|
||||
urldate = {2023-06-12},
|
||||
language = {eng}
|
||||
title = {Tesseract Documentation},
|
||||
url = {https://tesseract-ocr.github.io/},
|
||||
urldate = {2023-06-12},
|
||||
date = {2023-05-23},
|
||||
language = {eng}
|
||||
}
|
||||
|
||||
@online{imagemagick,
|
||||
title = {ImageMagick Homepage},
|
||||
url = {https://www.imagemagick.org/},
|
||||
date = {2023-05-23},
|
||||
urldate = {2023-06-12},
|
||||
language = {eng}
|
||||
title = {ImageMagick Homepage},
|
||||
url = {https://www.imagemagick.org/},
|
||||
urldate = {2023-06-12},
|
||||
date = {2023-05-23},
|
||||
language = {eng}
|
||||
}
|
||||
|
||||
@online{textract_pricing,
|
||||
title = {Amazon Textract - Pricing},
|
||||
url = {https://aws.amazon.com/textract/pricing/},
|
||||
date = {2023-05-23},
|
||||
urldate = {2023-06-12},
|
||||
language = {eng}
|
||||
title = {Amazon Textract - Pricing},
|
||||
url = {https://aws.amazon.com/textract/pricing/},
|
||||
urldate = {2023-06-12},
|
||||
date = {2023-05-23},
|
||||
language = {eng}
|
||||
}
|
||||
|
||||
@online{gcv_pricing,
|
||||
title = {Google Cloud Vision - Pricing},
|
||||
url = {https://cloud.google.com/vision/pricing},
|
||||
date = {2023-05-23},
|
||||
urldate = {2023-06-12},
|
||||
language = {eng}
|
||||
title = {Google Cloud Vision - Pricing},
|
||||
url = {https://cloud.google.com/vision/pricing},
|
||||
urldate = {2023-06-12},
|
||||
date = {2023-05-23},
|
||||
language = {eng}
|
||||
}
|
||||
|
||||
@online{azurevision_pricing,
|
||||
title = {Azure AI Vision - Pricing},
|
||||
url = {https://azure.microsoft.com/en-gb/pricing/details/cognitive-services/computer-vision/},
|
||||
date = {2023-05-23},
|
||||
urldate = {2023-06-12},
|
||||
language = {eng}
|
||||
title = {Azure AI Vision - Pricing},
|
||||
url = {https://azure.microsoft.com/en-gb/pricing/details/cognitive-services/computer-vision/},
|
||||
urldate = {2023-06-12},
|
||||
date = {2023-05-23},
|
||||
language = {eng}
|
||||
}
|
||||
|
||||
@online{tessrepo,
|
||||
title = {Tesseract Repository},
|
||||
url = {https://github.com/tesseract-ocr/tesseract},
|
||||
date = {2023-05-23},
|
||||
urldate = {2024-01-04},
|
||||
language = {eng}
|
||||
title = {Tesseract Repository},
|
||||
url = {https://github.com/tesseract-ocr/tesseract},
|
||||
urldate = {2024-01-04},
|
||||
date = {2023-05-23},
|
||||
language = {eng}
|
||||
}
|
||||
|
||||
@online{todo,
|
||||
title = {TODO: MISSING SOURCE},
|
||||
url = {https://example.com/todo},
|
||||
date = {2023-05-23},
|
||||
urldate = {2024-01-04},
|
||||
language = {eng}
|
||||
title = {TODO: MISSING SOURCE},
|
||||
url = {https://example.com/todo},
|
||||
urldate = {2024-01-04},
|
||||
date = {2023-05-23},
|
||||
language = {eng}
|
||||
}
|
||||
|
||||
|
||||
@article{asif2014overview,
|
||||
title={An overview and applications of optical character recognition},
|
||||
author={Asif, AMAM and Hannan, Shaikh Abdul and Perwej, Yusuf and Vithalrao, Mane Arjun},
|
||||
journal={Int. J. Adv. Res. Sci. Eng},
|
||||
volume={3},
|
||||
number={7},
|
||||
pages={261--274},
|
||||
year={2014}
|
||||
title = {An overview and applications of optical character recognition},
|
||||
author = {Asif, AMAM and Hannan, Shaikh Abdul and Perwej, Yusuf and Vithalrao, Mane Arjun},
|
||||
year = 2014,
|
||||
journal = {Int. J. Adv. Res. Sci. Eng},
|
||||
volume = 3,
|
||||
number = 7,
|
||||
pages = {261--274}
|
||||
}
|
||||
|
||||
@inbook{cc_platforms_comparison,
|
||||
author = {Gupta, Urvashi and Sharma, Rohit},
|
||||
year = {2023},
|
||||
month = {09},
|
||||
pages = {67-78},
|
||||
title = {“Comparison of Different Cloud Computing Platforms for Data Analytics”},
|
||||
isbn = {978-981-99-3715-8},
|
||||
doi = {10.1007/978-981-99-3716-5_7}
|
||||
title = {“Comparison of Different Cloud Computing Platforms for Data Analytics”},
|
||||
author = {Gupta, Urvashi and Sharma, Rohit},
|
||||
year = 2023,
|
||||
month = {09},
|
||||
pages = {67--78},
|
||||
doi = {10.1007/978-981-99-3716-5_7},
|
||||
isbn = {978-981-99-3715-8}
|
||||
}
|
||||
|
||||
@online{tessdoc,
|
||||
title = {Tesseract Documentation},
|
||||
url = {https://tesseract-ocr.github.io/},
|
||||
date = {2023-05-23},
|
||||
urldate = {2023-06-12},
|
||||
language = {eng}
|
||||
title = {Tesseract Documentation},
|
||||
url = {https://tesseract-ocr.github.io/},
|
||||
urldate = {2023-06-12},
|
||||
date = {2023-05-23},
|
||||
language = {eng}
|
||||
}
|
||||
|
||||
@inproceedings{the_old_bailey_and_ocr,
|
||||
title = "The Old Bailey and OCR: Benchmarking AWS, Azure, and GCP with 180,000 Page Images",
|
||||
keywords = "Amazon Web Services, Google Cloud Platform, Historical Documents, Microsoft Azure, Old Bailey, Optical Character Recognition",
|
||||
author = "William Ughetta and Kernighan, {Brian W.}",
|
||||
year = "2020",
|
||||
month = sep,
|
||||
day = "29",
|
||||
doi = "10.1145/3395027.3419595",
|
||||
language = "English (US)",
|
||||
series = "Proceedings of the ACM Symposium on Document Engineering, DocEng 2020",
|
||||
publisher = "Association for Computing Machinery, Inc",
|
||||
booktitle = "Proceedings of the ACM Symposium on Document Engineering, DocEng 2020",
|
||||
title = {The Old Bailey and OCR: Benchmarking AWS, Azure, and GCP with 180,000 Page Images},
|
||||
author = {William Ughetta and Kernighan, {Brian W.}},
|
||||
year = 2020,
|
||||
month = sep,
|
||||
day = 29,
|
||||
booktitle = {Proceedings of the ACM Symposium on Document Engineering, DocEng 2020},
|
||||
publisher = {Association for Computing Machinery, Inc},
|
||||
series = {Proceedings of the ACM Symposium on Document Engineering, DocEng 2020},
|
||||
doi = {10.1145/3395027.3419595},
|
||||
keywords = {Amazon Web Services, Google Cloud Platform, Historical Documents, Microsoft Azure, Old Bailey, Optical Character Recognition},
|
||||
language = {English (US)}
|
||||
}
|
||||
|
||||
@article{eikvil1993optical,
|
||||
title={Optical character recognition},
|
||||
author={Eikvil, Line},
|
||||
journal={citeseer. ist. psu. edu/142042. html},
|
||||
volume={26},
|
||||
year={1993}
|
||||
title = {Optical character recognition},
|
||||
author = {Eikvil, Line},
|
||||
year = 1993,
|
||||
journal = {citeseer. ist. psu. edu/142042. html},
|
||||
volume = 26
|
||||
}
|
||||
@article{islam2017survey,
|
||||
title={A survey on optical character recognition system},
|
||||
author={Islam, Noman and Islam, Zeeshan and Noor, Nazia},
|
||||
journal={arXiv preprint arXiv:1710.05703},
|
||||
year={2017}
|
||||
title = {A survey on optical character recognition system},
|
||||
author = {Islam, Noman and Islam, Zeeshan and Noor, Nazia},
|
||||
year = 2017,
|
||||
journal = {arXiv preprint arXiv:1710.05703}
|
||||
}
|
||||
|
||||
@article{chowdhary2020natural,
|
||||
title={Natural language processing},
|
||||
author={Chowdhary, KR1442 and Chowdhary, KR},
|
||||
journal={Fundamentals of artificial intelligence},
|
||||
pages={603--649},
|
||||
year={2020},
|
||||
publisher={Springer}
|
||||
title = {Natural language processing},
|
||||
author = {Chowdhary, KR1442 and Chowdhary, KR},
|
||||
year = 2020,
|
||||
journal = {Fundamentals of artificial intelligence},
|
||||
publisher = {Springer},
|
||||
pages = {603--649}
|
||||
}
|
||||
@article{10.1145/219717.219778,
|
||||
author = {Church, Kenneth W. and Rau, Lisa F.},
|
||||
title = {Commercial Applications of Natural Language Processing},
|
||||
year = {1995},
|
||||
issue_date = {Nov. 1995},
|
||||
publisher = {Association for Computing Machinery},
|
||||
address = {New York, NY, USA},
|
||||
volume = {38},
|
||||
number = {11},
|
||||
issn = {0001-0782},
|
||||
url = {https://doi.org/10.1145/219717.219778},
|
||||
doi = {10.1145/219717.219778},
|
||||
journal = {Commun. ACM},
|
||||
month = {nov},
|
||||
pages = {71–79},
|
||||
numpages = {9}
|
||||
title = {Commercial Applications of Natural Language Processing},
|
||||
author = {Church, Kenneth W. and Rau, Lisa F.},
|
||||
year = 1995,
|
||||
month = {nov},
|
||||
journal = {Commun. ACM},
|
||||
publisher = {Association for Computing Machinery},
|
||||
address = {New York, NY, USA},
|
||||
volume = 38,
|
||||
number = 11,
|
||||
pages = {71–79},
|
||||
doi = {10.1145/219717.219778},
|
||||
issn = {0001-0782},
|
||||
url = {https://doi.org/10.1145/219717.219778},
|
||||
issue_date = {Nov. 1995},
|
||||
numpages = 9
|
||||
}
|
||||
|
||||
@article{kalyanathaya2019advances,
|
||||
title={Advances in natural language processing--a survey of current research trends, development tools and industry applications},
|
||||
author={Kalyanathaya, Krishna Prakash and Akila, D and Rajesh, P},
|
||||
journal={International Journal of Recent Technology and Engineering},
|
||||
volume={7},
|
||||
number={5C},
|
||||
pages={199--202},
|
||||
year={2019}
|
||||
title = {Advances in natural language processing--a survey of current research trends, development tools and industry applications},
|
||||
author = {Kalyanathaya, Krishna Prakash and Akila, D and Rajesh, P},
|
||||
year = 2019,
|
||||
journal = {International Journal of Recent Technology and Engineering},
|
||||
volume = 7,
|
||||
number = {5C},
|
||||
pages = {199--202}
|
||||
}
|
||||
|
||||
@inproceedings{tong1996statistical,
|
||||
title={A statistical approach to automatic OCR error correction in context},
|
||||
author={Tong, Xiang and Evans, David A},
|
||||
booktitle={Fourth workshop on very large corpora},
|
||||
year={1996}
|
||||
title = {A statistical approach to automatic OCR error correction in context},
|
||||
author = {Tong, Xiang and Evans, David A},
|
||||
year = 1996,
|
||||
booktitle = {Fourth workshop on very large corpora}
|
||||
}
|
||||
|
||||
@inproceedings{karpinski2018metrics,
|
||||
title={Metrics for complete evaluation of ocr performance},
|
||||
author={Karpinski, Romain and Lohani, Devashish and Belaid, Abdel},
|
||||
booktitle={IPCV'18-The 22nd Int'l Conf on Image Processing, Computer Vision, \& Pattern Recognition},
|
||||
year={2018}
|
||||
title = {Metrics for complete evaluation of ocr performance},
|
||||
author = {Karpinski, Romain and Lohani, Devashish and Belaid, Abdel},
|
||||
year = 2018,
|
||||
booktitle = {IPCV'18-The 22nd Int'l Conf on Image Processing, Computer Vision, \& Pattern Recognition}
|
||||
}
|
||||
|
||||
@article{approximate_string_matching,
|
||||
author = {Navarro, Gonzalo},
|
||||
year = {2000},
|
||||
month = {04},
|
||||
pages = {},
|
||||
title = {A Guided Tour to Approximate String Matching},
|
||||
volume = {33},
|
||||
journal = {ACM Computing Surveys},
|
||||
doi = {10.1145/375360.375365}
|
||||
title = {A Guided Tour to Approximate String Matching},
|
||||
author = {Navarro, Gonzalo},
|
||||
year = 2000,
|
||||
month = {04},
|
||||
journal = {ACM Computing Surveys},
|
||||
volume = 33,
|
||||
pages = {},
|
||||
doi = {10.1145/375360.375365}
|
||||
}
|
||||
|
||||
@inproceedings{levenshtein1966binary,
|
||||
title={Binary codes capable of correcting deletions, insertions, and reversals},
|
||||
author={ and others}
|
||||
title = {Binary codes capable of correcting deletions, insertions, and reversals},
|
||||
author = {and others}
|
||||
}
|
||||
|
||||
@inproceedings{wang2003word,
|
||||
title={Is word error rate a good indicator for spoken language understanding accuracy},
|
||||
author={Wang, Ye-Yi and Acero, Alex and Chelba, Ciprian},
|
||||
booktitle={2003 IEEE workshop on automatic speech recognition and understanding (IEEE Cat. No. 03EX721)},
|
||||
pages={577--582},
|
||||
year={2003},
|
||||
organization={IEEE}
|
||||
title = {Is word error rate a good indicator for spoken language understanding accuracy},
|
||||
author = {Wang, Ye-Yi and Acero, Alex and Chelba, Ciprian},
|
||||
year = 2003,
|
||||
booktitle = {2003 IEEE workshop on automatic speech recognition and understanding (IEEE Cat. No. 03EX721)},
|
||||
pages = {577--582},
|
||||
organization = {IEEE}
|
||||
}
|
||||
|
||||
@inproceedings{park2008empirical,
|
||||
title={An empirical analysis of word error rate and keyword error rate.},
|
||||
author={Park, Youngja and Patwardhan, Siddharth and Visweswariah, Karthik and Gates, Stephen C},
|
||||
booktitle={Interspeech},
|
||||
volume={2008},
|
||||
pages={2070--2073},
|
||||
year={2008}
|
||||
title = {An empirical analysis of word error rate and keyword error rate.},
|
||||
author = {Park, Youngja and Patwardhan, Siddharth and Visweswariah, Karthik and Gates, Stephen C},
|
||||
year = 2008,
|
||||
booktitle = {Interspeech},
|
||||
volume = 2008,
|
||||
pages = {2070--2073}
|
||||
}
|
||||
|
||||
@article{sporici2020improving,
|
||||
title={Improving the accuracy of Tesseract 4.0 OCR engine using convolution-based preprocessing},
|
||||
author={Sporici, Dan and Cușnir, Elena and Boiangiu, Costin-Anton},
|
||||
journal={Symmetry},
|
||||
volume={12},
|
||||
number={5},
|
||||
pages={715},
|
||||
year={2020},
|
||||
publisher={MDPI}
|
||||
title = {Improving the accuracy of Tesseract 4.0 OCR engine using convolution-based preprocessing},
|
||||
author = {Sporici, Dan and Cușnir, Elena and Boiangiu, Costin-Anton},
|
||||
year = 2020,
|
||||
journal = {Symmetry},
|
||||
publisher = {MDPI},
|
||||
volume = 12,
|
||||
number = 5,
|
||||
pages = 715
|
||||
}
|
||||
|
||||
@article{mursari2021effectiveness,
|
||||
title={The effectiveness of image preprocessing on digital handwritten scripts recognition with the implementation of OCR Tesseract},
|
||||
author={Mursari, Lily Rojabiyati and Wibowo, Antoni},
|
||||
journal={Computer Engineering and Applications Journal},
|
||||
volume={10},
|
||||
number={3},
|
||||
pages={177--186},
|
||||
year={2021}
|
||||
title = {The effectiveness of image preprocessing on digital handwritten scripts recognition with the implementation of OCR Tesseract},
|
||||
author = {Mursari, Lily Rojabiyati and Wibowo, Antoni},
|
||||
year = 2021,
|
||||
journal = {Computer Engineering and Applications Journal},
|
||||
volume = 10,
|
||||
number = 3,
|
||||
pages = {177--186}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user