Improving OCR Accuracy on Early Printed Books by combining Pretraining, Voting, and Active Learning [PDF]
, 2018 We combine three methods which significantly improve the OCR accuracy of OCR models trained on early printed books: (1) The pretraining method utilizes the information stored in already existing models trained on a variety of typesets (mixed models ...
Puppe, Frank +3 more
core +3 more sources
Corpus-based technique for improving Arabic OCR system
Indonesian Journal of Electrical Engineering and Computer Science, 2021 <p><span>An optical character recognition (OCR) refers to a process of converting the text document images into editable and searchable text. OCR process poses several challenges in particular in the Arabic language due to it has caused a high percentage of errors.
Ahmed Hussain Aliwy, Basheer Al-Sadawi
openaire +2 more sources
Design and Development of Sindhi Text Based CAPTCHAs for Regional Websites
Sukkur IBA Journal of Emerging Technologies, 2021 Bots are created to use the resources maliciously on World Wide Web. The misuse of the resources could be prevented by employing CAPTCHAs. Several types of CAPTCHAs are being used against the bots (robot) attacks but text-based CAPTCHA type is the most ...
Asadullah Kehar +8 more
doaj +1 more source
Unconstrained Scene Text and Video Text Recognition for Arabic Script
, 2017 Building robust recognizers for Arabic has always been challenging. We demonstrate the effectiveness of an end-to-end trainable CNN-RNN hybrid architecture in recognizing Arabic text in videos and natural scenes.
Jain, Mohit +2 more
core +1 more source
Managing complexity in a distributed digital library [PDF]
, 1999 As the capabilities of distributed digital libraries increase, managing organizational and software complexity becomes a key issue. How can collections and indexes be updated without impacting queries currently in progress?
Apperley, Mark +5 more
core +2 more sources
An OCR System for Arabic Calligraphy Documents
International Journal of Engineering & Technology, 2019 This paper introduces to get good accuracy for Arabic OCRresultsforolddocumentsandcalligraphydocuments.While our developed system has provided accurate results for modern Arabic documents, when we used that system for old Arabic documents, we got a steep degradation in performance, (around 25% accuracy compared with 85% for modern Arabic documents ...
Hassanin Al-Barhamtoshy +5 more
openaire +1 more source
A Comparative study of Arabic handwritten characters invariant feature [PDF]
, 2011 This paper is practically interested in the unchangeable feature of Arabic handwritten character. It presents results of comparative study achieved on certain features extraction techniques of handwritten character, based on Hough transform, Fourier ...
Hassen, Hamdi, khemakhem, Maher
core +4 more sources
Optical Character Recognition for Quranic Image Similarity Matching
IEEE Access, 2018 The detection and recognition and then conversion of the characters in an image into a text are called optical character recognition (OCR). A distinctive-type of OCR is used to process Arabic characters, namely, Arabic OCR.
Faiz Alotaibi +5 more
doaj +1 more source
Persian Optical Character Recognition Using Deep Bidirectional Long Short-Term Memory
Applied Sciences, 2022 Optical Character Recognition (OCR) is a system of converting images, including text,into editable text and is applied to various languages such as English, Arabic, and Persian.
Zohreh Khosrobeigi +3 more
doaj +1 more source
Towards a flexible open-source software library for multi-layered scholarly textual studies: An Arabic case study dealing with semi-automatic language processing [PDF]
, 2014 This paper presents both the general model and a case study of the Computational and Collaborative Philology Library (CoPhiLib), an ongoing initiative underway at the Institute for Computational Linguistics (ILC) of the National Research Council (CNR ...
Del Grosso, Angelo Mario, NAHLI, OUAFAE
core +1 more source