Results 71 to 80 of about 226,611 (194)

copninich/TH-National-Document-OCR: First releases of THND OCR

, 2021
Tesseract OCR Tools for reading Thai National Document using TH Sarabun National Font for training and finetune.
Kampanart Chaimooltan
core   +1 more source

Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

Journal of Imaging, 2018
Recognizing texts in video is more complex than in other environments such as scanned documents. Video texts appear in various colors, unknown fonts and sizes, often affected by compression artifacts and low quality. In contrast to Latin texts, there are
Oussama Zayene, Sameh Masmoudi Touj, Jean Hennebert, Rolf Ingold, Najoua Essoukri Ben Amara   +4 more
doaj   +1 more source

Arabic in contact/ edited by Stefano Manfredi, CNRS, INALCO, SeDyl ; Mauro Tosco, University of Turin.

, 2018
Selected proceedings of the conference, Arabic in Contact: Linguistic and Sociolinguistic Perspective, held December 15-17, 2014 at the University of Naples.Includes bibliographical references and index.Arabic in contact, now and then / Stefano Manfredi ...
Manfredi Stefano, Tosco Mauro
core  

Designing an OCR-Based Medication Support System With Drug–Drug Interaction Alerts for Elderly

IEEE Access
Medication adherence and safety remain major healthcare challenges for elderly populations, particularly within Arabic-speaking communities. Managing multiple prescriptions (polypharmacy) increases the risk of medication errors and adverse drug– ...
Ohoud Mosa Alharbi
doaj   +1 more source

Arabic type from a multicultural perspective: multi-script Latin-Arabic type design

, 2013
Multiculturalism constitutes a mixture of expressions where languages are fundamental, not only as the vehicular form of thought, but also as a powerful tool for social cohesion and relationships within a community.
Balius Planelles, Andreu
core   +1 more source

CNN-optimized text recognition with binary embeddings for Arabic expiry date recognition

Journal of Electrical Systems and Information Technology
Recognizing Arabic dot-matrix digits is a challenging problem due to the unique characteristics of dot-matrix fonts, such as irregular dot spacing and varying dot sizes.
Mohamed Lotfy, Ghada Soliman
doaj   +1 more source

PsOCR: Benchmarking large multimodal models for optical character recognition in low-resource pashto language

Ain Shams Engineering Journal
This paper evaluates the performance of Large Multimodal Models (LMMs) on Optical Character Recognition (OCR) for the low-resource Pashto language. Pashto OCR is challenging due to its cursive Perso-Arabic script and the scarcity of large-scale annotated
Ijazul Haq, Yingjie Zhang, Muhammad Saqib   +2 more
doaj   +1 more source

Performance Evaluation of Two Arabic OCR Products

, 2007
Numerous Optical Character Recognition (OCR) companies claim that their products have near-perfect recognition accuracy (close to 99.9%). In practice, however, these accuracy rates are rarely achieved.
Osama Bulbul, Gregory A. Marton, Tapas Kanungo   +2 more
core  

Automatic Arabic Text Classification

, 2008
Automated document classification is an important text mining task especially with the rapid growth of the number of online documents present in Arabic language.
Khorsheed, M. S., Al-Harbi, S, Al-Thubaity, A, Al-Rajeh, A, Almuhareb, A   +4 more
core   +1 more source

An Efficient Thinning Algorithm for Arabic OCR Systems

Signal & Image Processing : An International Journal, 2012
This paper address an efficient iterative thinning algorithm based on boundary pixels deletion using colour coding for different pixel types. A black pixel is tested by observing neighbouring pixels, and it gives us an efficient way to decide whether the pixel is deleted or not.
openaire   +1 more source