Results 151 to 160 of about 5,692 (199)

Secure Arabic Handwritten CAPTCHA Generation Using OCR Operations

2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), 2016
Handwritten CAPTCHAs can be generated from pre-written or synthesized words, with added distortions and noise to survive OCR attacks. This paper takes a different approach for generating CAPTCHAs: use OCR operations themselves to secure the CAPTCHAs.
Suliman A. Alsuhibany, Mohammad Tanvir Parvez   +1 more
openaire   +1 more source

Pre-processing Issues in Arabic OCR

2012
Pre-processing of scanned documents is a necessary first step in the process cycle of any document processing application. While pre-processing methods are generally language independent, the effectiveness of downstream OCR processes can often be improved by language/script specific adaptations, particularly in the case of non-Latin scripts such as ...
Zhixin Shi, Srirangaraj Setlur, Venu Govindaraju   +2 more
openaire   +1 more source

Effect of OCR error correction on Arabic retrieval

Information Retrieval, 2008
Arabic documents that are available only in print continue to be ubiquitous and they can be scanned and subsequently OCR'ed to ease their retrieval. This paper explores the effect of context-based OCR correction on the effectiveness of retrieving Arabic OCR documents using different index terms.
Walid Magdy, Kareem Darwish
openaire   +1 more source

Space Anomalies in OCRs for Arabic Like Scripts

2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), 2018
This paper investigates and analyses the nature of errors occurring in Optical Character Recognition (OCR) for Arabic-like scripts. Existing research on the area of OCR for Arabic-like scripts often focuses on achieving the best performance in terms of character error rates.
Riaz Ahmad, M. Zeshan Afzal, S. Faisal Rashid, Marcus Liwicki, Andreas Dengel   +4 more
openaire   +1 more source

Arabic OCR Based on Image Invariants

Geometric Modeling and Imaging--New Trends (GMAI'06), 2006
Optical character recognition (OCR) is an area of interest for converting hard copies of written information, as in faxed or scanned documents. In this paper, we compare two common image invariant methods in OCR, the invariant central moments (NCM) and the normalized Fourier descriptors (NFD) of the character.
openaire   +1 more source

Improvements in hidden Markov model based Arabic OCR

2008 19th International Conference on Pattern Recognition, 2008
This paper describes recent advances in hidden Markov model (HMM) based OCR for machine-printed arabic documents. A combination of script-independent and script-specific techniques are applied to glyph models and language models (LM). Script-independent techniques we applied are higher order n-gram LMs for N-best rescoring and discriminative estimation
Rohit Prasad, Shirin Saleem, Matin Kamali, Ralf Meermeier, Prem Natarajan   +4 more
openaire   +1 more source

An arabic OCR using neural network classifiers

1995
A typewritten Arabic OCR (Optical Character Recognition system) is introduced. The system automatically predicts the size of the font, and uses it in separating lines, words and subwords. Then, it scans the text in a way similar to what the Arabic readers do to recognize and segment the different characters. A set of nine Neural Network modules is used
Hazem Raafat, Gasser Auda
openaire   +1 more source

Ocr of Arabic texts

1988
This paper presents a method for the recognition of multi-fonts Arabic texts entered from a scanner (300 dpi). The technique for the recognition presents the following steps: digitization, line sparation, word separation, segmentation of a word into characters, indentification of each character and finally recognition of the word.
openaire   +1 more source

First steps in developing an arabic OCR system

2016
La Reconnaissance optique de caractères présente à nos jours une méthode très utilisées pour la numérisation des documents dont le but de les protéger. Ce projet présente un premier pas pour réaliser un système de la Reconnaissance Optique des Caractères Arabes. Il a été réalisé avec la coopération du Centre Nationale d’Archives Tunisien qui a fourni l’
Ouled Omar, Ilyes, Amiri, Hamid
openaire   +1 more source

A segmentation-free approach to Arabic and Urdu OCR

SPIE Proceedings, 2013
In this paper, we present a generic Optical Character Recognition system for Arabic script languages called Nabocr. Nabocr uses OCR approaches specific for Arabic script recognition. Performing recognition on Arabic script text is relatively more difficult than Latin text due to the nature of Arabic script, which is cursive and context sensitive ...
Nazly Sabbour, Faisal Shafait
openaire   +1 more source