arabic, anism1a2.gif (1972 bytes) arabic software solutions, anism1b1.gif (3409 bytes) arabic, anism1a2.gif (1972 bytes)

Arabic International & Multilingual Software  Desktop Publishing  Machine Translation  Document Management  NLP   OCR  ASR  TTS  MultimediA


The Best Arabic OCR Technology

ocrpho.jpg (10515 bytes)

Introduction

Sakhr Automatic Reader is the outcome of Sakhr ongoing research in the fields of Arabic Natural Language Processing and Character Recognition technologies. Sakhr Automatic Reader pioneers the OCR programs in Arabic language. OCR stands for Optical Character Recognition. When a text document is scanned, the computer recognizes this text as a graphical image. The user cannot manipulate, search, or edit the image text in its image format. An OCR program reads this scanned text, recognizes it, and then converts the figures and characters into editable text pieces.

Sakhr Automatic Reader transforms scanned images into a grid of millions of dots, optically recognizes the characters found in them and ultimately converts them into text. The complex nature of the Arabic language is evident in the cursives of the text, character overlapping, various character shapes, diacritics and the variety of calligraphic Arabic fonts that exist. As a result, these specific Arabic language complexities present major technical challenges in the Arabic OCR industry. The Automatic Reader, backed by Sakhr extensive experience in Arabic Natural Language Processing (NLP) technologies, addresses these challenges effectively, thus providing Arabic users with an award-winning and high quality OCR solution.


Automatic Reader Features

The following tables summarize the Automatic Reader features categorized as General Features, Image Processing & Recognition Features, and Technical & Integration Specifications.


Available in two new versions

OCR Gold Edition   -   OCR Platinum Edition

General Features

No.

Feature

Description

1

Performance and Accuracy

-1 2400 characters per second on PIV-based computers, 2.0 GHz, and 4000 characters per second on Core2 2.13 GHz processor.

-2 Up to 99%accuracy in recognizing Arabic books, newspapers, and similar quality scanned documents.

2

Languages Supported

Recognizing:

-3 The main Arabic based characters languages: Arabic, Farsi, Urdu, Jawi, Pashto (Urdu, Jawi, and Pashto come in an extra language pack).

-4 As well as 18 other international languages (as it includes the most powerful Latin OCR engine – ScanSoft): English, French, German, Dutch, Czech, Danish, Finnish, Greek, Hungarian, Indonesian, Italian, Norwegian, Polish, Portuguese, Russian, Spanish, Swedish, and Turkish.

3

Language Pair Supported

-5 Recognizing bilingual documents: Arabic/English, Arabic/French, and Farsi/English.

-6 Including a bilingual spellchecker (Arabic/English).

4

Recognition Technologies

Supporting OMNI and Learning technologies to obtain higher accuracy in different fonts.

5

Supported Input Formats

-7 Dealing with all image formats (*.BMP, *.TIFF, *.JPEG, *.PCX etc.)

-8 Supporting also PDF format; which is needed especially with Document and Content Management Systems.

Fax Support

Supporting standard fax documents.

6

Supported Output Formats

Saving the output text in different formats such as *.txt, *.rtf, *.XML, *.HTML and searchable *.PDF.

7

Supported Scanners

Working with any type of scanner supporting Twain protocol.

8

Send E-Mails

User has the ability to send OCR results by e-mail.

9

Interface

A very convenient intuitive bilingual (English/Arabic) interface and easy to use. It allows even inexperienced users to navigate and perform the program functions easily and quickly.

10

Help

Comprehensive help is provided in both Arabic and English.

Image Processing and Recognition Features

To increase the recognition accuracy of fax documents and image files, Sakhr Automatic Reader is backed up with the following unique features:

No.

Feature

Description

1

Powerful Imaging Enhancement Tools

Supporting automatic and manual image rotation and fixing, deskewing image, removing shading, zooming, smoothing and inverting colors if the image background is black and its foreground is white.

2

Diacritics

Recognizing or skipping diacritics in Arabic images.

3

Preserving Document Layout

Recognizing and supporting tables (with a special support for ill-formed tables), column, pictures, page size detection, and paragraph indentation in scanned images.

4

Frames Support

-9 Supporting automatic framing and manual framing modes, saving frames in files and applying the saved frames as templates.

-10 Supporting non rectangular frames.

-11 Supporting adding custom attributes for each frame to gain more control on recognition accuracy.

5

Arabic Language Morphological Support

Sakhr NLP technologies for Arabic Language are used to correct the recognition results (like Morphological Analyzer, Morphological Syntax, Statistical Language Pattern, Arabic Thesaurus and other NLP technologies to enhance OCR results). Also the program includes Sakhr corrector as well as an English spellchecker. This is a unique feature in Arabic OCR field which makes Sakhr OCR accuracy incomparable.

6

Batch Operations

Supporting 4 different types of batch operations:

-12 Scan & Save

-13 Scan & Recognize

-14 Load & Recognize

-15 Scan & Save, then Load & Recognize

7

Program Operating Modes

Working as a standalone application with an interactive interface, and can be integrated with other applications via its SDK, available only with Platinum version.

Technical and Integration Specifications

No.

Feature/Spec.

Description

1

Package/Protection Sakhr OCR currently comes in two versions both protected by WIBU dongle,

- Gold edition, runs on either client or server machines but the concurrent OCR sessions is limited to only two sessions.

- Platinum edition, bundling also the OCR SDK. When running on client Windows, only two concurrent OCR sessions can be carried out, while if running on Server Windows there is no limitation on running sessions. It worth to mention that running on server Windows will require the OCR server licensing.

System Requirements

Item

Minimum

Recommended

CPU

Pentium IV 700 MHz

Core2 2.13 GHz processor or higher

Free Disk Space

620 MB

650 MB

or higher

RAM

256 MB

1GB

or higher

Operating System

For Desktop edition

Windows XP SP2, Vista and windows 7 (Arabic-Enabled)

Windows XP SP2, Vista and windows 7 (Arabic-Enabled)

Operating System

For Server edition

Windows, and windows (32 / 64 bit)(Arabic-Enabled)

Windows, and windows (32 / 64 bit)(Arabic-Enabled)

 

be

Price - Order Now - Gold Edition
Price - Order Now - Platinum Edition

International Language Pack Add-On Includes:
Farsi, Jawi, Pashto and Urdu
Price - Order Now

ASR | Categorization | Correction | Diacritization | DMS/ArabDox | Ibsar Reading Machine | IDRISI Search |
Johaina | Keyword Extraction | KMS | MMMP | MT | NLP | OCR | Services  | SET | Speech | Summarization | TTS |
OCR Options | Optical_Character_Recognition | Automatic_Reader_OCR_FAQ | OCR_Gold_Edition |
|
OCR_Platinum_Edition | OCR_Professional | OCR_Technologies | Readiris Multilingual OCR
|


|| Home Page || AramediA Contact Info || Adobe Middle East (ME) || Arabic Fonts || Arabic Language Tutors || All Languages Tutors ||
|| Arabic NewsStand
|| Arabic Resources || American Sign Language (ASL) || Arabic Calligraphy || Children || Desktop Publishing DTP ||
 || Dictionaries of the World || Digital Marvel Comics || Educational Programs || Games for All Ages || Islamic Software ||
Microsoft Arabic Software ||
||
Multilingual Keyboards & Stickers || New Products || OCR || Machine Translation || Sakhr Enterprise Solutions || Search Engines || Software Solutions ||
||
Universal Word || World Resources || Word Processors || The AramediA Sales Policy || Site Map || Software Search || aramediaStore.com ||
Amazon.com ||

AramediA

Join Our Newsletter

37 Adams Street, Braintree, MA 02184-1906
United States of America (USA)
Tel 1-781-849-0021 Fax 1-781-849-2922

 

animail2.gif (5769 bytes)

We Ship All Around the Globe

Copyright © 1995 - 2013 - GnhBos Incorporated dba AramediA. All rights reserved.