Sakhr Arabic and Islamic Software AramediA Group, technical translation, Multimedia, Localization of software into Arabic. Graphic Web page Design

What is an OCR technology?

OCR stands for Optical Character Recognition. When you scan a text document, the computer can only see this text as graphical figures on a page. That text is not usable, searchable, or editable. It's considered as an image.

OCR programs are designed to read this text and recognize it. It is a software that converts the shapes (in a scanned text) into a text document. However, there may be some errors especially if the font is small or the scanning unclear. But after all, it is considered as a faster and more time-saving way than typing the text.

Arabic OCR

With the Arabic language having its unique characteristics, it was more difficult for Arabic OCR technology to exist. There're many challenges in Arabic text recognition. First Arabic is written cursively so that more than one character are written connected to form what we call 'Block of Characters- BC'. It can also be written in many fonts so that a BC has more than one base line. Then Arabic uses many types of external objects such as dots, 'Hamza' and 'Madda'. Also Arabic may be written diacritized which adds a new set of external objects. Besides, Arabic characters can have more than one shape according to their position inside the BC (initial, middle, final, or standalone BC). There's also Overlapping, which makes the problem of determination of spacing between BCs and words difficult. Moreover, Arabic fonts suppliers do not follow a common standard and therefore, Arabic fonts are very different and characters characteristics are not reliable to build an OMNI OCR.

Depending on its researches in computational linguistics, Sakhr Software was able to get over these problems and produce its Arabic OCR program.

It combines two main technologies: Omni technology which depends on highly advanced research in Artificial Intelligence, And the Training technology which increases accuracy of character recognition. Sakhr OCR can identify more than one language through Xerox TextBridge technology, one of the most popular OCR programs. The program can also identify both Arabic and English characters on the same page.

The OCR can distinguish between 26 true types of Arabic fonts. The Advanced version of the program is designed to enable the user scan large amounts of documents, save them as graphic files and classify them to be recognized later to save time. The program recognizes graphics and puts them in their proper place on the page. The program also saves page format without any modification to tables, columns or graphics. It can also identify diacritics and keep or remove them according to the user's choice.

The output can be saved to disk for use in a variety of applications such as word processing. The program is compatible with many programs such as DDE or OLE automation.

The Advanced Version and the Office Version of the OCR are compatible with the Arabic or any European edition of Microsoft Office 95.

Technologies Used in Sakhr OCR |
What is OCR? | Sakhr OCR FAQ |


	*Arabic Software Desktop Publishing Translation OCR ASR TTS MultimediA*