ARAXPage accepts almost all popular image file formats such as TIFF, BMP, JPG and so on. Pictures can be Black and White, Grayscale or Color and of any resolution. To gain optimized results, it's recommended that input picture have at least 300dpi resolution.

ARAXPage can communicate with scanners with manual or automatic feeds which have TWAIN or WIA interface and get the pictures. It's possible to use ARAXPage scanning interface or the original vendor one.

All of the pictures that are opened or scanned are listed in graphical interface and you can easily move between them. It shows status of each of pictures in the batch(status in the process of OCR), graphically.

You can save your work on the current batch, and open it later to continue working.

ARAXPage analyses the content of document image and automatically identifies zones of text, images or tables. Text zones and table zones are passed to recognition engine to be converted automatically. Image zones are put in the output as is. If the zoning needs modification, you can do this by the specific toolbar.

ARAXPage can recognize 10 famous Farsi fonts Lotus, Nazanin, Mitra, Zar, Yaghut, Titr, Traffic, Homa, Tahoma and Times New Roman in the printed document image. If you need to recognize a font that is not among these, please contact HODA System.

ARAXPage can identify Table zones as where described before. It reads the tables, cell by cell and creates a table in the output with corresponding data, while preserving table layout.

ARAXPage can recognize and read english words and phrases in the midst of Farsi texts. According to document language, you can set language options (Farsi, Farsi-English, English) to achieve best performance.

ARAXPage is equipped with a powerful image enhancement module which helps you to retouch low quality pictures, high noise pictures or pictures with too much rotation!

A powerful editor is contained in the software which has several capabilities. With aid of this editor OCRed documents can be edited before saving. Advanced capability of synchronized view of text and original picture helps you to always have part of picture corresponding the word or phrase under edition in hand. Added to this, the editor shows tables and pictures for you to see what will you get as PDF or RTF file. It also shows corrsponding parts of picture with table cells while editing them and eases editing tables.

Farsi and English spell checker with a huge database of Farsi and English words is another capability that is included in ARAXPage. By aid of this, correcting Farsi texts is made ultimately easy. If some word is not in the dictionary, ARAXPage shows a list of words most relevant to it and by one click you can replace wrong word with correct one. In the mean time, the original image of word being corrected is displayed to help the user with correction. Also ARAXPage can show low confidence words on the spell check form. Spell checkinf in ARAXPage can be done in two ways: in the editor or in a new form.

With ARAXPage you can save the output of OCR process as Text files, RTF files or PDF. Text files have smaller size but don't support table or image insertion so if the document you have OCRed do not have image or table, this format is suitable. RTF(Rich Text Format) is windows standard format for creating rich documents. In this format, different font layouting, tables and images are allowed to insert. Microsoft® Word® uses this format and is the origin of RTF so you can edit these files by the software. Adobe® PDF(Portable Document Format) files are suitable for publishing and information sharting. They don't need fonts to be installed in the destination computer for being displayed properly.