• Retyping paper documents is no longer needed

    Retyping paper documents

    Instead of spending hours or even days retyping documents you already have printed on papers, do this by ARAXPage only with a few clicks in a few seconds. Experience has shown that a professional typist in an 8 hour working shift can type about 60 pages (Each page approximately 600 words). ARAXPage can do the same thing only in 8 minutes. This is an improvement in efficiency about 6000%!


  • Convert your documents, articles, magazines, ... into digital libraries

    documents, articles, magazines

    Do you spend a lot of space for archiving documents, books, newspapers,...? Do you want to share them with society (through INTERNET for example)?

    ARAXPage will help you to convert paper documents into digital edit and searchable versions and by this means, a huge paper printed library can be contained in disk! Also you can search among your document and get information from resources you wouldn't refer to it in it's paper printed form! You will be able to search in books with improper table of contents and find even your desired word in them and by this means speed up your research much more faster.


  • Make your office automation system intelligentoffice automation system

    Have you got an office automation system in which you store letters, circulars and deeds after scanning them? If you add ARAXPage into this system, you can add a digital version of those pictures to your automation system and eliminate need for retyping them or extracting data from them such as dates, serial numbers,....


  • Exploit your facilities functionalityfacilities

    Do you have already paid for computer and scanner? If you add ARAX to this collection, it will enable you to get your money back from resulting save in time and cost. ARAXPage makes your computer and scanner an intelligent entity which can do the job of several professional typists. It suffices to scan your documents and give the images to ARAXPage.

In order to check the accuracy of ARAXPage in reading Farsi/English texts, you can check some sample forms read by the software. In this collection different kinds of documents (different scanning resolutions, fonts, context, ...) are gathered so that you can have a better sense about ARAXPage capabilities. For each document you can download the picture and corresponding RTF file. It's considerable that there has been no manual correction done on these files and the RTF is the file created with ARAXPage, just with a single click!

A poem from Hafez (300 dpi)

One poem from Hafez with dark background. ARAX intelligently identifies dark backgrounds and extract text in these backgrounds also. This text contains serious text spacing corrections, the ARAX identifies and preserves.

Fatemeh, is Fatemeh(300 dpi)

This text which is chosen from "Fatemeh, is Fatemeh" written by Dr. Sharia'ti, is typed using Mitra Font.

Ferdowsi biography (300 dpi)

Biography of Ferdowsi, scanned with 300dpi resolution. There are different fonts used in this document, which ARAX has identified and used in creating output RTF file.

Fonts recognized by ARAXPage (300dpi)

This text contains different zones: Text, Picture and Table. Cells in the table contain both Farsi and English words.

Roodaki biography (300 dpi)

Written in English, this text is Rudaki's biography. ARAX not only read Farsi texts accurately, but also English texts are read with a magnificent accuracy.

A random text (300 dpi)

A text with complex layout (pictures and text) containing both Farsi and English words.

Hafez biography (300 dpi)

Brief biography of Iran and world's great poet Shamsoddin Mohammad Hafez, scanned with 300dpi resolution. In the text there is one of his great poems, for which the ARAX has saved the page layout correctly.

A poem from Movlavi(300 dpi)

Delighting poem of Jalaloddin Mohammad Balkhi(Movlavi) scanned with 300dpi resolution.

Ferdowsi biography (200 dpi)

Biography of Ferdowsi, scanned with 300dpi resolution. There are different fonts used in this document, which ARAX has identified and used in creating output RTF file.

Alisadr cave specification (300 dpi)

A brief description of Alisadr Cave, one majestic natural scene in Hamadan. In this document, text has been decorated with pictures with complex layout.

Professor Hesabi biography (300 dpi)

This is a text about Professor Mahmood Hesabi, a well-known face in the world of physics. This is also containing both Farsi and English words and is written in a two column layout.

ARAXPage specification (300 dpi)

This is about ARAX software, in landscape orientation and containing colored background textboxes.

Some screen-shots from ARAXPage professional Edition, will let you become more familiar with the ARAXPage. Pictures are chosen so that they display basic operations of the program. Although they don't tell everything about ARAXPage, for more information, you can refer to ARAXPage features link.

batch-pro.jpg spell-pro.jpg setting-pro.jpg main-pro.jpg
Batch management
Spell checking
ARAXPage setup
Main screen


editor-pro.jpg prop-pro.jpg enhance-pro.jpg
Document properties
Enhancement module


splash_pro.jpg zoning-pro.jpg
ARAXPage splash screen
Document auto-zoning


Output document regeneration

ARAXPage as the first and most powerful Farsi OCR software has unique features which are listed below:


Automatic document layout analysis and recognition accuracy

ARAXPage's automatic analysis of document layout and high accuracy in extracting texts, makes it an outstanding product. Some of these features are:

  1. Automatic correction of rotation and black edges of scanned documents:

    ARAXPage can automatically delete black edges of documents and also corrects rotations which are usually occurred during scan process. This increases recognition accuracy.

  2. Enhancing pictures quality:

    For different reasons including low quality of printed document, noises, dirt and blemishes or incorrect scan settings, the document image may not be qualified for OCR process. ARAXPage provides you with picture editing and enhancement tools by which you can enhance document images manually and increase the accuracy.

  3. High Accuracy:

    Innovative approaches are used in the software which are carefully chosen for Farsi language. This has improved the quality of recognition dramatically. In the same time, ARAXPage can read typed English texts with high accuracy also. In other words by purchasing ARAXPage you don't need an English OCR system.

  4. Automatic Language Identification:

    ARAXPage is capable of identifying English words and phrases in midst of Farsi text and read them. For this reason, you can comfortably use
    ARAXPage for converting new scientific Farsi articles which include many English words.

  5. Trade-off between speed and accuracy:

    For documents with suitable quality, you can choose to read documents very fast and do your job in less time.

  6. Possibility of recognition of text in pictures:

    If there is certain text inside some pictures and you want to read them, ARAXPage provides you with tools to this by creating text zones inside those pictures manually.

  7. Possibility of manual zoning:

    If for any reason (e.g. drastically low quality of document image) automatic zoning did not work properly or you want to change it (e.g. you don't want to read all parts of document) you can do it manually!


WYSIWYG Editor and standard output formats

ARAXPage includes a built-in text editor which enables you to easily correct extracted texts in case they need corrections. By this editor, you don't need to use other editors like Microsoft® Word®, although in the included editor original image of the word you want to correct is displayed along with it. Some features of this part are:

  1. Farsi Font Recognition:

    One of the most important features of ARAXPage is the capability of text font recognition. Currently ARAXPage can identify 10 famous Farsi fonts successfully.

  2. Table Recognition:

    ARAXPage can identify table in document image and read its cells separately.

  3. Preserving document layout:

    ARAXPage with above two features along with others can preserve document image layout and create the output exactly as seen in document image. It's obvious that this feature saves time for users by eliminating the need for recreating layout in other editors.

  4. Display of original image of chosen word in editor:

    ARAXPage displays original image of word or phrase which you are currently editing and also highlights the corresponding part of document image. There's no need to say how much this feature eases editing operation.

  5. Farsi and English Spell-Checker:

    If there's a word recognized which is not in the dictionary, ARAXPage shows this word to you and list the suggestions sorted according to similarity. You can use several Farsi and English dictionaries at the same time.

  6. Search and replace:

    This feature enables you to apply a series of similar changes easily.


User Interface

We've tried our best to bring you OCR functionality with simplest form. This will enable even novice users to utilize ARAXPage easily. Some of the features are:

  1. Simplicity and Usability:

    To run major operation with software only one click of mouse is enough. Even there's a standard set of shortcuts defined so that user don't even need clicking to do what he/she wants!

  2. Batch Management:

    ARAXPage enables you to collect relevant document images together and perform OCR actions on some of them, all of them or one of them. Also you can save your current batch and continue your work on the next session.

  3. Document status:

    If the user wants to know the status of a document (from OCR point of view), it suffices to command software to display document status! By this utility in addition to the status of document, you can even see the histogram of recognition confidence!


Support for Networking (Network edition only)

In case you've chosen network edition for your organization, incorporation or company, in addition to economic benefits you can utilize networking capabilities too:

  1. Distributing process load on the network:

    Each of network clients can take a specific role in OCR process and this will increase the overall speed.

  2. Easy expansion:

    If you've got too many documents it suffices to buy some new computers and connect them to your network, afterwards put a part of process load on them.

  3. Centralized control utility:

    In network edition you can manage the OCR process centrally and apply your own standards to whole OCR workflow. Added to this you can supervise users and see how they work on-line.

  4. Economic solution for organizations:

    If you want to provide many people in your organization with OCR technology, we will give you reasonable discount (according to number of users).


HODA iReadDoc has a client/server architecture with parallel processing and pipe-lining capabilities. There are three main modules on HODA iReadDoc package: Administration module, FormReader module and FormVerifier module.
HODA iReadDoc has a client/server architecture with parallel processing and pipe-lining capabilities. There are three main modules on HODA iReadDoc package: Administration module, FormReader module and FormVerifier module.


Server module.jpg

  • Administration Module (server)

    Using Administration module, the admin of the system can define his/her management policies, include roles and users, workspace management, recognition and verification parameters, verification workflow, batch management (add, delete, reset, analyze, commit and roll-back), on-line monitoring and export.



  • FormReader ModuleForm Reader.jpg

    FormReader is the most critical module of the system. FormReader gets the form images from Administration module, extract data and send the results to server. FormReader is able to read Farsi, Arabic and Latin alpha-numeric values, barcodes, OMR bubbles and personal photos. To see some samples of data fields, extracted by FormReader, you can visit Fields Gallery.



  • FormVerifier ModuleForm verifier.jpg

    Human operators on the iReadDoc LAN network can verify the read data using FormVerifier module. The main idea behind FormVerifier is that the operator checks the read data against data field image. If he/she finds some mistakes, corrects the field value.
    The important fact is that only small percentage of read data should be verified by human operators. For example in the case of numeric values, to reach the maximum accuracy, you need to verify only 5% of total characters. In this case the throughput of data entry increases, while the maximum accuracy is kept by HODA iReadDoc.

    For more information and read successful case studies, please click here.

HODA iReadDoc is able to read handwritten and machine-printed charactres, barcodes, OMR bubbles and tick marks. Also it is able to extract an ellipse format of face photos from input face image. In the list below you can find some sample of field images and the result data, extracted by HODA iReadDoc auomatically.


Input Image

  Outout Data

























کیانی خورده چشمه 









احمدزاده حبیبی آباد 






















Why we offer you HODA iReadDoc to automate your data entry systems?
You can find some advantages of using HODA iReadDoc software package in list below:


Decision making in the least time

Making the best decision can be done by having accurate information in minimum time HODA iReadDoc functionalities in extracting data quickly and correctly, provides you the opportunity of making your important decisions with the most confidence.


Decreased data entry/data validation time

Reading data is done in fraction of time by using HODA iReadDoc while your customized rules for increasing data accuracy are also considered. And the workflow will be done by minimum interaction with user. It considerably saves cost and time for you.


Increased data accuracy

HODA iReadDoc uses several mechanisms to improve the accuracy of data input system up to 100%. Mechanisms such as removing noises from scanned images, internal defaults and defined business rules for validating recognized data in processing forms in addition to complete set of predefined tools for verifying data which can receive your own custom desires for increasing data accuracy.


No need to sort forms manually

There is no need to manually sort paper forms, HODA iReadDoc will do it as you want.


Electronic documents archive is in hand

Using HODA iReadDoc you have an electronic archive of images with search capabilities on each field. In other word, HODA iReadDoc give you the opportunity to be in a paperless world of information as well as the need for more paying for placing paper forms will be removed.


Improved customer services

Customer services will be improved thanks to electronic access to form images in addition to form processing time is decreased as well as data accuracy is increased through using HODA iReadDoc.


Added employees' satisfaction and efficiency

You will find HODA iReadDoc as a powerful tool to use power of your staffs as controllers instead of being only doers and through it you will provide them with a better atmosphere of job and you will be able to improve their knowledge and level of their works which will be result in more satisfaction they feel and more performance they have in the organization.


Easy to extend system

HODA iReadDoc scalability power helps you to distribute form processing through the LAN and to participate more workstations and people easily as your paper forms volume to be processed increased. We provide you a robust system for processing large documents volume.


Pay for itself within a short time

Your invest for HODA iReadDoc will be return to your organization within a very short time thanks to increased throughput up to 1000% provided by automating data input system.


Better management of manpower in the system

Using HODA iReadDoc through its Log Analyzer, you will be able to assign proper job to each employee according to its real functionalities.


Secure accessing to secret information

You can define several levels of accessibilities to different fields according to their degree of importance to avoid not allowed data accessing.

ICR (Intelligent Character Recognition) technology is an advanced automatic data entry system. In this technique a computer program reads handwritten, machine-printed, barcodes and other data fields from document images automatically and saves the result on a database.

To use ICR as data entry method, you should do the following steps:


    1. Design and print machine-readable (ICR-enabled) forms

      To reach the maximum accuracy and performance in ICR technology, you need to design a special data gathering forms, which is called machine-readble forms, ICR-enabled forms or in more general terms Structured Forms. But from ICR point of view, it is not necessary to design ICR-enabled forms. ICR is able to extract data from semi-structured forms like checques and coupons. Till now, HODA System has designed and print more than 40 ICR forms for different projects. For example you can visit Iran general housing and population census 2006 for more information.

    1. Form preparation and scanning

      After gathering filled ICR forms, it is recommended to classify them on some batches based on the desired paramter (for example by date received). This is not necessary to classify forms on the form of batches, but this will streamline the whole ICR process. The next step after form preparation, is scanning. To scan forms, we offer our customers the most powerful scanner family on the market, microform scanners.

    1. Data extraction form images

      After scanning the forms, the ICR software gets the images and extracts information automatically. There are many important capabilities, an ICR software should provide. For example speed, accuracy rate, verification methods, export capabilities, monitoring and management reports.

      You can find all of these capabilities plus many more advanced features in HODA iReadDoc.

  1. Export read information to other systems

    After extarcting and verifying data using ICR software, you must transfer data to destination systems for more processing or archiving. As a first company, HODA System introduced HODA iReadDoc to the market for Farsi and Arabic languages. This product has been used successfully, in more than 20 large data entry projects. For example you can visit Iran general housing and population census 2006, for more information.


hte L.jpg

Omrstudio1 L.jpg





setup L.jpg worksheet L.jpg



HFD%20L.jpg ANALYSI L.jpg export L.jpg



OMR is the most accurate technology to enter data into computer systems. This technology has been used in last decades in many official and business processes. To use OMR in data entry, you need to take in consideration, 3 main requirements:

  • OMR form design and print


    To use OMR as an automatic data capture solution, you need to design and print special forms to support the OMR standards. In the other hand, in OMR technology you are not able to read data from none-standard forms.

  • OMR Machine


    OMR is a hardware-based technology and you need an OMR machine to read OMR forms. In general OMR machines have 1 or 2 OMR heads (for single-side or double side forms) and maybe equipped with barcode reader heads.

  • OMR Software


    To define the location and type of the data fields on the OMR forms, connect to OMR machine and receive read data, you need a software application.

    HODA System offers to the customers, the best choices for these requirements.

DocMan is the key for optimizing business processes, increasing performance, improvement in information storage and retrieval and preferment of customer support.

  • Capture

    DocMan uses a database to organize the documents enter to the system. Usually, the paper documents are scanned and electronic files are imported to the system. By the scan, fax and import capabilities, the organizations sure that all important information are captured and stored in a secure and central place. DocMan users can import a large variety of electronic files like Excel, Words and HTMLs to the system.
    DocMan has some unique and advanced tools to streamline the document import to the system. The capability of connecting to HODA iReadDoc and ARAXPage (The most advanced and accurate Farsi OCR) are sample of these tools.


  • Document indexing and storing

    All the documents imported to DocMan, can be described using metadata (profiles). This metadata is necessary to have the search and retrieval capabilities. The database features of DocMan enable users to add indexing data by entering profile fields and prepare them for fast searching. The fields used for profiling are defined by the system administrator in the profile management tool. There are two types of profiling in DocMan: manual by operators or automatic by DocMan itself.


  • Retrieval

    Targeted search is the fastest method to find documents in DocMan. DocMan enable users to do their searches on the profile fields, contents (ARAXPage OCR result) or annotation.


  • Document viewing and editing

    The document viewer tool is for viewing the popular file formats. Using this tool, users can view, index, annotate or edit documents.
    The versioning technique of DocMan protects a document from concurrent editing by different users at a same time. Using this capability, the different versions of a document are stores (check in, check out capability).
    The viewer tool enables users to do different annotations on image documents. Users can annotate, draw lines and freehand, highlight and stamp documents. These annotations have the security labels to view or edit only by authenticated users.


  • Document sharing and collaboration

    Information and documents in DocMan can be shared between users in a LAN or WAN network. Document sharing with others is done by print, fax, email or share in the network. Also it is possible to export documents in popular formats like PDF or TIFF, even with profiling data.


  • Secure Contents

    DocMan uses from a simple but effective mechanism to protect documents and information. Protecting is done by assigning passwords to users and set the required permissions for users.
    Also the logging tool of DocMan logs every action done by users and enable users to monitor the user’s activities.

The design and architecture of DocMan enable it to be applicable in different document management solutions. It helps users to capture, index, store, find, retrieve and distribute documents. By using DocMan you have the following benefits:

  • Increase in performance

    By instant and secure access to required documents and information, users are able to finish their jobs quickly. Efficient using of information will increase the overall performance and allow users to focus on their abilities and use the advantages.

  • On time and documented decision making

    As the required information are saved centrally, mangers and users sure that they access to the last version of available documents and information.

  • Fast and accurate customer support

    Using the search capabilities, support staffs can access to the required information, question answers and data queries to respond the customer needs. This will increase the customer satisfaction.

  • Decrease managing and executing cost

    Printers, photocopies, archive spaces, human staffs, transportation and maintenance costs are just few samples of cost which paper-based organizations must pay for it.
    While in this process, some document are lost, damaged, fired or used incorrectly, they will be irrecoverable. DocMan by reducing the cost of such organizations, allows them to spend the save monies in other interested areas.

  • Reducing business process cycles

    In a manual paper-based process, reviewing, assigning, studying and final approvals may take days, weeks or even months. DocMan help users to reduce this time dramatically.