PrizmDoc® v14.1 Release - Updated
In This Topic
    PrizmDoc OCR API
    In This Topic


    PrizmDoc OCR REST API performs high accuracy OCR recognition in user-defined areas of interest (zones) and full page OCR. The PrizmDoc OCR REST API allows your application to take a source image as input and produce a JSON output.

    The PrizmDoc OCR REST API is available as a Docker image and exposes several metrics to monitor behavior, performance, and status. A demo is available here.

    The PrizmDoc OCR REST API supports 73 languages and 4 regions, which includes the following:

    Afrikaans, Albanian, Azerbaijani (Cyrillic, Latin), Basque, Belarusian, Bosnian (Latin), Bulgarian, Catalan,  Croatian, Czech, Danish, Dutch, English, Estonian, Faroese, Finnish, French, Frisian, German, Greek, Guarani, Hani, Hungarian, Icelandic, , Irish, Italian, Kazakh (Cyrillic, Latin), Kirghiz (Cyrillic), Kirundi, , Latin, Latvian, Lithuanian, Luxembourgish, Macedonian, Malay, Norwegian, Polish, Portuguese, Quechua, Rhaeto Romanic, Romanian, Russian, Rwanda, Serbian (Cyrillic, Latin), Shona, Slovak, Slovenian, Somali, Sorbian, Spanish, Swahili, Swedish, Tajik (Cyrillic), Turkish, Turkmen (Cyrillic, Latin), Ukrainian, Uzbek (Cyrillic, Latin), Wolof, Xhosa, Zulu, and combined Baltic, Cyrillic, Central European, and Western European languages.

    Additionally, the following Asian languages are supported with a PrizmDoc license that has the OCR-Asian add-on:

    Chinese (Traditional, Hong Kong Traditional, and Simplified), Indonesian, Korean, Japanese, Thai, and Vietnamese.

    Customize OCR for Your Needs

    The PrizmDoc® OCR REST API offers a variety of ways to improve overall recognition results and individual character recognition.

    To optimize character recognition, you can:

    • Perform segmentation
    • Specify predefined character sets for recognition
    • Reject characters when their recognition fails
    • Specify minimum acceptable confidence values

    To improve recognition results, you can:

    • Configure expected recognition results by specifying the expected type of data
    • Select the expected language(s) being recognized
    • Report alternate character results and associated confidence values
    • Define recognition zones of interest to avoid recognizing unusable data


    The OCR add-on for PrizmDoc requires a license. Without a valid license, PrizmDoc will function in a limited evaluation mode. The OCR add-on will also function in Evaluation mode, allowing you to try it before you buy it. If you are using an OEM License or an Offline Metered License, you will need to Configure the Process Manager with the solution name, solution key, and license key of your ImageGear license and SmartZone license.

    To purchase the OCR add-on, contact us at

    You can register for a free trial of PrizmDoc here.