Skip to main content
This Easily extract text from images including from those of documents in realtime Generic optical character recognition is a very useful AI model as it detects & extracts text from all types of images with great accuracy.

​
Request

[POST]
{{baseurl}}/api/v1/ml/ocr/generic
HeaderTypeDescription
AppIdstringCreate an app to get your app ID on dashboard here
AuthorizationstringPrivate/secret key. Use <key> not Bearer <key>

​
Body Parameters

|Parameter | Type | Description | | --- | --- | --- | --- | |img REQUIRED | string | Base64 value of the image. please do not include the data type example: data:image/jpeg;base64 |

​
Sample response

Response
{
    "entity": {
        "data": [
            "National Identity Management System",
            "Nimc",
            "Federal Republic of Nigeria",
            "National Identification Number Slip (NINS)",
            "Address:",
            "Tracking ID:",
            "S7Y0NYFD7890123",
            "Surname:",
            "John",
            "26 JOHNSON STREET AGODO AREA",
            "NIN:",
            "70142123456",
            "First Name:",
            "Doe",
            "Issue Date:",
            "26/08/2014",
            "Middle Name: OLA-Doe",
            "IKOTUN EGBE",
            "Gender:",
            "M",
            "Lagos",
            "Note: The National Identification Number (NIN) is your identity. It is confidential and may only be released for legitimate transactions.",
            "You will be notified when your National Identity Card is ready (for any enquiries please contact)",
            "07040144452, 07040144453,",
            "National Identity Management Commission",
            "helpdesk@nimc.gov.ng",
            "www.nimc.gov.ng",
            "07040144454",
            "11. Sokode Crescent, Off Dalaba Street, Zone 5 Wuse, Abuja Nigeria"
        ]
    }
}

​
Response Fields

FieldTypeDescription
entityobjectContains the response data
entity.dataarrayOrdered list of text strings extracted from the image via OCR. Each element is a distinct text block detected in the image, returned in reading order