Ocr Object

The ocr field is a property of the document_page_object and contains all the text extracted from the page.

{
    "ocr": [
        ...
    ]
}

Schema

Schema: Ocr Object

Key	Type	Description
ocr	list [object]	list of object containing text info

Each object in the list usually, but not always, represent a single word and with some other useful information. For simplicity will be called word object

Schema: Word Object

Key	Type	Description
Text	string	the word text
Confidence	float	the confidence on the extracted word
BoundingBox	list [object]	list of object representing the polygon

Example of ocr

Example of ocr

{
    "ocr": [
        {
            "Text": "TESSERA",
            "Confidence": 99.44908142089844,
            "BoundingBox": [
                [
                    340,
                    140
                ],
                [
                    468,
                    140
                ],
                [
                    468,
                    168
                ],
                [
                    340,
                    168
                ]
            ]
        },
        {
            "Text": "SANITARIA",
            "Confidence": 98.53160095214844,
            "BoundingBox": [
                [
                    477,
                    141
                ],
                [
                    638,
                    141
                ],
                [
                    638,
                    167
                ],
                [
                    477,
                    167
                ]
            ]
        },
        {
            "Text": "Codice",
            "Confidence": 99.22911071777344,
            "BoundingBox": [
                [
                    183,
                    228
                ],
                [
                    246,
                    228
                ],
                [
                    246,
                    245
                ],
                [
                    183,
                    245
                ]
            ]
        },
        {
            "Text": "VRDGPP13R10B293P",
            "Confidence": 90.97354888916016,
            "BoundingBox": [
                [
                    268,
                    236
                ],
                [
                    543,
                    236
                ],
                [
                    543,
                    255
                ],
                [
                    268,
                    255
                ]
            ]
        },
        {
            "Text": "Fiscale",
            "Confidence": 98.39080047607422,
            "BoundingBox": [
                [
                    182,
                    248
                ],
                [
                    246,
                    248
                ],
                [
                    246,
                    265
                ],
                [
                    182,
                    265
                ]
            ]
        },
        {
            "Text": "Cognome",
            "Confidence": 98.35092163085938,
            "BoundingBox": [
                [
                    181,
                    287
                ],
                [
                    272,
                    287
                ],
                [
                    272,
                    307
                ],
                [
                    181,
                    307
                ]
            ]
        },
        ...
    ]
}