Job description
JSON files with data to create template and layout text based on polygon. Below is a JSON example.
The model extracts all identified blocks of text in a collection of paragraphs as a top-level object. Each entry in this collection represents a block of text and contains the extracted text as content and the coordinates of the bounding polygon. The span information indicates the portion of text in the top-level content property that contains the full text from the document. Points are listed in clockwise order: top left, top right, bottom right, bottom left. The units are pixels for images and inches for PDFs.
"pageNumber": 1,
"angle": 0,
"width": 8.2639,
"height": 11.0139,
"unit": "inch",
"words": [
{
"content": "265",
"polygon": [
4.1415,
1.1855,
4.4037,
1.1855,
4.4037,
1.3528,
4.1415,
1.3528
],
"confidence": 0.346,
"span": {
"offset": 0,
"length": 3
}
},
{
"content": "ideal",
"polygon": [
0.5936,
2.5938,
2.4536,
2.5938,
2.4536,
3.0943,
0.5936,
3.0943
],
"confidence": 1,
"span": {
"offset": 4,
"length": 7
}
},
{
"content": "to",
"polygon": [
2.5921,
2.5938,
3.2166,
2.5938,
3.2166,
2.9678,
2.5921,
2.9678
],
"confidence": 1,
"span": {
"offset": 12,
"length": 2
}
},
