This Endpoint provide you get list (text, score, locale, boundingBox) and dimensions from image
Supported two request types
For both cases we have same response type
Response Data Sturucture - in this example we used
"objects": [
{
"text": "Chair",
"score": 0.843457818031311,
"locale": "",
"boundingBox": {
"tl": {
"x": 0.045202311128377914,
"y": 0.6389181017875671
},
"tr": {
"x": 0.4727531671524048,
"y": 0.6389181017875671
},
"br": {
"x": 0.4727531671524048,
"y": 0.9685030579566956
},
"bl": {
"x": 0.045202311128377914,
"y": 0.9685030579566956
}
}
},
{
"text": "Umbrella",
"score": 0.6488758325576782,
"locale": "",
"boundingBox": {
"tl": {
"x": 0.18290652334690094,
"y": 0.23769409954547882
},
"tr": {
"x": 0.9811277389526367,
"y": 0.23769409954547882
},
"br": {
"x": 0.9811277389526367,
"y": 0.9368109107017517
},
"bl": {
"x": 0.18290652334690094,
"y": 0.9368109107017517
}
}
}
],
"success": true,
"dimensions": {
"height": 1200,
"width": 1020,
"type": "webp"
}
}