February 2019
Intermediate to advanced
494 pages
11h 5m
English
Optical character recognition (OCR) extracts machine-readable text from an image containing printed or handwritten characters.
Consider an example where a fictional company called ShipAnyWhere receives expenses filled by their employees in a paper form, as shown in the following screenshot:

They now need to automate the process of logging the expenses in the database. They are going to use the OCR-to-JSON API to get a JSON file from the image.
A POST request is made to the API as follows:
https://northeurope.api.cognitive.microsoft.com/vision/v1.0/ocr?language=unk&detectOrientation =true
The post ...
Read now
Unlock full access