Building an OCR model
OCR is useful for apps – such as a conference management app – where you need to collect the names of attendees or read a product label for inventory management. You may have documents with a fixed style and format, such as names, badges, and labels for stock items on the shelf. Without OCR, the app user needs to manually type into the form view in the AppSheet app to register data. OCR removes the need for this manual process by automatically scanning the document and recognizing the fields and values for each of them.
After taking a photo of the target document and uploading it, OCR extracts the text data from the image file and converts it into a structured set of data automatically. Let’s have a look at this powerful feature in detail.
