Overview

Tencent Cloud Optical Character Recognition (OCR), based on the deep learning and multimodal large model technology of Tencent YouTu Lab, intelligently identifies text in images as editable text or extracts structured information. OCR supports the recognition of identity documents, bank cards, invoices, and other standard cards and documents. It also supports the recognition of industry documents in various complex formats, such as transportation and logistics weighbridge tickets and consignment notes, as well as healthcare documents such as diagnosis certificates and expense lists.
This section introduces the text recognition API interfaces, all of which are API 3.0 interfaces.
You can call APIs to perform text recognition operations, such as general OCR, card text recognition, invoice recognition, and intelligent document processing.
For information on all APIs supported by text recognition, please see API overview.

Glossary

Common terminology for text recognition API interfaces: see the table below:

Usage Limits

For API parameter limits, see the parameter description in each API document.

Getting Started with APIs

You can use the API Explorer tool to call APIs online.
This document uses the general printed text recognition (high-precision version) API call as an example. The steps to make an API call through the API Explorer Tool are as follows:

1. After signing up for a Tencent Cloud account and completing real-name authentication, log in to the text recognition console, click Enable Now, and you can obtain the API interface call permission for text recognition.
2. Go to the API Explorer page. For more information about API Explorer tool usage, see the document.
3. Call the GeneralAccurateOCR API.
4. After entering the corresponding parameters, make an online call to view the response result. For input parameter description, see the API Documentation (https://www.tencentcloud.com/document/product/866/34937?from_cn_redirect=1).