Help Center> Optical Character Recognition> SDK Reference> Introduction to OCR SDK
View PDF

Introduction to OCR SDK

OCR Overview

Optical Character Recognition (OCR) can convert characters in images or scanned copies into editable text, eliminating the need for manual input to improve service efficiency. It can recognize characters on ID cards, driving licenses, vehicle licenses, receipts, general tables, and general text.

OCR provides services through open application programming interfaces (APIs). You can obtain the inference result by accessing and invoking APIs in real time, greatly improving business efficiency.

SDK Overview

Optical Character Recognition Software Development Kit (OCR SDK for short) encapsulates the RESTful APIs provided by OCR to simplify application development. You can directly call API functions provided by OCR SDKs to use OCR.

Mappings Between Services and APIs

Table 1 lists the mappings between the OCR sub-services and APIs.

Table 1 Mappings between services and APIs

Service

API

General Table OCR

POST /v1.0/ocr/general-table

General Text OCR

POST /v1.0/ocr/general-text

Web Image OCR

POST /v1.0/ocr/web-image

Auto Classification OCR

POST /v1.0/ocr/auto-classification

Handwritten Text OCR

POST /v1.0/ocr/handwriting

ID Card OCR

POST /v1.0/ocr/id-card

Vehicle License OCR

POST /v1.0/ocr/vehicle-license

Driving License OCR

POST /v1.0/ocr/driver-license

Passport OCR

POST /v1.0/ocr/passport

Bank Card OCR

POST /v1.0/ocr/bankcard

Business License OCR

POST /v1.0/ocr/business-license

Transportation License OCR

POST /v1.0/ocr/transportation-license

Plate Number OCR

POST /v1.0/ocr/license-plate

VAT Invoice OCR

POST /v1.0/ocr/vat-invoice

Motor Vehicle Sales Invoice OCR

POST /v1.0/ocr/mvs-invoice

Taxi Invoice OCR

POST /v1.0/ocr/taxi-invoice

Train Ticket OCR

POST /v1.0/ocr/train-ticket

Quota Invoice OCR

POST /v1.0/ocr/quota-invoice

Toll Invoice OCR

POST /v1.0/ocr/toll-invoice

Flight Itinerary OCR

POST /v1.0/ocr/flight-itinerary