What's Optical Character Recognition (OCR)?
OCR Activities & Promotions Activities
OCR Web Image API
Function:
This API identifies and extracts text from web images and converts the text into a structured JSON format.
For details about the constraints on using this API, see Constraints. For details about how to use this API, see Introduction to OCR.
Constraints:
English and Chinese are supported but support for traditional Chinese characters is limited.
Only images in JPG, JPEG, PNG, BMP, TIFF, TGA, or WebP format can be recognized.
Common image types are supported, such as mobile phone or desktop screenshots, e-commerce product images, and advertisement design drawings.
No side of the image can be smaller than 15 or larger than 8,192 pixels.
The characters to be recognized must occupy more than 60% of the image.
The web image to be recognized can be rotated to any angle (direction detection must be enabled).
Debugging:
You can debug this API through automatic authentication in API Explorer. API Explorer can automatically generate and debug sample SDK code.
NOTE: API Explorer can be called in ap-southeast-2.
Prerequisites
Before you use this API, apply for the service and complete authentication. For details, see Subscribing to an OCR Service and Authentication.
NOTE: Before you use the service for the first time, enable the service by clicking Subscribe. You only need to subscribe to the service once. If the service is not enabled, an error message with error code "ModelArts.4204" will be displayed when you call the service. Before calling the service, log in to the OCR console and enable the service. Ensure that the region where the service is enabled is the same as that where the service is called.
URI:
POST https://{endpoint}/v2/{project_id}/ocr/web-image
Table Path parameters
Request Parameters
Request header parameters
OCR FAQs
Billing & Subscription