Image intelligence provides AI-enabled analytic capabilities for image content, such as facial detection, tag detection, and quality assessment. You can call the RESTful API operation (x-oss-process and x-oss-async-process) to analyze images stored in Object Storage Service (OSS) anywhere, anytime, and from any connected devices.
Parameters
OSS allows you to use image intelligence-related features by configuring a single parameter. You can encapsulate this parameter in a style to process images in bulk. For more information about the styles, see Styles.
The following table describes the parameters for image intelligence:
Image intelligence | Parameter | Description |
image/faces | Detects the position of faces in the image and analyzes facial attributes. | |
image/bodies | Detects the position of bodies in the image. | |
image/cars | Detects and analyzes information about vehicles and license plates in the image. | |
image/codes | Identifies QR codes in the image. | |
image/labels | Identifies tags associated with scenes, objects, and events in the image. | |
image/score | Assesses the aesthetic quality of the image based on a set of metrics, such as color and saturation. | |
image/blindwatermark | Adds text blind watermarks to the image. | |
image/deblindwatermark | Decodes text blind watermarks in the image. |
Usage
You can process images by calling the x-oss-process operation. For more information, see Synchronous processing.
To decode blind watermarks, you need to call the x-oss-async-process operation. For more information, see Asynchronous processing.
Billing
The fees for Image Intelligence are included in the bills of Intelligent Media Management (IMM) service. For more information, see billable items.