This document introduces the features of Vision APIs.
Vision APIs analyze a given image, and then determine whether it is a face, product, porn content, or text or create a content-oriented thumbnail or tag.
Here are the features of Vision APIs.
Name | Description |
---|---|
Face detection | Detects faces in images, analyzes the position, key points, angles of the face, and estimates the gender and age of the detected face. |
Product detection | Detects the position and type of products in the image. |
Adult image detection | Determines if the image is porn content. |
Thumbnail creation | Finds an area that represents the content the most out of the image and creates a thumbnail(preview) image with the requested size. |
Thumbnail detection | Finds an area that represents the content the most out of the image and suggests a thumbnail that can capture user's attention. |
Multi-tag creation | Creates a tag for specific content in an image. |
OCR | Detects the text area in the image and extracts the texts. |
You can use Vision APIs only with a REST API.