AI Tagging – Computer Vision is used to analyze pictures, extract the recognized objects and properties as metadata, and tag them on the dataset or file.
After an image file is uploaded, the 4ALLPORTAL passes on the files to Microsoft Azure Cognitive Services, which performs the “Computer Vision” service. The extracted metadata is passed back to the 4ALLPORTAL and tagged on the corresponding image file. At the same time, the image file is put through a face recognition service and you receive metadata about the properties of recognized faces on the pictures.
Metadata is classified in:
Categories (AI Categories)
Description (AI Caption)
Tags (AI Keywords)
Language support:
The tagging of extracted metadata is carried out as standard in English (US). No other languages are currently supported.
Page content
Tagging of metadata
The accuracy of the extracted and tagged metadata of image content is dependent on the performance of Microsoft Azure Cognitive Services. For this reason, you can edit the tagged metadata afterwards as needed.
Images are sorted into categories using metadata (AI Categories). As a result, it is possible to have search queries for image categories, for example “outdoor”, “people_group” or “people_portrait”.
2. Description
A short description is created for every image (AI Caption). This makes it possible to have search queries relating to the general theme of the image, for example “a group of people sitting on a bench”.
3. Tags
For each image, keywords are created about the objects shown (AI Keywords). As a result, it is possible to have search queries for objects on images and the properties of images, for example “woman”, “park”, “sitting”.
