Auto Tagging: Model descriptionsLast Updated: February 26, 2019
Here is a general description of the auto-tagging settings you can access. Please mind the options you select before tagging your photos for the best results and to avoid false positive.
Click the letter "i" in your dashboard to see the associated metadata. If you have selected the option "try to describe the image", the description will be available in the description field of your metadata.
Tag general concepts, objects and scenes (1 credit)
This setting is for all-purpose visual recognition needs. The ‘General’ model recognizes over 11,000 different ideas including objects, themes, moods, and more, with outputs in different languages.
Detect face, age, gender, smile and more (1 credit)
The ‘Demographics’ model analyzes images and returns information on age, gender, and multicultural appearance for each detected face based on facial characteristics.
Identify adult or racy content (1.5 credits)
This model helps you detect images that contain concepts such as gore, drugs, explicit nudity, or suggestive nudity.
Try to describe the image (2.5 credits)
This feature returns information about visual content found in an image and general descriptions in the form of text.
Identify celebrity (1.5 credits)
The ‘Celebrity’ model analyzes images to identify media that contains the face(s) of over 200,000 celebrities from business, politics, sports and entertainment.
Identify landmark (1.5 credit)
The landmark option recognizes more than 9,000 natural and humanmade landmarks from around the world.
Understand wedding concepts (1.5 credit)
The ‘Wedding’ model recognizes over 400 concepts related to weddings including bride, groom, flowers, and more.
Understand food concepts (1.5 credit)
The ‘Food’ model recognizes more than 1,000 food items in images down to the ingredient level.
Understand travel concepts (1.5 credit)
The ‘Travel’ model recognizes specific features of residential, hotel, and travel-related properties.
Understand apparel concepts (1.5 credit)
The ‘Apparel’ model recognizes more than 100 fashion-related concepts including clothing and accessories. This setting is recommended for e-commerce platform or a fashion curation site.
Understand textures and pattern concepts (1.5 credit)
The Textures & Patterns model is designed to acquire and apply knowledge for recognizing textures/patterns in a two-dimensional image. It includes common textures (feathers, woodgrain), unique/fresh concepts (petrified wood, glacial ice), and overarching descriptive concepts (veined, metallic).