Create your own models using your own images or text with your own concepts.
Detect items of clothing or fashion-related items.
Detect whether images contain the face(s) of celebrities.
Return density values for dominant colors present in images in hex format or closest W3C counterpart.
Predict age, gender and multicultural appearance for each detected face based on facial characteristics.
Detect if an image contains human faces and coordinate locations of where those faces appear with a bounding box.
Analyze images and return numerical vectors that represent each detected face in a 1024-dimensional space.
Recognize more than 1,000 food items and dishes in images down to the ingredient level.
Analyze images and return numerical vectors that represent the input images in a 1024-dimensional space.
Recognize over 11,000 concepts including objects, themes, moods and more.
Detect if an image contains concepts such as gore, drugs, explicit nudity or suggestive nudity.
Identify different levels of nudity in visual content and automatically moderate or filter offensive content.
Detect people and vehicles in image and video data.
Detect people in images and video data.
Assign tags to text based on any concept you want to analyze its content.
Detect toxic, obscene, racist or threatening language or train your own custom moderation models.
Identify textures and patterns within an image including glacial, ice, metallic, veined, feathers and more.
Recognize specific features of residential, hotel, and travel-related properties.
Detect vehicles in image and video data.
Recognize over 400 concepts related to weddings including bride, groom, flowers and more.