• Face Embedding

    Analyze images and returns numerical vectors that represent each detected face in the image in a 1024-dimensional space. The vector representation is computed by using Clarifai’s ‘Face Detection’ model. The vectors of visually similar faces will be close to each other in the 1024-dimensional space. The ‘Face Embedding’ model can be used for organizing, filtering, and ranking images according to visual similarity.

    Request a demo
  • Model Information

    Model ID: 240a8f047a6ef4328331b5c6fb3952ca

    Model Name: people-vehicle-detector-v1 Model

    Type ID: visual-detector

    Owner: Clarifai

  • or
    Start now for free

     

    5,000 free operations per month.

  • Request

    You can call the Predict API with the 'Face Embedding' model. Simply pass in an image input with a publicly accessible URL or by directly sending image bytes.

    Learn more about the Predict API.
    API Guide

  • Response

    The Predict API returns an array of regions. Each region element has bounding box coordinates for each face detected as well as a data object containing a ‘vector’ and ‘num_dimensions’.

    The returned ‘bounding_box’ values are the coordinates of the box outlining each face within the image. They are specified as float values between 0 and 1, relative to the image size; the top-left coordinate of the image is (0.0, 0.0), and the bottom-right of the image is (1.0, 1.0). If the original image size is (500 width, 333 height), then the box above corresponds to the box with top-left corner at (208 x, 83 y) and bottom-right corner at (175 x, 139 y). Note that if the image is rescaled (by the same amount in x and y), then box coordinates remain the same. To convert back to pixel values, multiply by the image size, width (for “left_col” and “right_col”) and height (for “top_row” and “bottom_row”).

    The ‘vector’ is a numerical vector that represents the face detected in a 1024-dimensional space. The numerical values within the vectors are between 0 and 1, inclusive. The vectors of visually similar faces will be close to each other in the 1024-dimensional space. The ‘num_dimensions’ for this model is set at 1024.

Endless possibilities with Computer Vision and AI

Gather valuable business insights from images, text and data using machine learning, natural language processing and computer vision.

  • Ready-to-use Models
  • Text moderation

    Detect toxic, obscene, racist, or threatening language, or your own custom moderation models.

    Try it out
  • Text embedding

    Assign tags or categories to analyze text based on content. Build models for topic analysis, sentiment analysis, smart reply and more.

    Try it out
  • Image moderation

    Identify unwanted content such as gore, drugs, explicit nudity or suggestive nudity.

    Try it out
  • General

    Recognize over 11,000 different concepts including objects, themes, moods and more.

    Try it out
  • Custom

    Create your own model and teach it with your own images and concepts.

    Try it out
  • Demographics

    Predict the age, gender or cultural appearances of faces.

    Try it out
  • Face detection

    Detect the location of faces with bounding boxes.

    Try it out
  • Celebrity

    Analyze images and return probability scores on the likelihood that the media contains the face(s) of over 10,000 recognized celebrities.

    Try it out
  • Apparel detection

    Detect items of clothing or fashion-related items.

    Try it out
  • Face embedding

    Analyze images and returns numerical vectors that represent each detected face in the image in a 1024-dimensional space.

    Try it out
  • Food

    Recognize more than 1,000 food items in images down to the ingredient level.

    Try it out
  • Color

    Identify the dominant colors present in your images in hex or W3C form.

    Try it out
  • Textures and patterns

    Recognize textures and patterns in a two-dimensional image e.g., feathers, woodgrain, petrified wood, glacial ice and overarching descriptive concepts (veined, metallic).

    Try it out
  • Not safe for work

    Identify different levels of nudity in your visual data. Ideal for moderating and filtering offensive content from your platform.

    Try it out
  • Travel

    Recognize specific features of residential, hotel, and travel-related properties.

    Try it out
  • Wedding

    Recognize over 400 concepts related to weddings including bride, groom, flowers and more.

    Try it out
  • General embedding

    Analyze images and returns numerical vectors that represent each detected face in the image in a 1024-dimensional space computed by our General model.

    Try it out
  • Model gallery

    Explore our pre-built, ready-to-use image recognition models to suit your specific needs.

    Learn more
  • Ready to get started?

    Whether you're a start-up or a Fortune 500, we'd like to discuss a personalized plan that fits your business use cases.

    Learn more about Clarifai

    Schedule a demo

    Discuss your solutions options

  • or
    Start now for free

     

    1,000 free operations per month.

  • Already a customer?

    If you're encountering a technical or payment issue, the customer support team will be happy to assist you.

    Contact support