NEWVectors or files. Pick a path.Start →
    Image

    Face Identity Extractor

    Detect, align, and embed faces to 512-D ArcFace vectors across image, video and PDF, using SCRFD for detection.

    v1 · 5 cr/image, 5 cr/face
    Note: This playground provides simulated output to showcase functionality. No input data is processed or stored on our servers. Use this demo to explore the feature extractor's capabilities before integrating it into your application.

    Input

    Enter a URL to a image file

    Drag and drop a image file here, or click to browse

    Output

    {
      "face_identity_extractor_v1_embedding": "ArcFace face embedding (512-d L2-normalized vector). Use cosine similarity for face matching. Similarity > 0.25-0.30 indicates same person.",
      "face_index": "Index of this face in source image (0-based)",
      "bbox": "Face bounding box {x1, y1, x2, y2, width, height}",
      "detection_score": "SCRFD detection confidence (0.0-1.0)",
      "landmarks": "5 facial landmarks for alignment",
      "quality_score": "Face quality score (0.0-1.0)",
      "quality_components": "Quality component scores",
      "face_crop_url": "S3 URL of aligned 112×112 face crop JPEG",
      "aligned_face_crop": "Base64 aligned 112×112 face crop",
      "source_frame_thumbnail": "Base64 resized source frame thumbnail for display with bbox overlay",
      "source_frame_width": "Original source frame width in pixels",
      "source_frame_height": "Original source frame height in pixels",
      "frame_number": "Frame number in source video",
      "timestamp": "Timestamp in source video (seconds)",
      "page_number": "Page number in source PDF (0-based)",
      "embedding_model": "Embedding model used",
      "detection_model": "Detection model used",
      "processing_time_ms": "Processing time (milliseconds)"
    }

    Ready to run Face Identity Extractor on your data? Spin it up in Studio: no infra to host.

    Run this in Studio

    Face Identity Extractor: common questions

    What is the Face Identity (SCRFD + ArcFace) extractor used for?
    Employee verification, photo organization, face clustering, surveillance, identity systems.
    When should I not use Face Identity (SCRFD + ArcFace)?
    General image search (use image_extractor), object detection (use multimodal_extractor). Reach for it when you need face search, person re-identification across footage, and cast/talent indexing.
    How much does the Face Identity (SCRFD + ArcFace) extractor cost?
    5 cr/image, 5 cr/face. Credits are billed per unit processed; see mixpeek.com/pricing for the credit rate.
    What file types does Face Identity (SCRFD + ArcFace) support?
    Image, Video, PDF. It produces embeddings from insightface__arcface.

    Already have embeddings? Skip extraction: search your own vectors with MVS, from $25/mo for up to 1M vectors.

    Try MVS →