Face Identity Extractor
Detect, align, and embed faces to 512-D ArcFace vectors across image, video and PDF, using SCRFD for detection.
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 StudioFace 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 →Related to Face Identity Extractor
Pages on the same stages, extractors and patterns.
Face Search Pipeline
Detect, align, and embed faces across your image and video library, then search by face identity. Uses SCRFD for detection and ArcFace for 512-dimensional identity embeddings, enabling large-scale face recognition and matching.
Image Embedding
Generate visual embeddings for similarity search and clustering
Image Similarity Search Pipeline
Deploy a visual search engine that finds similar images using state-of-the-art embedding models. Perfect for product catalogs, stock photo libraries, and visual discovery.
Automatic Image Tagging Pipeline
Automatically tag images with objects, scenes, colors, and custom labels using computer vision models. Perfect for DAM systems and media libraries.
E-commerce Product Image Analytics
Analyze product images across your catalog to extract visual attributes, identify trends, detect quality issues, and benchmark against competitors.
Reverse Image Search
Build a reverse image search engine that accepts an image as input and returns visually similar results from your indexed collection. Uses multimodal embeddings to match visual features like color, shape, composition, and semantic content.