Skip to content

Face Recognition Tab

Face recognition allows Fast Video Cataloger to automatically detect faces in video thumbnails and match them to actors in your catalog. To enable faces an actor for face detection you need to Generate Embeddings from the edit actors dialog. You can generate embeddings from the portrait but also from selected companion images. The quality of the portraits will determine to a high degree how good the facial detection will work.

Face Recognition -- When checked, faces are automatically detected and matched to actors during video indexing.

Min frame confidence -- Minimum confidence for a single frame match to count. Faces with lower confidence in individual frames are ignored. Value between 0.0 and 1.0.

Avg confidence threshold -- Average confidence across all matching frames required to tag an actor. Higher values reduce false positives. Value between 0.0 and 1.0.

Min frames required -- An actor must appear in at least this many frames to be tagged. Higher values reduce false positives. Value between 1 and 100.

Frame skip -- Skip N thumbnails between each processed frame. Set to 1 to process all frames, higher values for faster processing. Value between 1 and 100.

Face detector -- Selects the face detection method. Two options are available:

  • HOG (Histogram of Oriented Gradients) -- Faster processing, works well for clear front-facing shots, but may miss faces at angles or in poor lighting. Good for quick scans of large batches.
  • CNN (Convolutional Neural Network) -- Slower but more accurate. Better at finding faces at various angles and more robust to lighting variations. Recommended for thorough detection.

Parallel instances -- Number of parallel face recognition instances. Higher values use more memory but process faster. Set to 0 for auto, which uses the CPU core count. Each instance uses approximately 100 MB of RAM.