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. Before an actor can be recognized you need to learn their face: open the Edit Actor dialog, select one or more companion images that clearly show the actor's face, and click Learn Face. The quality and variety of these photos largely determine how well recognition works -- see Face Recognition for details and tips.

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 of the best 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) -- Runs the CNN detector on every frame in addition to HOG and combines the results. Finds faces at angles and in difficult lighting that HOG misses, but detection is much slower. 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.