Malerhände

Features

Face detection

• deepface
  • dlib
  • mtcnn
  • mediapipe
  • opencv
  • retinaface
  • ssd
  • yolov8
  • yunet
• insightface (also reimplemnted by deepface retinaface, but taht is worse)

Only insightface does properly report the face landmarks. It's also the best performing so we use that.

This topic is described in paper_humanities_wenzelfacedetection.

Face comparison features

• VGG-Face
• Facenet
• Facenet512
• OpenFace
• DeepFace
• DeepID
• ArcFace
• Dlib
• SFace
• GhostFaceNet

Other comparison features

• ccv
• lbp
• lpips

Data

Face are detcted with insightface (Tiles with 3000 tilesize, scale factor 1, and rotation factor 0° and ±45°) and face landmarks (for alignment are stored). Tags come from the groundtruth if it can be matched with detected faces.

Transform

Derived from that we have two basic extractions, normal (no tag) and transformed (t).

normal	transformed

Context

This is the additional image information around the face which is included in the extracted image, either with 50 pixel context on each side from the source image (c50) or no additional context (nc), see above for nc examples.

c50	c50t

Selectors

All have ground truth from those we selected only 'Wenzel' for the following tests. Codex 2759 (the first book) is used.