5
Home
ojrandom edited this page 2024年11月21日 16:58:42 +00:00
Comparison to other Programs
Please feel free to correct this comparison and contribute the result of own tests!
The test was done with Deepface. Digikam and the Darktable addon might use different implementations. At least the results should point into a direction.
What was tested?
81 pictures
- 23 x Brigitte Bardot (3 x are named)
- 51 x Claudia Cardinale (3 x are named)
- 7 x Marylin Monroe (2 x are named)
Used metric: Cosine with the optimized default thesholds provided by Deepface
- dlib: 0.07
- OpenFace: 0.1
- Facenet512: 0.3
| Program | Detector | Model | Pictures | Detected | Named | Recognized | False Positives |
|---|---|---|---|---|---|---|---|
| face_recognition (Darktable) | dlib | dlib | 81 | 110 | 8 | 17 (of 73) | 1 |
| Digikam | yolov8 *1 | OpenFace | 81 | 176 (?) | 8 | 0 (of 73) *2 | 0 |
| Darktable's Face Companion | yolov8 | Facenet512 | 81 | 176 | 8 | 51 (of 73) | 3 |
*1... Digikam uses the outdated yolov3 instead of yolov8.
*2... OpenFace resulted in many false positives if the threshold was increased to recognize more faces.
Summary Darktable's Face Companion Compared
Pros
- Detection and recognition more up-to-date
- Variety of detectors and models available
- Change the method of detection
- Change the method of recognition
- Change the distance metric
- Upgrade of detectors and models if new ones are published (and integrated by Deepface)
- training data can be filtered and sorted by
- confidence (this is a face)
- width of faces relativ to width of picture
- sharpness
- how directly a person looks into the camera
- most similar faces if there are (too) many faces
Cons
- Not integrated in Darktable
Digikam
Digikam comes with a face detection and recognition, see
Pros:
- Integrated in Digkam
- Detection and recognition applied to current collection
- Training data can be filtered by
- noise
- sharpness
- compression
- overall quality (AI feature ?)
Cons:
- Both detection and recognition seem to be quite outdated.
Dartktable's Addon face_recognition
Darktable has the addon face_recognition.
It seems to use
Pros:
- Integrated in Darktable
Cons:
- Both detection and recognition seem to be quite outdated.
- Results can not be confirmed.