Accesso libero

Research on face feature point detection algorithm under computer vision

Dan Li

Dan Li

School of Information Engineering, Shaanxi Polytechnic InstituteXianyang, China
Cerca questo autore su
Sciendo|Google Scholar
Li, Dan
 e 
Yanfen Jiang

Yanfen Jiang

Hebei Vocational University of Industry and TechnologyShijiazhuang, China
Cerca questo autore su
Sciendo|Google Scholar
Jiang, Yanfen
  
19 mar 2025
Research on face feature point detection algorithm under computer vision's Cover Image
INFORMAZIONI SU QUESTO ARTICOLO
Articolo precedente
Articolo Successivo
Cita
Scarica la copertina
Pubblicato online: 19 mar 2025
Ricevuto: 07 nov 2024
Accettato: 16 feb 2025
DOI: https://doi.org/10.2478/amns-2025-0503
Parole chiave
© 2025 Dan Li et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Training block diagram of cascade regression algorithm
Training block diagram of cascade regression algorithm

Figure 2.

Test block diagram of cascade regression algorithm
Test block diagram of cascade regression algorithm

Figure 3.

The training manner of conventional CR
The training manner of conventional CR

Figure 4.

Parallel update method based on mixed Gaussian distribution sampling
Parallel update method based on mixed Gaussian distribution sampling

Figure 5.

Comparison of average relative positioning errors of face feature points
Comparison of average relative positioning errors of face feature points

Figure 6.

Cumulative relative error distribution curve and comparison
Cumulative relative error distribution curve and comparison

Figure 7.

Detection rate of each feature point on LFW face data set
Detection rate of each feature point on LFW face data set

Figure 8.

Pupil precision location map
Pupil precision location map

Face detection module evaluation

Test set Forward propagation time/ms Detection time/ms
AFW 7.39 10.76
PASCAL Faces 7.25 12.28
FDDB 7.48 11.68
CASIA-WebFace 7.27 10.80
WIDER Face 7.42 11.59
MALF 7.36 12.15
Lingua:
Inglese
Frequenza di pubblicazione:
1 volte all'anno
Argomenti della rivista:
Scienze biologiche, Scienze della vita, altro, Matematica, Matematica applicata, Matematica generale, Fisica, Fisica, altro
Feed RSS della rivista