|
| << vorige | volgende >> |
Tijdschrift beschrijving
Alle jaargangen van het bijbehorende tijdschrift
Alle afleveringen van het bijbehorende jaargang
Alle artikelen van de bijbehorende aflevering
Details van artikel 50 van 89 gevonden artikelen
| Titel: |
Fast Template-based Face Detection Algorithm Using Quad-tree Template |
| Auteur: |
Chang-Woo Park Mignon Park |
| Verschenen in: |
Journal of applied sciences |
| Paginering: | Jaargang 6 (2006) nr. 4 pagina's 795-799 |
| Jaar: |
2006 |
| Inhoud: |
Machine recognition of faces from still and moving images is emerging as an active research area spanning several research fields such as image processing, pattern recognition, computer vision and communication. In addition, human face detection, recognition and identification techniques have numerous applications such as human interface based systems and real-time video systems for surveillance and security, etc. In this study, we suggest an algorithm for face detection from 2D color images using the quad-tree deformable template matching method. The deformable template matching method is used to find the face area and locate facial features. In order to make the algorithm insensitive to luminance, we convert the conventional RGB coordinates into the normalized CIE coordinates. The face detection procedure can speed-up under limited conditions and we also modify the algorithm for fast detection using the quad-tree hierarchical template of the face. The quad-tree template can easily and quickly sizable and the comparison between the template and the image is weighted according to the deviation of color. The template comparison results with the plain texture template and the quad-tree template are shown in this study. |
| Uitgever: |
Asian Network for Scientific Information, Pakistan (provided by DOAJ) |
| Bronbestand: |
Elektronische Wetenschappelijke Tijdschriften |
Details van artikel 50 van 89 gevonden artikelen
| << vorige | volgende >> |