Automatic Detection of Facial Midline And Its Contributions To Facial Feature Extraction
We propose a novel approach for detection of the facial midline from a frontal face image. Using midline as a guide reduces computational cost required for facial feature extraction (FFE) because the midline is capable of restricting multi-dimensional searching process into one-dimensional search. T...
| Autores: | , , , |
|---|---|
| Formato: | artículo |
| Fecha de publicación: | 2007 |
| País: | España |
| Recursos: | Universitat Autònoma de Barcelona |
| Repositorio: | Dipòsit Digital de Documents de la UAB |
| Idioma: | inglés |
| OAI Identifier: | oai:ddd.uab.cat:24591 |
| Acesso em linha: | https://ddd.uab.cat/record/24591 https://dx.doi.org/urn:doi:10.5565/rev/elcvia.142 |
| Access Level: | acceso abierto |
| Palavra-chave: | Mitja línia facial Detecció de característica facial Media línea facial Detección de característica facial Facial midline Facial feature detection Generalized Hough transformation Biometrics |
| Resumo: | We propose a novel approach for detection of the facial midline from a frontal face image. Using midline as a guide reduces computational cost required for facial feature extraction (FFE) because the midline is capable of restricting multi-dimensional searching process into one-dimensional search. The proposed method detects the facial midline from an edge image as the symmetry axis using the generalized Hough transformation. Experimental results on the FERET database indicate that the proposed algorithm can accurately detect facial midlines over many different scales and rotation. The total computational time for facial feature extraction has been reduced by a factor of 280 using the midline detected by this method. |
|---|