We describe a face detection algorithm, which characterizes and localizes skin regions and eyes in 2D images using color information and Support Vector Machine. The method is scale-independent, works on images of either frontal, rotated faces, with a single person or group of people, and does not require any manual setting or operator intervention. The algorithm can be used in face image database management systems both as a first step of a person identification, and to discriminate the images on the basis of the number of faces in them.
A face detection system based on color and support vector machines / E. Casiraghi, R. Lanzarotti, G. Lipori (LECTURE NOTES IN COMPUTER SCIENCE). - In: Neural Nets : 14th Italian Workshop on Neural Nets, WIRN VIETRI 2003, Vietri sul Mare, Italy, June 4-7, 2003 : revised papers / [a cura di] B. Apolloni, M. Marinaro, R. Tagliaferri. - Berlin : Springer, 2003. - ISBN 9783540202271. - pp. 113-120 (( Intervento presentato al 14. convegno Italian Workshop on Neural Networks tenutosi a Vietri sul Mare, Italy nel 2003 [10.1007/978-3-540-45216-4_12].
A face detection system based on color and support vector machines
E. Casiraghi;R. Lanzarotti;G. Lipori
2003
Abstract
We describe a face detection algorithm, which characterizes and localizes skin regions and eyes in 2D images using color information and Support Vector Machine. The method is scale-independent, works on images of either frontal, rotated faces, with a single person or group of people, and does not require any manual setting or operator intervention. The algorithm can be used in face image database management systems both as a first step of a person identification, and to discriminate the images on the basis of the number of faces in them.File | Dimensione | Formato | |
---|---|---|---|
978-3-540-45216-4_12.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
170.17 kB
Formato
Adobe PDF
|
170.17 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.